A PROJECT REPORT ON

“Lane Line Detection Algorithm for Self-Drive Cars”

SUBMITTED TO SAVITRIBAI PHULE PUNE UNIVERSITY, PUNE
IN THE PARTIAL FULFILLMENT FOR THE AWARD OF THE DEGREE
OF
BACHELOR OF ENGINEERING
IN
COMPUTER ENGINEERING

SUBMITTED BY

SAURABH AHIRE SEAT NO: B150624204

PRATIK CHANDORE SEAT NO: B150624217
YASHODA GAVIT SEAT NO: B150624225
YOGESH KHALANE SEAT NO: B150624235

UNDER THE GUIDANCE OF

PROF. S. S. BANNE

DEPARTMENT OF COMPUTER ENGINEERING

BRAHMA VALLEY COLLEGE OF ENGINEERING & RESEARCH

INSTITUTE ANJANERI, TRIMBAK ROAD, NASHIK - 422213

SAVITRIBAI PHULE PUNE UNIVERSITY

2021-2022
 CERTIFICATE

This is to certify that the Project Report Entitled

“Lane Line Detection Algorithm for Self-Drive Cars”

Submitted By
Saurabh Ahire Seat No: B150624204
Pratik Chandore Seat No: B150624217
Yashoda Gavit Seat No: B150624225
Yogesh Khalane Seat No: B150624235

Is a bonafide work carried out by them under the supervision Prof. S. S. Banne of and it
is submitted towards the partial fulfillment of the requirement of Savitribai Phule Pune
University, Pune for the award of the degree of Bachelor of Engineering (Computer
Engineering).

Prof. S. S. Banne Prof. S. S. Banne

Project Guide Project Coordinator

Prof. V. D. Badgujar Dr. H. N. Kudal

Head of Dept. Principal

Brahma Valley College of Engineering & Research Institute, Nashik - 422213

Place : Nashik
Date :
 ACKNOWLEDGEMENT

It is a great pleasure in presenting the preliminary project report on ‘Lane line detection
algorithm for self-driving car’. We would like to take this opportunity to thank our
internal guide Prof. S. S. Banne & Head of Department Prof. V. D. Badgujar for giving
us all the help and guidance we needed. So really grateful to him for their kind support.
Their valuable suggestions were very helpful. We are thankful to management and Dr.
H. N. Kudal Principal of our college. We are thankful to our family members for
supporting and to encourage us and for providing their guidance, for Our Project. In the
end our thanks to all friends’ colleagues for providing their useful suggestions which
contributed greatly in making our project successful.

Saurabh Ahire Seat No: B150624204

Pratik Chandore Seat No: B150624217

Yashoda Gavit Seat No: B150624225

Yogesh Khalane Seat No: B150624235

 ABSTRACT

Being able to detect lane lines could be a crucial task for any self-driving autonomous
vehicle. In this project, to identify lane lines on the road OpenCV is used. OpenCV
method uses the input images to find any lane lines command among and also for
rendering out an illustration of the lane. The OpenCV tools like color selection, the region
of interest selection, grey scaling, Gaussian smoothing, Canny Edge Detection, and
Hough Transform line detection are being employed. A color detection algorithm
identifies pixels in a picture that matches a given color or color range. Region of interest
selection allows you to select a rectangle in an image, crop the rectangular region and
finally display the cropped image. Grey scaling is the method of changing an image from
different color spaces e.g., RGB, CMYK, HSV, etc. to shades of gray.

In Gaussian Blur operation, the image is converted with a mathematician filter

rather than the box filter. The Gaussian filter could be a low-pass filter that removes the
high-frequency elements. Canny Edge Detection is used to detect the edges in a picture.
It accepts a grayscale image as input and it uses a multi-stage algorithm. The Hough
Transform line is a method that is used in image processing to detect any shape if that
shape can be represented in mathematical form. The goal is to piece along a pipeline to
detect the line segments within the image, then average/extrapolate them and draw them
onto the image for the show.

Keywords: Lane Line Detection, Hough Transform, Canny Edge Detection Algorithm
 CONTENTS

Chapter Topic Page

No. No.
1. INTRODUCTION 1
1.1 Overview………………………………………………............. 1
1.2 Motivation…….……………………………………………….. 2
1.3 Problem Definition and Objectives…………..……………….. 2
1.4 Project Scope & Limitations………………………………....... 3
1.5 Methodologies of Problem solving………………………......... 4
2. LITERATURE SURVEY 5
3. SOFTWARE REQUIREMENTS SPECIFICATION 7
3.1 Assumptions and Dependencies………………………………. 7
3.2 Functional Requirements……………………………………… 7
3.2.1 System Feature 1…………………………...……………. 7
3.3 External Interface Requirements.………..…………………….. 7
3.3.1 User Interfaces…………………………………………... 7
3.3.2 Software Interfaces……………………………………… 8
3.4 Nonfunctional Requirements………………………………….. 8
3.4.1 User Interfaces…...……………………………………… 9
3.4.2 Safety Requirements…………………………………….. 10
3.4.3 Software Quality Attributes…………………...………… 10
3.5 System Requirements………………………………………….. 11
3.5.1 Software Requirements……………………..…………… 11
3.5.2 Hardware Requirements…………………………………. 12
3.6 Analysis Models: SDLC Model to be Applied………………... 12
4. SYSTEM DESIGN 14
4.1 System Architecture……...……………………………………. 14
4.2 Mathematical Model……………………………………........... 16
4.3 Data Flow Diagrams……………………………………........... 18
4.4 Entity Relationship Diagrams…………………………………. 19
 4.5 UML Diagrams……………………………………................... 21
5. PROJECT PLAN 24
5.1 Project Estimate…..……...……………………………………. 24
5.1.1 Reconciled Estimates…..……...………………………… 24
5.1.2 Project Resources…..……...…………………………….. 25
5.2 Risk Management………………………………………........... 25
5.2.1 Risk Identification……………………………………….. 25
5.2.2 Risk Analysis………………………………………......... 27
5.2.3 Overview of Risk Mitigation, Monitoring, Management.. 28
5.3 Project Schedule…...……………………………………........... 28
5.3.1 Project Task Set………………………………………..... 28
5.3.2 Task Network………………………………………......... 30
5.3.3 Timeline Chart………………………………………....... 30
5.4 Team Organization………….…………………………………. 31
5.4.1 Management Reporting and Communication…………… 31
6. PROJECT IMPLEMENTATION 33
6.1 Overview of Project Modules…………………………………. 33
6.2 Tools and Technologies Used…………………………………. 33
6.3 Algorithm Details..………….…………………………………. 35
6.3.1 Algorithm 1..………….…………………………………. 35
6.4 Screenshots And Outputs..………….…………………………. 37
7. CONCLUSIONS 42
7.1 Conclusions……………………………………………………. 42
7.2 Future Scope…………...……………………………………… 42
7.3 Applications……………….…………………………………... 42
8. REFERENCES 44
9. APPENDIX………………………………………………........... 45
Appendix A………………………………………………………... 45
Appendix B………………………………………………………... 57
 LIST OF FIGURES

Figure No. Title Page No.

