REAL - TIME HUMAN DETECTION

& COUNTING

PROJECT REPORT
BY
Akash Ramanand Rajak (CSE/435/19008)
Amaan Khan (CSE/438/19011)
Kumar Saurabh (CSE/470/19043)
Pallav Dubey (CSE/481/19054)

submitted to
Indian Institute of Information Technology, Kalyani
for 3rd Year Project
Bachelor of Technology
In
Computer Science and Engineering
Nov, 2021
Certificate
This is to certify that project report entitled “Real Time Human
Detection & Counting” being submitted by Akash Ramanand Rajak
(Reg No. 435), Amaan Khan (Reg No. 438), Kumar Saurabh (Reg No.
470) and Pallav Dubey(Reg No. 481), undergraduate students in the
Department of Computer Science and Engineering, Indian Institute of
Information Technology Kalyani, West Bengal, 741235, India, for the
award of Bachelor of Technology in Computer Science and
Engineering, is an original research work carried by them under my
supervision and guidance.

The project has fulfilled all the requirements as per the regulations of
the Indian Institute of Information Technology Kalyani and in my
opinion, has reached the standards needed for submission. The
work, techniques and the results presented have not been submitted
to any other university or institute for the award of any other degree
or diploma.

...................................
(Dr. Anirban Lakshman)
Assistant Professor
Department of Computer Science and Engineering
Indian Institute of Information Technology Kalyani
Kalyani, W.B.-741235, India.
i
Declaration
We hereby declare that the work being presented in this project
entitled Real Time Human Detection & Counting, submitted to
Indian Institute of Information Technology Kalyani in partial
fulfilment for the award of the degree of Bachelor of Technology in
Computer Science and Engineering during the period from August
2021 to October 2021 under the supervision of Dr. Anirban
Lakshman, Department of Computer Science and Engineering, Indian
Institute of Information Technology Kalyani, West Bengal - 741235,
India, does not contain any classified information.

Name of the Candidates : Akash Ramanand Rajak (Reg No. 435)

Amaan Khan (Reg No. 438)
Kumar Saurabh (Reg No. 470)
Pallav Dubey (Reg No. 481)

Name of the Department : Computer Science and Information Engineering

Institute Name : Indian Institute of Information Technology Kalyani

Date : 08/11/2021

ii
Acknowledgment
First of all we would like to take this opportunity to thanks our
supervisor Dr. Anirban Lakhsman without whose efforts this project
would not have been possible. We are grateful to him for guiding us
towards the project wherever possible. We are most grateful to
Department of Computer Science and Engineering, IIIT Kalyani, India,
for providing us this wonderful opportunity to complete our 3rd year
project.

And last but the biggest of all, We want to thank to each of the group
members, for always helping keeping a continuous check that
project never wandered off the track from our goal.

IIIT Kalyani Akash Ramanand Rajak (Reg No. 435)

Date : 08/11/2021 Amaan Khan (Reg No. 438)
Kumar Saurabh (Reg No. 470)
Pallav Dubey (Reg No. 481)

iii
Abstract
This project investigates and reports benchmarks for detecting and
enumerating humans through real time images, videos and camera.
This is very useful in various image processing and performing
computer vision tasks. This schemes have been implemented in
Python programming language, and using various tech-stacks like
OpenCv[2], Tensorflow[3], etc.

Keywords : Computer Vision, Human Detection, Enumeration

iv
Content

Certificate i
Declaration ii
Acknowledgment iii
Abstract iv
Content v
List of Acronyms vii
1.) Introduction 1
1.1) Computer Vision …………………………………………………………. 1
1.2) Application of Computer Vision …………………………………… 2
1.3) Detection & Enumeration in Computer Vision ……………… 2
1.4) Roadmap of the report ………………………………………………… 3
2.) Human Detection & Counting 4
2.1) Human Detection ………………………………………………………… 4
2.2) Detection & Counting through Image ………………………….. 5
2.3) Detection & Counting through Video …………………………… 5
2.4) Detection & Counting through Camera ……………………….. 6
3.) Accuracy 7
3.1) Introduction …………………………………………………………………. 7
3.2) Maximum Accuracy ……………………………………………………… 7
3.3) Maximum Average Accuracy ………………………………………… 7

