Pothole detection using lightweight network models
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.
| Asıl Yazarlar: | , , , , |
|---|---|
| Diğer Yazarlar: | |
| Materyal Türü: | Tez |
| Dil: | English |
| Baskı/Yayın Bilgisi: |
Brac University
2024
|
| Konular: | |
| Online Erişim: | http://hdl.handle.net/10361/23966 |
| id |
10361-23966 |
|---|---|
| record_format |
dspace |
| spelling |
10361-239662024-10-01T08:54:09Z Pothole detection using lightweight network models Abdullah, S. M. Hasan, Shakib Al Parsa, Antara Firoz Kabbya, MD. Asif Shahidullah Talukder, Anika Hasan Noor, Jannatun Department of Computer Science and Engineering, Brac University Machine learning Neural networks Deep learning Lightweight models Road construction industry--Automation. Computational intelligence. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 76-80). Potholes are defective cavities found on road surfaces. Potholes can lead to serious accidents and vehicle damage if not properly detected. Thus, we are proposing the use of neural network models for pothole classification. The study involves a comprehensive performance analysis of existing lightweight neural network models in pothole classification, compared against the traditional heavyweight models. Lightweight models are emphasized in the thesis due to their low computational requirements, faster prediction times and better compatibility with real-time detection. We have tested six lightweight models (CCT, CNN, INN, Swin Transformer, EANet and ConvMixer) and four heavyweight models (VGG16. ResNet50, DenseNet201 and Xception). A custom dataset of 900 images containing image samples from roads of Dhaka and Bogura was created by the authors to run the models. The dataset was further augmented into 10,000 images by applying various augmentation methods. Separate tests for each model were conducted in the augmented dataset to compare performance against the original dataset. Augmentation enhanced the performance of 9 out of the 10 models. CNN achieved the highest accuracy of 96.55% and the highest F1 score of 0.96 in our testing. Furthermore, CCT exhibited accuracy of 94.6% and F1 score of 0.9. The lightweight models overall performed better than the heavyweight models in both datasets. S. M. Abdullah Shakib Al Hasan Antara Firoz Parsa MD. Asif Shahidullah Kabbya Anika Hasan Talukder B.Sc. in Computer Science 2024-09-04T05:50:00Z 2024-09-04T05:50:00Z ©2024 2024-01 Thesis ID 19201050 ID 19201049 ID 20101437 ID 20301017 ID 20301331 http://hdl.handle.net/10361/23966 en 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. 90 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Machine learning Neural networks Deep learning Lightweight models Road construction industry--Automation. Computational intelligence. |
| spellingShingle |
Machine learning Neural networks Deep learning Lightweight models Road construction industry--Automation. Computational intelligence. Abdullah, S. M. Hasan, Shakib Al Parsa, Antara Firoz Kabbya, MD. Asif Shahidullah Talukder, Anika Hasan Pothole detection using lightweight network models |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. |
| author2 |
Noor, Jannatun |
| author_facet |
Noor, Jannatun Abdullah, S. M. Hasan, Shakib Al Parsa, Antara Firoz Kabbya, MD. Asif Shahidullah Talukder, Anika Hasan |
| format |
Thesis |
| author |
Abdullah, S. M. Hasan, Shakib Al Parsa, Antara Firoz Kabbya, MD. Asif Shahidullah Talukder, Anika Hasan |
| author_sort |
Abdullah, S. M. |
| title |
Pothole detection using lightweight network models |
| title_short |
Pothole detection using lightweight network models |
| title_full |
Pothole detection using lightweight network models |
| title_fullStr |
Pothole detection using lightweight network models |
| title_full_unstemmed |
Pothole detection using lightweight network models |
| title_sort |
pothole detection using lightweight network models |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/23966 |
| work_keys_str_mv |
AT abdullahsm potholedetectionusinglightweightnetworkmodels AT hasanshakibal potholedetectionusinglightweightnetworkmodels AT parsaantarafiroz potholedetectionusinglightweightnetworkmodels AT kabbyamdasifshahidullah potholedetectionusinglightweightnetworkmodels AT talukderanikahasan potholedetectionusinglightweightnetworkmodels |
| _version_ |
1814309735929741312 |