3.1 Waterfall Model……………………………………………........ 12
4.1 System Architecture…………………………………………...... 14
4.2 Mathematical Model……….………………………………........ 17
4.3 Data Flow Diagram 01………………..………………………… 18
4.4 ER-Diagram 01……………………..…………………………... 19

4.5 ER-Diagram 02……………………..…………………………... 20

4.6 Component Diagram…………………………..……………....... 21

4.7 Activity Diagram…...………………………………………....... 21
4.8 Sequence Diagram…………………………………………........ 22

4.9 Use-Case Diagram …………………………………………....... 23

5.1 Task Network……………..…………………………………….. 29

5.2 Timeline Chart………………………………………………….. 30
6.1 Canny Edge Detection Algorithm …...…...…………………….. 35
6.2 Selected Testing Image So That It Undergoes into Process……. 37
6.3 Grey Scaled Image Output of a Selected Image………………... 37
6.4 Gaussian Filtered Image After Gaussian Kernel Sliding……….. 38
6.5 Edges Detected Image by Canny Edge Detection Process……... 38
6.6 The Masked Image with Considering Only the Required Road
for Vehicle Movement………………………………………….. 39
6.7 Output of Detected Road from Image Captured by Vehicle…… 39
6.8 Code of Canny Edge Detector………………………………….. 40
6.9 Code of Region Selection………………………………………. 40
6.10 Code of RGB Color Selection………………………………….. 41
6.11 Code of Main Algorithm………………………………………... 41
 LIST OF TABLES

Table No. Title Page No.

3.1 Software Requirement…………...……………………………... 11
3.2 Hardware Requirement…..…………………………………....... 12
5.1 Risk Table……...……………………………………………….. 27
5.2 Risk Probability Definitions….……………………………........ 27
5.3 Risk Impact Definitions……...…………………………………. 27
5.4 Risk for Development Environment….………………………… 28
5.5 Risk for Requirement……...……………………………………. 28
5.6 Risk for Technology……...…………………………………….. 29
Chapter 1 Introduction
______________________________________________________________________

Chapter 1

INTRODUCTION

1.1 Overview

The main aim of this project is to design and construct a lane line detection Algorithm for
self-driving cars. Lane line detection is the process of detecting lanes of the road via the
automate system of the car which is using camera, cancers and process the information in
computing unit of the computer of the car.

Lane detection is an important component of intelligent transportation systems. First,

lane marks are extracted based on color information and the resultant binary image with
Canny line detection. Next, the perspective transformation and define the Region of
Interest (ROI) helps eliminate irrelevant elements in the image. The starting points of lane
lines can be roughly determined by calculating the histogram of the binary image. Finally,
the pixels of lane lines are detected by applying sliding windows from detected starting
points. The proposed algorithm can be used to detect lane lines on both images and videos.
The main aim of this project is to design and construct a lane line detection.

Algorithm for self-driving cars. Lane line detection is the process of detecting lanes
of the road via the automate system of the car which is using a camera, cancers and
processes the information in the computing unit of the computer of the car.

Traffic accidents have become one of the most serious problems in today’s world.
Roads are the mostly chosen modes of transportation and provide the finest connections
among all modes. Most frequently occurring traffic problem is the negligence of the
drivers and it has become more and more serious with the increase of vehicles. Increasing
the safety and saving lives of human beings is one of the basic functions of Intelligent
Transportation System (ITS). Intelligent transportation systems are advanced applications
which aim to provide innovative services relating to different modes of transport and
traffic management. This system enables various users to be better informed and make
safer, more coordinated, and smarter use of transport networks. These road accidents can
be reduced with the help of road lanes or white markers that assist the driver to identify
_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 1
Chapter 1 Introduction
______________________________________________________________________
the road area and non-road area. A lane is a part of the road marked which can be used
by a single line of vehicles asto control and guide drivers so that the traffic conflicts can
be reduced.

1.2 Motivation

➢ Lane Line detection is a critical component for self-driving cars and also for
computer vision in general. This concept is used to describe the path for self-
driving cars and to avoid the risk of getting in another lane.
➢ Using computer vision techniques in Python, we will identify road lane lines in
which autonomous cars must run. This will be a critical part of autonomous cars,
as the self-driving cars should not cross its lane and should not go in opposite
lane to avoid accidents.
➢ To detect white markings in the lane, first, we need to mask the rest part of the
frame. We do this using frame masking. The frame is nothing but a NumPy array
of image pixel values. To mask the unnecessary pixel of the frame, we simply
update those pixel values to 0 in the NumPy array.
➢ After making it we need to detect lane lines. The technique used to detect
mathematical shapes like this is called Hough Transform. Hough transformation
can detect shapes like rectangles, circles, triangles, and lines.

1.3 Problem Definition and Objectives

➢ Problem Statement
This project is based on converting the audio signals received to text using speech
to text api (python modules or google api) and then using the semantics of Natural
Language Processing to breakdown the text into smaller understandable pieces
which requires. Machine Learning as a part. Data sets of predefined sign language
are used as the input so that the software can use artificial Intelligence to display
the converted audio into the sign language.
➢ Goals and objectives
• To provide the safe riding experience.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 2
Chapter 1 Introduction
______________________________________________________________________

• To develop a scalable project which can be extended to capture the lane line
on the road in tough conditions.
• The aim of this thesis is to avoid accidental deaths and provide a better safety
on roads, by use of advanced technologies in driving assistance system. The
clear idea of the important aims and objectives of this thesis is explained with
the help of block diagram.