v
4.) Plots 9
4.1) Plots ……………………………………………………………………………. 9
4.2) Enumeration Plot ………………………………………………………… 9
4.3) Average Accuracy Plot …………………………………………………. 9
5.) Conclusion and Further Scope 10
Bibliography 11

vi
List of Acronyms
GUI – Graphical User Interface[4]
CNN – Convolutional Neural network[3]
HOG – Histogram of Oriented Gradients [2]

vii
Chapter 1
Introduction
This chapter resembles the brief introduction about the most widely
used field of study “Computer Vision”[1]. Here talked about the
various aspects and uses of computer vision, basic meaning and
keywords like detection, enumeration, and discussed the roadmap to
the report.

1.1) Computer Vision

Computer vision is an interdisciplinary scientific field that deals
with how computers can gain high-level understanding from digital
images or videos. It is most widely used field of artificial intelligence
(AI) that enables computers and systems to derive meaningful
information from digital images, videos and other visual inputs. [1]

Different types of computer vision include image segmentation,

object detection, facial recognition, edge detection, pattern
detection, image classification, and feature matching.
Computer Vision itself is a big domain and is divided into

1
various subdomains like scene reconstruction, object detection,
event detection, video tracking, object recognition, 3D pose
estimation, learning, indexing, motion estimation, visual servoing, 3D
scene modeling, and image restoration. [2]

1.2) Application of Computer Vision

It has various different application[1] that too in various fields.
Some of them are listed below:

- Object Detection
- Screen Reader
- Intruder Detection
- Code and Character Reader
- Robotics
- Motion Analysis
- Image Restoration
There are many left to list as it is very wide topic and here in this
project we have used one of the application i.e. Object Detection.[2]

1.3) Detection and Enumeration in Computer Vision

Detection is a computer technology related to computer vision
and image processing that deals with detecting instances of semantic
objects of a certain class (such as humans, buildings, or cars) in
digital images and videos.
For Detection process in computer vision, there are various
methods and each one have different level of accuracy according to
their advancement level, like is some methods that is invented in
very early stage, they give more cases of false detection as compared
to the advanced methods that had been discovered after that.

2
 And here we have used the human as an entity which we are
detecting our project and along with that, we are also counting
humans through image, video and camera.

1.4) Roadmap to the report

The structure of the report is as follows:
Chapter 1: It discusses about brief introduction of what computer
vision[1] is, what are there wide applications, some important
keywords like detection and counting in computer vision, and finally
roadmap of the report.
Chapter 2: It is based on the discussion of one of the domain of
computer vision i.e. Human Detection and further is emphasize the
detection of humans in real time image, video and through camera
and discussed the meaning of Maximum Human Count.
Chapter 3: This chapter is based on key point of various computer
vision project or basically any project i.e. Accuracy. Inside that we
have discussed about Max. Accuracy we got in detection process,
Max. Average Accuracy.
Chapter 4: It talks about the graphical representation results of
detection process, on the basis of the data we got. In that we
focussed on two basic plot that are Enumeration Plot and Average
Accuracy Plot.[5]
Chapter 5: At last, this chapter deals with a brief conclusion and
further scope of this project.
 3

Chapter 2
2.1) Human Detection
Human detection[2] is the task of locating all instances of
human beings present in an image, and it has been most widely
accomplished by searching all locations in the image, at all possible
scales, and comparing a small area at each location with known
templates or patterns of people.
In this we can use various predefined methods and can detect
the human in any image, video and can even get various factors like
accuracy, each detections counting, etc.
Some common methods are :

- Using Haar Cascade Classifier:[2]

o Here we make use of .xml file for human detection, and
using that we detect the humans in real time videos and
images
- Using HOG(Histogram of Oriented Gradients) :[2]
o Here we make used of predefined functions and with
that we detect, and this case gives some how better
accuracy as compared to Harr Cascade Classifier.
- Using Tensorflow:[3]
o TensorFlow is an open-source API from Google, which is
widely used for solving machine learning tasks that
involve Deep Neural Networks. And again this method
gives even better accuracy than above two methods.
Here we have implemented the application using the third
method and got almost the better accuracy.
 4

We have implemented the project for three different cases:

o Image
o Video
o Camera

2.2) Detection & Counting through Image

This section works with real time images. Here will allow user
to select any real time image from the local system and then user
can detect the humans in it. And along with that it also gives the
count of humans detected.

