Scribd
Upload
103 views14 pages

DSP Project Report

This project report describes an attempt at developing an object detection algorithm using computer vision techniques. The report includes an introduction to object detection, an abstract, flow diagram, coding details, methodology, results of detecting a box and elephant in images, and conclusions. The algorithm detects objects by finding feature point correspondences between reference and target images and is robust to some rotation and occlusion. Results showed successful detection of a box and elephant in cluttered scenes.

Uploaded by

Ushba Saleem
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
103 views14 pages

DSP Project Report

This project report describes an attempt at developing an object detection algorithm using computer vision techniques. The report includes an introduction to object detection, an abstract, flow diagram, coding details, methodology, results of detecting a box and elephant in images, and conclusions. The algorithm detects objects by finding feature point correspondences between reference and target images and is robust to some rotation and occlusion. Results showed successful detection of a box and elephant in cluttered scenes.

Uploaded by

Ushba Saleem
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

SIR SYED UNIVERSITY OF ENGINEERING & TECHNOLOGY

PROJECT REPORT
DEPARTMENT OF COMPUTER ENGINEERING
DIGITAL SIGNAL PROCESSING (CE-405)

OBJECT DETECTION

GROUP MEMBERS:
MEHWISH MIRZA ASIF BAIG 2018-CE-162
USHBA M. SALEEM 2018-CE-142
HAMZA HAFEEZ 2018-CE-157
MUHAMMAD FAIZAN 2018-CE-155

SUBMITTED TO:
MISS SIDRA & MISS SHAMA

1
TABLE OF CONTENTS

• Introduction……….......................................................................................... 3

• Abstract…….......................................................................................................4

• Flow Diagram of Object Detection…………..............................................5

• Coding………………………………….....................................................................6

• Methodology…………………............................................................................8

• Results….......................................................................................................... 8

• Conclusion...................................................................................................... 14

• References….................................................................................................. 14

2
INTRODUCTION

Object detection is a computer vision technique that allows us to


identify and locate objects in an image or video. With this kind of
identification and localization, object detection can be used
to count objects in a scene and determine and track their precise
locations, all while accurately labeling them. Object detection is a key
technology behind advanced driver assistance systems (ADAS) that
enable cars to detect driving lanes or perform pedestrian detection to
improve road safety. Object detection is also useful in applications such
as video surveillance or image retrieval systems.

3
ABSTRACT
This project was an attempt at developing an object detection using
modern computer vision technology. Computer Vision is the branch of
the science of computers and software systems which can recognize as
well as understand images and scenes. Computer Vision is consists of
various aspects such as image recognition, object detection, image
generation, image super-resolution and many more. Object detection is
widely used for face detection, vehicle detection, pedestrian counting,
web images, security systems and self-driving cars. This project
presents an algorithm for detecting a specific object based on finding
point correspondences between the reference and the target image. It
can detect objects despite a scale change or in-plane rotation. It is also
robust to small amount of out-of-plane rotation and occlusion.
This method of object detection works best for objects that exhibit non-
repeating texture patterns, which give rise to unique feature matches.
This technique is not likely to work well for uniformly-colored objects,
or for objects containing repeating patterns.
The results of the project are expressed in this report.

4
FLOW DIAGRAM OF OBJECT DETECTION
General block diagram of object detection and significance of each
block in the system. Common object detection mainly includes image
capture, Feature Detection, Collecting Putative Points, Object
detection.

5
CODING

6
7
METHODOLOGY
In this project, algorithm first check which image he wants to check and
selects 100 strongest feature points from that image and 300 strongest
feature points from scene image and then algorithm putatively selects
matched points (including outliers and inliers) and then finally it detects
objects. By using this algorithm we can detect many objects as we
wants to detect.

RESULTS:
IMAGE OF A BOX:

8
IMAGE OF A CLUTTERED SCENE:

100 STRONGEST FEATURE POINTS FROM BOX IMAGE:

9
300 STRONGEST FEATURE POINTS FROM SCENE IMAGE:

PUTATIVELY MATCHED POINTS (INCLUDING OUTLIERS)

10
MATCHED POINTS (INLIERS ONLY)

DETECTED BOX

11
IMAGE OF AN ELEPHANT

100 STRONGEST FEATURE POINTS FROM ELEPHANT IMAGE:

12
PUTATIVELY MATCHED POINTS (INCLUDING OUTLIERS)

MATCHED POINTS (INLIERS ONLY)

13
DETECTED ELEPHANT AND BOX

CONCLUSION:
Hence, object detection involves detecting instances of objects from a
particular class in an image. The goal of object detection is to detect all
instances of objects from a known class, such as people, cars or faces in
an image.

REFERENCES:

https://gist.github.com/tmwatchanan/01348a2ff54966b71de136566ec
c9df5
https://www.mathworks.com/help/vision/object
detection.html?s_tid=CRUX_lftnav

14

You might also like