1.4 Project Scope And Limitation

➢ Real-time and robustness are the purpose of lane detection. When the vehicle is
driving at a certain speed, the road image collected must be processed in time to
ensure the normal driving of the vehicle. The entire lane line detection system not
only needs to adapt to the complicated and changeable road environment but also
adapts to the influence of some force majeure factors.
➢ Most existing lane line detection algorithms are mainly designed for structured
roads and not structured roads, due to the influence of the surrounding
environment of the road, such as the influence of shadows of surrounding trees
or buildings and the pair of vehicles ahead of the road. The influence of the lane
line shielding, etc. makes the detection of the lane line very poor.
➢ When affected by other markers on the driveway, or when the lane is damaged or
the pollution is serious, the image of the lane line collected by the system is
incomplete and of poor quality, making it difficult for the system to accurately
judge and analyze the data, and it is impossible to guarantee the correctness of
the data and real-time detection of lane lines.
➢ Unclear detection and multi-peak detection problems are the biggest problems
faced by traditional Hough transforms and are severely affected by noise. After
the Hough transform is improved, the robustness and adaptability of the detection
result are enhanced. In order to overcome the weather changes and the camera
lens is not clean, this paper uses the two-dimensional median filtering method to
process the original image.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 3
Chapter 1 Introduction
______________________________________________________________________

1.5 Methodologies of Problem Solving

➢ Visual input on a Doc Camera, and process these images using python modules.
➢ We firstly extract the color features based on the white color and then extract the
edge features based on the straight lane. Because the high-speed section is the
traffic accident-prone section, the high-speed road section mostly is the straight-
line lane. Therefore, in order to obtain a very high recognition rate, we
successively carry-on color detection and edge detection to the lane. This paper
combines color features extraction and edge features extraction, and the
experiment proves that the recognition rate and accuracy of lane detection are
greatly improved.
➢ Our main contribution in this paper is to do a lot of work in the pre-processing
stage. We proposed to perform color transform of HSV in the pre-processing
stage, then extract white, and then perform conventional pre-processing
operations in sequence. Moreover, we selected an improved method proposed in
the area of interest (ROI). In this paper, based on the proposed pre-processing
method, one-half part of the processed image is selected as the area of interest. In
addition, we performed twice edge detection. The first is in the pre-processing
stage, and the second is in the lane detection stage after the ROI is selected. The
purpose of performing twice edge detection is to enhance the lane recognition
rate.

Outcome:

• A lane line visual on the live screen on the car display monitor.
• A tool which has a wide range of lane line detection using some python libraries.
• These systems which showcase the ability to see what human can’t see is beyond
the limitation of human being.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 4
Chapter 2 Literature Survey
______________________________________________________________________

Chapter 2

LITERATURE SURVEY

➢ Saha et al. [2012] [1] discussed an algorithm for detection of marks of road lanes
and road boundary by using intelligent vehicles. It converted the RGB road scene
image into gray image and employed the flood-fill algorithm to label the connected
components of that gray image. After that the largest connected component obtained
by the algorithm and which was the road region was extracted. The unwanted region
was detected and subtracted like outer-side of the road. The extracted connected
component was filtered to detect white marks of road lane and road boundary. The
road lane detection algorithm still had some problems such as critical shadow
condition of the image and color of road lanes other than white.
➢ Tseng et al. [2005] [2] gave a lane marking detection algorithm by using geometry
information and modified Hough transform. In that algorithm the captured image
was divided into road part and non-road part by using camera geometry information.
The color road image was quantized into a binary image. The modified Hough
transform with road geometry consideration was used to detect the lane markings. The
histogram of intensities was applied to quantize the road image into a binary image.
A modified Hough transform method has been developed to detect the lane markings
in road image by using the road geometry information. It was time consuming because
Hough transform was a full search algorithm in parameter space. It also failed when
the lane boundaries intersected in a region which was a non-road part.
➢ Shen et al. [2012] [3] discussed a monocular vision system that could locate the
positions of the road lane in real time. An algorithm proposed for lane detection
using single camera. The algorithm worked in five steps. Initially edge detection was
done to find all present edges from road image as road line required was included in
it. Canny approach has been used to achieve the edge map from road image for its
accurate edge detection. Then matching was done to eliminate unwanted figures. A
priority and orientation-based searching method has been used for enhance and label
potential lane segments from edge map, degrading unwanted edge features. Based on
results from search, a linking condition was used to assemble matched segment that
_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 5
Chapter 2 Literature Survey
______________________________________________________________________
further strengthen the confidence of the potential lane line. Finally, a cluster algorithm
was used to localize the road-lane lines.
➢ M. Dhana Lakshmi et al. [2012] [4] discussed a novel algorithm to detect white-
and yellow-colored lanes on the road. An automatic lane marking violence detection
algorithm was designed and implemented in real time. The lane detection method was
robust and effective in finding the exact lanes by using both color and edge
orientations. The color segmentation procedure identified the yellow and white
colored lanes followed by edge orientation in which the boundaries was eliminated,
regions was labeled and finally the lanes was detected. As the height of the camera
was relatively constant with respect to the road surface, the road portion of the image
can be exclusively cropped by providing the coordinates, so that identifying the lanes
became much more efficient.
➢ Cuong Le et al. [2012] [5] discussed the task of finding the pedestrian lanes that
are indicated by painted markers for the vision impaired people. An assistive
navigation system has been developed for the blind by employing geometric figures
like straight line, parabola, or hyperbola. By combining color and local intensity
information, this method detected correctly pedestrian marked lanes in different
illumination and weather conditions (sunny, cloudy, strong shadows, times of day).
This method has also been evaluated and compared with existing approaches. It has
been found that the potential of the method in challenging environmental conditions.
➢ Shan Xu et al. [2012] [6] discussed a method of structured road lane detection
for blind travel aid. Median Filter has been implemented to process image firstly,
then mark off the region of interesting in the initial image. Using Canny Edge
Enhancement, threshold has been used to segment the image; road lane was fitted by
modified Hough Transformation. Finally, according to the detected region, it judged
whether racing course of bind has a deviation. It has been proved that this algorithm
was very robust and real-time.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 6
Chapter 3 Software Requirement Specification
______________________________________________________________________

Chapter 3

SOFTWARE REQUIREMENT SPECIFICATION

3.1 Assumptions and Dependencies

1. System is well performed if proper Wi-Fi is provided
2. Navigation Logs
3. Notifications
4. Car Dash Board Camera
5. System Monitor

3.2 Functional Requirements

3.2.1 System Feature 1
• Detect the Lines
• Detect the Color of Line
• Select the appropriate line

3.3 External Interface Requirements

3.3.1 User Interfaces
User has to interface with system to access the features and to analyze the line
detection from the system monitor.