2.3) Detection & Counting through Video

This section works with real time videos. Here will allow user to
select any real time video from the local system and then user can
detect the humans in it.
Now in case of video, since it is running, while the detection
process is going on user will be able to see the detected peoples and
their count for each frames per second of the video.
 5

2.4) Detection & Counting through Camera

This section works somehow similar to case of video. Here user
will be asked to first open the webcam, and it will detect humans
that will comes in that webcam during the detection process.
 6

Chapter 3
3.1) Accuracy
Now here we have discussed about the main keypoint of all
computer vision project i.e. Accuracy[3]. During the detection
process of human, we along with process also kept track of the
accuracy with each human is getting detected in image, video and
camera.
In our method, we have set the threshold accuracy for the
detection process as 70%, so the object detected with accuracy more
than the threshold accuracy, we declared it as the well detected
human, and display detection indicator around that human during
process. We have set this threshold in order to prevent false
detection to det displayed while detection process.
Now whenever term accuracy comes, there is always a general
question, “What is the maximum accuracy of the detection?” and
that we have discussed in the next topic.

3.2) Maximum Accuracy

Since we got the factor of accuracy with which each human is
getting detected, so we also kept the track of maximum accuracy
which we are getting throughout the detection process. This factors
basically tells us about the preciseness of our implemented
application.

3.3) Maximum Average Accuracy

This factor comes in the case of detecting through video and
camera. Because in case of image, since the image is static, there is
no meaning of maximum avg. accuracy.
 7
In case of video and camera, it basically reflects the maximum
of all the average of accuracy that we get for each frames in running
video and webcam. This factors we have used in plotting purpose,
which is covered in next chapter.
 8

Chapter 4
4.1) Plots
This section basically deals with the graphical representation of
the data[4][5] we got from the detection process. Using this
graphical representation, one can do the analysis of the human
count and accuracy very well.
In our application, we have basically talked about two basic
plots.
o Enumeration Plot
o Avg. Accuracy Plot

4.2) Enumeration Plot

This plot basically represent the plot between humans count
against each time interval. For this plot, the parameter we took on X-
axis is time(in seconds) and on Y-axis, we took, human count at that
particular time.[4]
And the highest peak in this enumeration plot, indicates the
maximum no. of people detected in whole detection process.

4.2) Average Accuracy Plot

This plot basically represent the plot between Average
Accuracy against each time interval. For this plot, the parameter we
took on X-axis is time(in seconds) and on Y-axis, we took, average
accuracy with which humans got detected at that particular time.[4]
And the highest peak in this plot, indicates the maximum avg.
accuracy with which people detected in whole detection process.
 9

Chapter 5
Conclusion and Future Scopes
In the last section of the project, we generate Crowd Report[5],
which will give some message on the basis of the results we got from
the detection process. For this we took some threshold human count
and we gave different message for different results of human count
we got form detection process.
Now coming to the future scope of this project or application,
since in this we are taking any image, video or with camera we are
detecting humans and getting count of it, along with accuracy. So
some of the future scope can be :

- This can be used in various malls and other areas, to analyse

the maximum people count, and then providing some
restrictions on number of people to have at a time at that
place.
- This can replace various mental jobs, and this can be done
more efficiently with machines.
- This will ultimately leads to some kind of crowd-ness control in
some places or areas when implemented in that area.
 10

Bibliography
[1] Programming Computer Vision with Python, 1st Edition, Jan Eric
Solem, 2012, O’ Reily

[2] Learning OpenCv, Adrian Kaehler and Gary Rost Bradski, 2008, O’
Reily

[3] Deep Learning with Tensorflow, Giancarlo Zaccone, Md. Rezaul

Karim, Ahmed Menshawy, 2017

[4] Python GUI Programming with Tkinter, Alan D. Moore, 2018

[5] Python Standard Library, Fredrik Lundh, 2001, O’ Reily

11