Mini-Project Report Format (CSE)

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 10

A MINI-PROJECT

REPORT
ON

PEDESTRIAN DETECTION
Submitted in partial fulfilment towards the award of degree in
B.TECH in Computer Science and Engineering
SESSION 2023-24

ODD SEMESTER

NITRA TECHNICAL CAMPUS,


GHAZIABAD
(College Code-802)
Affiliated to Dr. A.P.J. Abdul Kalam Technical University, Lucknow)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

SUBMITTED BY:

ABHISHEK BHARTI
2208020109002
CSE/3rd

III
INDEX

S No. CONTENT PAGE


1 ACKNOWLEDGEMENT III
2 DECLARATION IV
3 ABSTRACT V
4 LIST OF TABLES VI
5 LIST OF FIGURES VII
6 CHAPTER’S 1
The chapters may be broadly divided into 7 parts as
below:

i. Introduction
ii. Problem Formulation
iii. Proposed Solution /
Methodology
iv. System requirements
v. Technology used
vi. Results
vii. Conclusion

IV
ACKNOWLEDGEMENT

It is my pleasure to be indebted to various people, who directly or indirectly


contributed to the development of this work and who influenced my thinking,
behaviour, and acts during my study.

I am also thankful to my friends who gave me support to help to complete this


project and solve all my difficulties.

I am taking this opportunity to express gratitude to the Management, Teachers and


staff.

(Sign of Student)

Abhishek Bharti
2208020109002
CSE/3rd

V
DECLARATION

I, ABHISHEK BHARTI (2208020109002) hereby declare that the report of the


Mini-Project titled “PEDESTRIAN DETECTION” is uniquely prepared by me
and does not form part of any other thesis or dissertation based on which a degree
or award was conferred on an earlier occasion on this or any other candidate.

I also confirm that the report is only prepared for my academic requirement, not
for any other purpose. It might not be used in the interest of the opposite party of
any organization.

(Sign of Student)

Abhishek Bharti

2208020109002
CSE/3rd

VI
ABSTRACT

Pedestrian detection is the task of finding people in images and videos. It is a


challenging task because people can look very different, depending on their
clothes, pose, and lighting. Pedestrian detection is used in many applications,
such as self-driving cars, security systems, and robotics.

To build a pedestrian detection system, you can use the following steps:

1. Collect a dataset of images or videos containing pedestrians. This


dataset will be used to train your system to detect pedestrians.
2. Choose a pedestrian detection algorithm. There are many different
algorithms available, both open-source and commercial. You can
choose an algorithm that is appropriate for your specific application
and the available resources.
3. Train the pedestrian detection algorithm on your dataset. This involves
feeding the dataset to the algorithm and allowing it to learn to detect
pedestrians.
4. Evaluate the pedestrian detection algorithm on a held-out test set. This
will give you an idea of how well the algorithm will perform on new
data.
5. Deploy the pedestrian detection system in your application. This may
involve integrating the algorithm into a software system or hardware
device.

VII
Once you have deployed your pedestrian detection system, you may need to
monitor its performance and make adjustments as needed. For example, you
may need to retrain the algorithm on new data or update the algorithm
parameters to improve its performance.

Here is an even simpler explanation:

Pedestrian detection is finding people in pictures and videos.


To build a pedestrian detection system:
1. Collect a bunch of pictures and videos of people.
2. Choose a pedestrian detection algorithm.
3. Train the algorithm on your pictures and videos.
4. Test the algorithm on new pictures and videos.
5. Use the algorithm in your application.

Once you have deployed your pedestrian detection system, you may need to
update it from time to time, so that it can detect people in new and different
situations.

VIII
LIST OF FIGURE
Figure 1: Pedestrian detection accuracy over time: This figure
shows the improvement in pedestrian detection accuracy over time, The
graph shows that pedestrian detection accuracy has improved significantly
in recent years, thanks to advances in deep learning.

Figure 2: Pedestrian detection examples: These images show


examples of pedestrian detection in different environments, such as
streets, sidewalks, and parks. The images show that pedestrian detection
algorithms can be used to detect pedestrians in a variety of conditions,
including different lighting conditions, poses, and clothing.

Figure 3: Pedestrian detection applications: These images show


examples of how pedestrian detection is used in real-world applications.
For example, pedestrian detection is used in self-driving cars to avoid
collisions with pedestrians.

IX
LIST OF TABLES

X
Chapter:1 Introduction

1
2

You might also like