Applications
• Robotics
• Laboure Charge Reduction
• Virtual Motion (Gaming)
• Transport

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 7
Chapter 3 Software Requirement Specification
______________________________________________________________________
3.3.2 Software Interface
• Anaconda (Jupyter Notebook)
Anaconda is a distribution of the Python and R programming languages
for scientific computing, that aims to simplify package management and
deployment. The Jupyter Notebook, an open-source, web-based IDE with
deep cross-language integration that allows you to create and share
documents containing live code, equations, visualizations, and narrative
text. Data scientists and engineers love using Jupyter for data cleaning and
transformation, statistical modeling, visualization, machine learning, deep
learning, and much more. Jupyter Notebook’s format (ipynb) has become
an industry standard.

Benefits of Anaconda are as follows:

• It is free and open-source.

• It has more than 1500 Python/R data science packages.
• Anaconda simplifies package management and deployment.
• A high-level data manipulation language.
• It has tools to easily collect data from sources using machine learning and
AI.
• It creates an environment that is easily manageable for deploying any
project.
• Anaconda is the industry standard for developing, testing and training on
a single machine.
• It has good community support- you can ask your questions there.

3.4 Nonfunctional Requirements

A Software requirements specification (SRS), a requirements specification for a software

system is a complete description of the behavior of a system to be developed and may
include a set of use cases that describe interactions the users will have with the software.
In addition, it also contains non-functional requirements. Non- functional requirements

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 8
Chapter 3 Software Requirement Specification
______________________________________________________________________
impose constraints on the design or implementation (such as performance engineering
requirements, quality standards, or design constraints). The software requirements
specification document enlists all necessary requirements that are required for the project
development. To derive the requirements, we need to have clear and thorough
understanding of the products to be developed. This is prepared after detailed
communications with the project team and customer. A software requirements
specification (SRS) is a comprehensive description of the intended purpose and
environment for software under development.

The SRS fully describes what the software will do and how it will be expected to
perform. An SRS minimizes the time and effort required by developers to achieve desired
goals and also minimizes the development cost. A good SRS defines how an application
will interact with system hardware, other programs and human users in a wide variety of
real- world situations. Parameter such as operating speed, response time, availability,
portability, maintainability, footprint, security and speed of recovery from adverse events
are evaluated. Methods of defining an SRS are described by the IEEE (Institute of
Electrical and Electronics Engineers) specification 830 1998. There are many good
definitions of System and Software Requirements Specifications that will provide us a
good basis upon which we can both define a great specification and help us identify
dependencies in our past efforts. There is also a lot of great students on the web about
writing good specifications. the problem is not lack of knowledge about how to create a
correctly formatted specification or even what should go into the specification.

3.4.1 User Interfaces

• Performance Requirement 1
Error message should be displayed.
• Performance Requirement 2
If there is no Visuals show the not found message displayed.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 9
Chapter 3 Software Requirement Specification
______________________________________________________________________
3.4.2 Safety Requirements
Antivirus should be installed. Refers to the technical innovations and
procedures applied to the hardware and operation systems to protect against
deliberate or accidental damage from a defined threat.

• Secure access of confidential data (user’s details). SSL can be used.

• 24 X 7 availability.
• Better component design to get better performance at peak time.
• Flexible service-based architecture will be highly desirable for future
extension.

3.4.3 Software Quality Attributes

• Passionate
The best interpreters are passionate about what they do. The interpretation
business is a people business and to do the job well, an interpreter must
have a passion for helping people. Every day, interpreters facilitate
communication between one or more parties and to do this accurately,
they must be comfortable in any situation.
• Excellent Communicators
Communication is more than spoken, written or signed words. Body
language and facial expressions communicate our thoughts and messages.
Sign language interpreters must read and interpret these non-verbal forms
of communication, and replicate them in form and meaning so the English
speaker can understand the fullness of the message. Being a “people
person” also means that communication skills are perfected as a result of
experiences. Interpreting is a highly stressful, think-on-your feet job
because no two assignments are alike. The more experience an interpreter
has is a testament to how well they handle multiple environments. For
example, in medical settings, interpreters need to understand how to
communicate with the patient’s family members before and after
appointments. They’re also trained to answer questions the medical
professional (speaking person) may have without confusing the Deaf
person.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 10
Chapter 3 Software Requirement Specification
______________________________________________________________________
• Ethical
Like a spoken language interpreter, the interpreter is a medium. This
means they are not involved in the conversation but rather transmit what
is said between speakers. The information discussed during appointments
cannot be revealed outside of the appointment. Everything that is
discussed must remain confidential. The best interpreters are cognizant of
their role and that their actions should not interfere with the word-for-
word, context or meaning of the interpretation. In addition, professional
interpreters are educated in HIPAA regulations. This ensures that they are
mindful of personal information sharing and the privacy laws that
coincide with the healthcare industry. HIPAA and the Code of Ethics set
forth by the Registry of Interpreters for the Deaf are put in place to protect
the Deaf or Hard- of-Hearing person and the interpreter, should an issue
arise.
• Experienced
Interpreters work in legal, medical, education and corporate settings.
Although it can be beneficial to specialize in one area, the demand for an
interpreter is always present. Overall, well-rounded professional
experience and training are what make an interpreter exceptional.

3.5 System Requirements

3.5.1 Software Requirements
Sr. No. Parameter Description

1. Operating System Windows 7 or above /

Anaconda / MIT App Inventory
2. Programming Language Python

Table 3.1 Software Requirements

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 11
Chapter 3 Software Requirement Specification
______________________________________________________________________
3.5.2 Hardware Requirements
Sr. No. Parameter Description

1. Computer System Ram 4 GB, Dual Core or more

2. Source Video Dashboard Camera Video

Table 3.2 Hardware Requirements

3.6 Analysis Models: SDLC Model to be applied Waterfall Model

Fig. 3.1 Waterfall Model

Waterfall Model is also called as the Linear Sequential Life Cycle Model. This model
followed in the sequential order and so we move to next step of development of software.

1. Requirement Gathering and Analysis

In this step of waterfall, we identify what are various requirements are need for our
project such are software and hardware required, database, and interfaces. MySQL
and java version are the requirements of our project.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 12
Chapter 3 Software Requirement Specification
______________________________________________________________________
2. System Design
In this system design phase, we design the system which is easily understood for end
user i.e., user friendly. We design some UML diagrams and data flow diagram to
understand the system flow and system module and sequence of execution. We have
analyse10basepapersforanalysisphase.

3. Design
In implementation phase of our project, we have implemented various module
required of successfully getting expected out come at the different module levels.
With inputs from system design, the system is first developed in small programs called
units, which are integrated in the next phase. Each unit is developed and tested for its
functionality which is referred to as Unit Testing. Design of web screen will be done
in this phase.

