Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Mostafa, Tanzim, Chowdhury, Sartaj Jamal
Rannpháirtithe:	Rhaman, Dr. Md. Khalilur
Formáid:	Tráchtas
Teanga:	en_US
Foilsithe / Cruthaithe:	Brac University 2022
Ábhair:	Autonomous Vehicles Occluded Object Detection Object Detection Machine Learning Deep Learning Supervised Learning Occluded Objects Dataset Transfer Learning YOLOv5 YOLOX Faster R-CNN Cognitive learning theory (Deep learning) Artificial intelligence Machine learning Autonomous vehicles Automobiles
Rochtain ar líne:	http://hdl.handle.net/10361/17614

id	10361-17614
record_format	dspace
spelling	10361-176142022-11-23T21:01:46Z Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN Mostafa, Tanzim Chowdhury, Sartaj Jamal Rhaman, Dr. Md. Khalilur Rabiul Alam, Dr. Md. Golam Department of Computer Science and Engineering, Brac University Autonomous Vehicles Occluded Object Detection Object Detection Machine Learning Deep Learning Supervised Learning Occluded Objects Dataset Transfer Learning YOLOv5 YOLOX Faster R-CNN Cognitive learning theory (Deep learning) Artificial intelligence Machine learning Autonomous vehicles Automobiles This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 33-34). Autonomous vehicles [AVs] are the future of transportation and they are likely to bring countless benefits compared to human-operated driving. However, there are still a lot of advances yet to be made before these vehicles can be considered com pletely safe and before they can reach full autonomy. Perceiving the environment with utmost accuracy and speed is a crucial task for autonomous vehicles, ergo mak ing this process more efficient and streamlined is of paramount importance. In order to perceive the environment, AVs need to classify and localize the different objects in the surrounding. For this research, we deal with the detection of occluded ob jects to help enhance the perception of AVs. We introduce a new dataset containing occluded instances of road scenes from the perspective of Bangladesh. We utilized transfer learning to train the YOLOv5, YOLOX and Faster R-CNN models, using their respective pre-trained weights on the COCO dataset. We then evaluate and compare the performance of the three object detection algorithms on our dataset. YOLOv5, YOLOX, and Faster R-CNN achieved mAP at 0.5 metric of 0.777, 0.849 and 0.688, and mAP at 0.5:0.95 of 0.546, 0.634, and 0.422 respectively in our test set. Therefore, we find YOLOX to be the best performing model on our dataset, and its high mAP scores demonstrate the effectiveness of the model as well as the dataset. Tanzim Mostafa Sartaj Jamal Chowdhury B. Computer Science 2022-11-23T06:38:35Z 2022-11-23T06:38:35Z 2022 2022-05 Thesis ID: 18201151 ID: 18201160 http://hdl.handle.net/10361/17614 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 34 Pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	en_US
topic	Autonomous Vehicles Occluded Object Detection Object Detection Machine Learning Deep Learning Supervised Learning Occluded Objects Dataset Transfer Learning YOLOv5 YOLOX Faster R-CNN Cognitive learning theory (Deep learning) Artificial intelligence Machine learning Autonomous vehicles Automobiles
spellingShingle	Autonomous Vehicles Occluded Object Detection Object Detection Machine Learning Deep Learning Supervised Learning Occluded Objects Dataset Transfer Learning YOLOv5 YOLOX Faster R-CNN Cognitive learning theory (Deep learning) Artificial intelligence Machine learning Autonomous vehicles Automobiles Mostafa, Tanzim Chowdhury, Sartaj Jamal Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.
author2	Rhaman, Dr. Md. Khalilur
author_facet	Rhaman, Dr. Md. Khalilur Mostafa, Tanzim Chowdhury, Sartaj Jamal
format	Thesis
author	Mostafa, Tanzim Chowdhury, Sartaj Jamal
author_sort	Mostafa, Tanzim
title	Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
title_short	Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
title_full	Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
title_fullStr	Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
title_full_unstemmed	Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN
title_sort	occluded object detection for autonomous vehicles employing yolov5, yolox and faster r-cnn
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/17614
work_keys_str_mv	AT mostafatanzim occludedobjectdetectionforautonomousvehiclesemployingyolov5yoloxandfasterrcnn AT chowdhurysartajjamal occludedobjectdetectionforautonomousvehiclesemployingyolov5yoloxandfasterrcnn
_version_	1814308329642524672

Occluded object detection for autonomous vehicles employing YOLOv5, YOLOX and Faster R-CNN

Míreanna comhchosúla