4. Testing
The different test cases are performed to test whether the project module is giving
expected outcome in assumed time. All the units developed in the implementation
phase are integrated into a system after testing of each unit. Post integration the entire
system is tested for any faults and failures.

5. Deployments Of System
Once the functional and nonfunctional testing is done, the product is deployed in the
customer environment or released into the market.

6. Maintenance
There are some issues which come up in the client environment. To fix those issues
patches are released. Also, to enhance the product some better versions are released.
Maintenance is done to deliver these changes in the customer environment. All these
phases are cascaded to each other in which progress is seen as flowing steadily
downwards like a waterfall through the phases. The next phase is started only after
the defined set of goals are achieved for previous phase and it is signed off, so the
name “Waterfall Model”. In this model phases do not overlap.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 13
Chapter 4 System Design
______________________________________________________________________

Chapter 4

SYSTEM DESIGN

4.1 System Architecture

Fig. 4.1 System Architecture

Introduction

With the rapid development of science and technology, intelligent cars, as representatives
of intelligent products, have become a hot research topic today. The gradual growth of
the automobile industry has led to a rapid increase in the number of automobiles in India,
but the traffic problem has become increasingly prominent, which seriously threatens
people's travel safety. Autopilot technology is particularly important, and a lot of research
and development have been made at home and abroad. In the Spring Festival of 2018,
Baidu Apollo platform staged the driving charm of unmanned vehicles on the Mubai
Bandra-Worli Sea Link, reflecting the maturity of India’s autonomous driving
technology. Lane line detection technology is the important technology of unmanned
driving. The correctness of the detection directly determines whether the driving is safe.
The basic idea is to obtain the current road information through the on-board camera, and

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 14
Chapter 4 System Design
______________________________________________________________________
use the relevant algorithm to detect the left and right lane lines of the lane (if there is no
lane line on the right, the road edge is detected), finally, the vehicle travel decision is
made. Since unmanned driving is online in real time, the environment in each time slot is
different, so real-time is also important while ensuring the correct rate. At present, based
on the development status at home and abroad, the algorithm of lane line detection can be
roughly divided into two types, which are based on feature and segmentation based on
model. In 2018, Y. Su proposed a robust vanishing point constraint lane detection method
based on stereo platform. This method can detect both straight lane and curve lane without
considering any parameter lane model. C Lee proposed a robust and real-time lane
detection algorithm based on vision. The algorithm has an effective region of interest and
can effectively reduce the high noise level and computation time. The algorithm can
process a gradient cue and a color cue together and a line clustering with scan-line tests
to verify the characteristics of the lane markings. X. W. Wei used improved Hough
transform to realize Lane detection. By controlling the slope of two lanes before and after
comparison, a limitation is made near the previously detected lane line area, set ROI and
perform the search of diagonal pixels to reconstruct the corner part. In this paper, a lane
line detection algorithm based on improved Hough transform is proposed in terms of
real-time performance and accuracy. In order to improve the real time of image
processing and reduce the interference of useless factors in the image, wavelet lifting is
used to process the image to extract low-frequency wavelet coefficients sub-images;
Compared with the traditional gray average binarization algorithm and maximum
entropy binarization algorithm, the binarization image processing based on edge features
can retain more original details of the image, which is conducive to processing the image
obtained under weak illumination intensity; Then the conditional constraints are added to
Hough transform to improve the accuracy and real-time performance of detection;
Finally, the improved Hough transform method is used to detect the lane line to eliminate
the interference line and pseudo-lane line, and the correct lane line is extracted by fitting
the straight line with regression analysis method.

Traffic accidents have become one of the most serious problems in today’s world.
Roads are the mostly chosen modes of transportation and provide the finest connections
among all modes. Most frequently occurring traffic problem is the negligence of the
drivers and it has become more and more serious with the increase of vehicles. Increasing
the safety and saving lives of human beings is one of the basic functions of Intelligent
_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 15
Chapter 4 System Design
______________________________________________________________________
Transportation System (ITS). Intelligent transportation systems are advanced applications
which aim to provide innovative services relating to different modes of transport and
traffic management. This system enables various users to be better informed and make
safer, more coordinated, and smarter use of transport networks. These road accidents can
be reduced with the help of road lanes or white markers that assist the driver to identify
the road area and non-road area. A lane is a part of the road marked which can be used
by a single line of vehicles as to control and guide drivers so that the traffic conflicts can
be reduced.

4.2 Mathematical Model

Smooth the image with a Gaussian filter to reduce noise and unwanted details and
textures.

Where,

The computed edge strengths are compared to the smoothed image in Figure

• Success Conditions:
Camera Embedding, Conversion, Sign Language, Text.
• Failure Conditions:
No data set, fail to read data set.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 16
Chapter 4 System Design
______________________________________________________________________

Fig. 4.2 Mathematical Model

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 17
Chapter 4 System Design
______________________________________________________________________

4.3 Data Flow Diagrams

Functional Model and Description

A description of each major software function, along with data flow (structured analysis)
or class hierarchy (Analysis Class diagram with class description for object-oriented
system) is presented.

Fig. 4.3 Data Flow Diagram 01

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 18
Chapter 4 System Design
______________________________________________________________________

4.4 Entity Relationship Diagrams

Data Description

Data objects that will be managed/manipulated by the software are described in this
section. The database entities or files or data structures required to be described. For data
objects details can be given as below.

Data objects and Relationships

Data objects and their major attributes and relationships among data objects are described
using an ERD- like form.

Fig. 4.4 ER-Diagram 01

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 19
Chapter 4 System Design
______________________________________________________________________

Fig. 4.5 ER-Diagram 02

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 20
Chapter 4 System Design
______________________________________________________________________

4.5 UML Diagrams

Fig. 4.6 Component Diagram

Fig. 4.7 Activity Diagram

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 21
Chapter 4 System Design
______________________________________________________________________

Fig. 4.8 Sequence Diagram

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 22
Chapter 4 System Design
______________________________________________________________________

Fig. 4.9 Use-Case Diagram

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 23
Chapter 5 Project Plan
______________________________________________________________________

Chapter 5

PROJECT PLAN

5.1 Project Estimate

5.1.1 Reconciled Estimate
The model followed is the Constructive Cost Model (COCOMO) for
estimating the effort required in completing the project. Like all the
estimation models, the COCOMO model requires sizing information. This
information can be specified in the form of:
• Object Point
• Function Point (FP)
• Lines of Source Code (KLOC) For our project, we use the sizing
information in the form of Lines of Source Code.
• Cost of each person per month, Cp=RS.200/- (per person-hour)
• Total Lines of Code for our project, KLOC=6k (approx.)

Cost Estimate
C=2*90*140=25200/-
Therefore, the cost of project is 25200/-(approx.)

Time Estimates
D=2.0 * (E) ˆ0.32
D=8.75 months
The approximate duration of project is 9 months. Number of people required
for the project N=22.31/7
N=2.47
N=2 people
Therefore 2 people are required to successfully complete the project on
schedule.
_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 24
Chapter 5 Project Plan
______________________________________________________________________
5.1.2 Project Resources
1. Hardware
• Computer System – RAM 4GB, Hard disk 200MB, Processor i3 or
above
2. Software
• Operating System - Windows 8 or above
• Anaconda/ MIT App Inventory
• Python
• Windows

5.2 Risk Management

NP-hard (non-deterministic polynomial-time hard), in computational complexity theory

is a class of problems that are informally, quote; at least as hard as the hardest problems
in NP quote; A problem H is NP-hard if and only if there is an NP-complete problem L
that is polynomial time Turing-reducible to H (i.e., LTH). In other words, L can be solved
in polynomial time by an oracle machine with an oracle for H. Informally, we can think
of an algorithm that can call such an oracle machine as a subroutine for solving H, and
solves L in polynomial time, if the subroutine call takes only one step to compute. NP-
hard problems may be of any type: decision problems, search problems, or optimization
problems. If there is a polynomial algorithm for any NP-hard problem, then there are
polynomial algorithms for all problems in NP and hence P = NP; If P NP, then NP-hard
problems have no solutions in polynomial time, while P = NP does not resolve whether
the NP-hard problems can be solved in polynomial time.

5.2.1 Risk Identification

1. Have top software and customer managers formally committed to support the
project?
• No

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 25
Chapter 5 Project Plan
______________________________________________________________________
2. Is end-user enthusiastically committed to the project and the system/product to
be built?
• No

3. Are requirements fully understood by the software engineering team and its
customers?
• Yes

4. Have customers been involved fully in the definition of requirements?

• No

5. Do end-users have realistic expectations?

• Yes

6. Does the software engineering team have the right mix of skills?
• Yes

7. Are project requirements stable?

• Yes

8. Is the number of people on the project team adequate to do the job?

• Yes

9. Do all customer/user constituencies agree on the importance of the project and

on the requirements for the system/product to be built?
• Yes

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 26
Chapter 5 Project Plan
______________________________________________________________________
5.2.2 Risk Analysis
The risks for the Project can be analyzed within the constraints of time and
quality.
Impact
ID Risk Description Probability
Schedule Quality Overall

1 Network
Low Low High High
Unavailable
2 Security Low Low High High

3 Connectivity Low High High Low

4 Consistency Low Low High High

Table 5.1 Risk Table

Probability Description Value

High If Hardware is not allowed > 75%

Medium Security 26 - 75%

Low Low < 25%

Table 5.2 Risk Probability Definitions

Probability Description Value

Very High If any network error occurs > 10%

High Design UI issue 5 -10%

Medium Due to less knowledge < 5%

Table 5.3 Risk Impact Definitions

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 27
Chapter 5 Project Plan
______________________________________________________________________
5.2.3 Overview of Risk Mitigation, Monitoring, Management

Following are the details for each risk.

Risk ID 1
Risk Description Description 1
Category Development Environment
Source Software requirement Specification document
Probability Low
Impact High
Response Mitigate
Strategy Strategy
Risk Status Occurred

Table 5.4 Risk for Development Environment

5.3 Project Schedule

5.3.1 Project Task Set

Major Tasks in the Project stages are:

Risk ID 2
Risk Description Description 2
Category Requirements
Source Software Design Specification documentation review
Probability Low
Impact High
Response Mitigate
Strategy Better testing will resolve this issue
Risk Status Identified

Table 5.5 Risk for Requirements

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 28
Chapter 5 Project Plan
______________________________________________________________________

Risk ID 3
Risk Description Description 3
Category Technology
Source This was identified during early development and testing.
Probability Low
Impact Very High
Response Accept
Strategy Example Running Service Registry behind proxy
Risk Status Identified

Table 5.6 Risk for Technology

• Task 1: Creating a transistor card

• Task 2: Designing a GUI
• Task 3: Creating Database
• Task 4: Model Creations
• Task 5: Final testing

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 29
Chapter 5 Project Plan
______________________________________________________________________
5.3.2 Task Network

Fig. 5.1 Task Network

5.3.3 Timeline Chart

Fig. 5.2 Timeline Chart

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 30
Chapter 5 Project Plan
______________________________________________________________________

5.4 Team Organization

5.4.1 Management Reporting and Communication

With the rapid development of science and technology, intelligent cars, as

representatives of intelligent products, have become a hot research topic today. The
gradual growth of the automobile industry has led to a rapid increase in the number
of automobiles in China, but the traffic problem has become increasingly prominent,
which seriously threatens people's travel safety. Autopilot technology is particularly
important, and a lot of research and development have been made at home and
abroad. In the Spring Festival of 2018, Baidu Apollo platform staged the driving
charm of unmanned vehicles on the Hong Kong-Zhuhai-Macao Bridge, reflecting the
maturity of China’s autonomous driving technology.

1) Lane line detection technology is the important technology of unmanned

driving. The correctness of the detection directly determines whether the driving
is safe.

2) The basic idea is to obtain the current road information through the on-board
camera, and use the relevant algorithm to detect the left and right lane lines of the
lane (if there is no lane line on the right, the road edge is detected), finally, the
vehicle travel decision is made. Since unmanned driving is online in real time, the
environment in each time slot is different, so real-time is also important while
ensuring the correct rate. At present, based on the development status at home and
abroad, the algorithm of lane line detection can be roughly divided into two types,
which are based on feature.

3) And segmentation based on model.

4) In 2018, Y. Su proposed a robust vanishing point constraint lane detection method

based on stereo platform. This method can detect both straight lane and curve
lane without considering any parameter lane model.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 31
Chapter 5 Project Plan
______________________________________________________________________

5) C. Lee proposed a robust and real-time lane detection algorithm based on vision.
The algorithm has an effective region of interest and can effectively reduce the
high noise level and computation time. The algorithm can process a gradient cue
and a color cue together and a line clustering with scan-line tests to verify the
characteristics of the lane markings.

6) X. W. Wei used improved Hough transform to realize Lane detection. By

controlling the slope of two lanes before and after comparison, a limitation is made
near the previously detected lane line area, set ROI and perform the search of
diagonal pixels to reconstruct the corner part.

7) In this paper, a lane line detection algorithm based on improved Hough transform
is proposed in terms of real-time performance and accuracy. In order to improve
the real time of image processing and reduce the interference of useless factors in
the image, wavelet lifting is used to process the image to extract low-frequency
wavelet coefficients sub-images; Compared with the traditional gray average
binarization algorithm and maximum entropy binarization algorithm, the
binarization image processing based on edge features can retain more original
details of the image, which is conducive to processing the image obtained under
weak illumination intensity; Then the conditional constraints are added to Hough
transform to improve the accuracy and real-time performance of detection;
Finally, the improved Hough transform method is used to detect the lane line to
eliminate the interference line and pseudo-lane line, and the correct lane line is
extracted by fitting the straight line with regression analysis method.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 32
Chapter 6 Project Implementation
______________________________________________________________________

Chapter 6

PROJECT IMPLEMENTATION

6.1 Overview of Project Modules

Lane line is an important reference for safe driving. In order to improve the accuracy and
real-time performance of lane line detection, a lane line detection algorithm based on
improved Hough transform is proposed in this paper. Firstly, the lifting algorithm of
wavelet is used to extract the low-frequency wavelet coefficients of the image, so as to
reduce the complexity of the image and improve the efficiency of image processing; Then
Canny operator is used to detect the edge of the image region of interest, and threshold is
automatically selected according to edge information for threshold processing; Finally,
three constraints are proposed from two aspects of angle and lane width to improve the
Hough transform to detect lane lines, and the correct lane lines are fitted by linear
regression method. Experiments show that the proposed algorithm has good correctness
and real-time performance for lane line detection. The recognition accuracy is above 94%
and the average processing time of each frame is 25.6ms.

6.2 Tools and Technologies Used

Anaconda:

• Anaconda is a distribution of the Python and R programming languages for

scientific computing (data science, machine learning applications, large-scale
data processing, predictive analytics, etc.), that aims to simplify package
management and deployment.
• The distribution includes data-science packages suitable for Windows, Linux,
and macOS. It is developed and maintained by Anaconda, Inc., which was
founded by Peter Wang and Travis Oliphant in 2012. As an Anaconda, Inc.
product, it is also known as Anaconda Distribution or Anaconda Individual

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 33
Chapter 6 Project Implementation
______________________________________________________________________
Edition, while other products from the company are Anaconda Team Edition and
Anaconda Enterprise Edition, both of which are not free.

Python:

• Python is an interpreter, high-level, general-purpose programming language.

Created by Guido van Rossum and first released in 1991, Python's design
philosophy emphasizes code readability with its notable use of significant
whitespace. Its language constructs and object-oriented approach aim to help
programmers write clear, logical code for small and large-scale projects.
• Python is dynamically typed and garbage-collected. It supports multiple
programming paradigms, including structured (particularly, procedural,) object-
oriented, and functional programming. Python is often described as a "batteries
included" language due to its comprehensive standard library.
• Python was conceived in the late 1980s as a successor to the ABC language.
Python 2.0, released in 2000, introduced features like list comprehensions and a
garbage collection system capable of Collecting reference cycles. Python 3.0,
released in 2008, was a major revision of the language that is not completely
backward-compatible, and much Python 2 code does not run unmodified on
Python 3.
• The Python 2 language, i.e., Python 2.7.X, was officially discontinued on 1
January 2020 (first planned for 2015) after which security patches and other
improvements will not be released for it. With Python 2's end-of-life, only Python
3.5.x and later are supported.
• Python interpreters are available for many operating systems. A global
community of programmers develops and maintains CPython, an open source
[33] reference implementation. A non-profit organization, the Python Software
Foundation, manages and directs resources for Python and CPython
development.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 34
Chapter 6 Project Implementation
______________________________________________________________________

6.3 Algorithm Details

6.3.1 Algorithm 1

Fig. 6.1 Canny Edge Detection Algorithm

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 35
Chapter 6 Project Implementation
______________________________________________________________________
The Canny edge detector is an edge detection operator that uses a multi-stage algorithm
to detect a wide range of edges in images. It was developed by John F. Canny in 1986.
Canny also produced a computational theory of edge detection explaining why the
technique works.

Canny edge detection is a technique to extract useful structural information from different
vision objects and dramatically reduce the amount of data to be processed. It has been
widely applied in various computer vision systems. Canny has found that the
requirements for the application of edge detection on diverse vision systems are relatively
similar. Thus, an edge detection solution to address these requirements can be
implemented in a wide range of situations. The general criteria for edge detection include:

• Detection of edge with low error rate, which means that the detection should
accurately catch as many edges shown in the image as possible.
• The edge point detected from the operator should accurately localize on the center of
the edge.
• A given edge in the image should only be marked once, and where possible, image
noise should not create false edges.

To satisfy these requirements Canny used the calculus of variations – a technique which
finds the function which optimizes a given functional. The optimal function in Canny's
detector is described by the sum of four exponential terms, but it can be approximated by
the first derivative of a Gaussian.

Among the edge detection methods developed so far, Canny edge detection algorithm is
one of the most strictly defined methods that provides good and reliable detection. Owing
to its optimality to meet with the three criteria for edge detection and the simplicity of
process for implementation, it became one of the most popular algorithms for edge
detection.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 36
Chapter 6 Project Implementation
______________________________________________________________________

6.4 Screenshots And Outputs

First, we will have a look at our projects User Interface. These are the screenshots of
project outputs.

Fig. 6.2 Selected Testing Image So That It Undergoes into Process

Fig. 6.3 Grey Scaled Image Output of a Selected Image

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 37
Chapter 6 Project Implementation
______________________________________________________________________

Fig. 6.4 Gaussian Filtered Image After Gaussian Kernel Sliding

Fig. 6.5 Edges Detected Image by Canny Edge Detection Process

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 38
Chapter 6 Project Implementation
______________________________________________________________________

Fig. 6.6 The Masked Image with Considering Only

the Required Road for Vehicle Movement

Fig. 6.7 Output of Detected Road from Image Captured by Vehicle

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 39
Chapter 6 Project Implementation
______________________________________________________________________

Fig. 6.8 Code of Canny Edge Detector

Fig. 6.9 Code of Region Selection

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 40
Chapter 6 Project Implementation
______________________________________________________________________

Fig. 6.10 Code of RGB Color Selection

Fig. 6.11 Code of Main Algorithm

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 41
Chapter 7 Conclusion
______________________________________________________________________

Chapter 7

CONCLUSION

7.1 Conclusion

A real time vision-based lane detection method was proposed. Image segmentation and
removing the shadow of the road were processed. Canny operator was used to detect
edges that represent road lanes or road boundaries. A hyperbola-pair road model used to
deal with the occlusion and imperfect road condition. A series of experiment showed that
the lanes were detected using Hough transformation with restricted search area and the
projection of their intersection will form the last scan point called the horizon.
Furthermore, in order to search out for the left and right vector points that represent the
road lanes, the lane scan boundary phase uses the edge image and the left and right
Hough lines and the horizon line as inputs, to effectively allocate the lane points. That
was demonstrated by two hyperbola lines. The experimental results showed that the
system is able to achieve a standard requirement to provide valuable information to the
driver to ensure safety.

7.2 Future Scope

In this system we will add OPEN CV, in future for more efficiency with the AI module
this system can also be used for system performance and accuracy.

7.3 Applications
• Robotics: Robots are widely used in manufacturing, assembly, packing and
packaging, mining, transport, earth and space exploration, surgery, weaponry,
laboratory research, safety, and the mass production of consumer and industrial
goods.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 42
Chapter 7 Conclusion
______________________________________________________________________
• Labour Charge Reduction: The equivalent hourly cost of robot labor has steadily
declined. One thing that’s not often discussed with collaborative robots is their ability
to provide quicker return on investment (ROI) than their heavier, more dangerous
industrial counterparts. Furthermore, collaborative robots are traditionally cheaper
than industrial robots, and still provide a much faster ROI when accounting for this
fact.
• Virtual Motion (Gaming): Lane detection and control has become a common feature
in many vehicles today. Additionally, it is a basic starting point for anyone going in
the direction of Autonomous Driving. But for most people who are not working on
autonomous driving or computer vision, starting with it might appear much more of
a daunting task than it actually is.
• Transport: We’ve all heard of self-driving cars, but this is just the start. From robot
buses already being trialed on European streets to drones set to create a whole new
transport network in city skies, companies are investing big to change the face of
private and commercial travel. In cities such as Paris, Las Vegas, Tokyo and Dubai
similar multi-person vehicles have and are being tested. Meanwhile in Singapore
they’ve gone one step further, building a whole town to help test and advance robot
bus tech.

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 43
Chapter 8 Bibliography
______________________________________________________________________

Chapter 8

BIBLIOGRAPHY

➢ FAN Chao, DI Shuai，HOU Li-long. A lane recognition algorithm based on line

model[J]. Application Research of Computers ， 2012,29(1):326-328,332 John
Smiley “Learn to Program with VB.Net 2008 Express”
➢ GE Ping-shu, GUO Lie, DU Yuan-hu. Lane line detection based on intelligent
adjustment of CCD parameters [J]. Automotive Engineering，2014,36(7):779-
784.Steven Roman, Ron Petrusha, and Paul Lomax (Paperback - Dec 2002) “VB.NET
Language Pocket Reference”
➢ MA Ying, LI Keqiang, XU Youchun. Lane line recognition method based on
improved projection transformation formula [J]. Journal of Tsinghua
University,2005,45(11):1530-1533.
➢ BI Shu-hao, LI Shou-cheng. Research on unattended environment sensing technology
based on monocular vision [J]. Mechanical Engineering and Automation,2014,2:57-
58.
➢ YU Hong-shan, ZHANG Wen-hao, YANG Zhen-geng, et al. An Image egmentation
Method Based on Improved uperpixel Fusion[J]. Journal of Hunan University
(Natural Science), 2018,45(10):121-129.
➢ MA Chao, XIE Mei. A method for lane detection based on color clustering[C]//Third
International Conference on Knowledge Discovery and Data Mining. Phutet: IEEE
[7] Computer Society, 2010: 200-203
➢ LIU C, WANG Z Q.The Research on Advertising Model of Self-Driving Car
Platform[C]//2017 IEEE 3rd Information Technology and Mechatronics Engineering
Conference (ITOEC2017),2017.
➢ Want, J.S. and Knipling, R.R. Single-Vehicle Roadway Departure Cranshes: Problem
Size Assessment and Statistical Description. National Highway Traffic Safety
Administration Technical Report DTNH-22-91-C-03121.
➢ PENG Bo, CAI Xiao-yu, ZHANG You-jie, et al. Automatic detection of UAV video
vehicles based on symmetric frame difference and block background modeling[J].
Journal of Southeast University (Natural Science Edition),2017,47(4):685-690.
_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 44
Chapter 9 Appendix
______________________________________________________________________

Chapter 9

APPENDIX A

IEEE PUBLISHED PAPER AND CERTIFICATE OF PUBLICATION

8.1 IEEE Published Paper

Journal name: Journal Publication of International Research for Engineering and

Management (JOIREM)

Paper Title: Lane Line Detection Algorithm for Self-Drive Cars.

8.2 Certificates of Publication

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 45
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 46
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 47
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 48
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 49
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 50
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 51
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 52
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 53
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 54
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 55
Chapter 9 Appendix
______________________________________________________________________

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 56
Chapter 9 Appendix
______________________________________________________________________

APPENDIX B

Group Member Details

• Name : Saurabh Ahire

• Class : B.E.
• Department : Computer Engineering
• Collage Name : Brahma Valley College of Engineering and Research
Institute, Nashik
• PRN No. : 72006524M

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 57
Chapter 9 Appendix
______________________________________________________________________

• Name : Pratik Chandore

• Class : B.E.
• Department : Computer Engineering
• Collage Name : Brahma Valley College of Engineering and Research
Institute, Nashik
• PRN No. : 72014081B

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 58
Chapter 9 Appendix
______________________________________________________________________

• Name : Yashoda Gavit

• Class : B.E
• Department : Computer Engineering
• Collage Name : Brahma Valley College of Engineering and Research
Institute, Nashik
• PRN No. : 71835854G

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 59
Chapter 9 Appendix
______________________________________________________________________

• Name : Yogesh Khalane

• Class : B.E.
• Department : Computer Engineering
• Collage Name : Brahma Valley College of Engineering and Research
Institute, Nashik
• PRN No. : 72006540C

_____________________________________________________________________________
“BVCOERI, Department of Computer Engineering 2021-22” 60