A comparative study of deep learning methods for automating road condition characterization
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.
| Main Authors: | , , |
|---|---|
| Outros Autores: | |
| Formato: | Thesis |
| Idioma: | en_US |
| Publicado em: |
Brac University
2021
|
| Assuntos: | |
| Acesso em linha: | http://hdl.handle.net/10361/14359 |
| id |
10361-14359 |
|---|---|
| record_format |
dspace |
| spelling |
10361-143592022-01-26T10:18:12Z A comparative study of deep learning methods for automating road condition characterization Ruhi, Zurana Mehrin Sheetal, Farahatul Aziz Prithu, Farisha Hossain Arif, Hossain Department of Computer Science and Engineering, Brac University CNN Residual Network Machine Learning XGboost Road Inspection Potholes Cracks This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. Cataloged from PDF version of thesis. Includes bibliographical references (pages 35-37). Roads in Bangladesh provide infrastructural facilities to both agricultural as well as industrial sectors of the country. Distressed roads can cause fatal accidents as well as largely decelerate sector progress. This makes swift road inspection and repairs one of the most important aspects of our country’s holistic growth. As much as it affects the general public, tackling this is as big a problem for the government as well. Currently, the problem for road repair is a multi-stage problem, which involves getting a complaint from a resident, physical road inspection by some official, identifying the type of damage and then comes the process of actually repairing it. Here, we intend to make this cumbersome process simpler, by automating the problem identification stage. We developed a method leveraging the Machine Learning and Deep Learning capabilities that can potentially detect a damaged road and identify the type of damage viz. pothole and crack. We self-captured data from the roads and streets, thus emulating the data we expect when this method is used in real-life by installing cameras on the city corporation’s garbage trucks. We reviewed various models ranging from conventional machine learning to complex deep learning algorithms and ultimately shortlisted three models: CNN, CNN-XGboost, and ResNet. These three models were then optimized for our problem, and then extensive testing was performed to determine the one that outperforms the rest. ResNet-34 emerged as a clear winner, with an accuracy of 87.8 % on the test data. Here, we’ll do an in-depth study of the efficacy of these models on our problem statement. Zurana Mehrin Ruhi Farahatul Aziz Sheetal Farisha Hossain Prithu B. Computer Science 2021-03-21T05:35:24Z 2021-03-21T05:35:24Z 2020 2020-04 Thesis ID: 20141049 ID: 16101083 ID: 16101259 http://hdl.handle.net/10361/14359 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. 37 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
CNN Residual Network Machine Learning XGboost Road Inspection Potholes Cracks |
| spellingShingle |
CNN Residual Network Machine Learning XGboost Road Inspection Potholes Cracks Ruhi, Zurana Mehrin Sheetal, Farahatul Aziz Prithu, Farisha Hossain A comparative study of deep learning methods for automating road condition characterization |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. |
| author2 |
Arif, Hossain |
| author_facet |
Arif, Hossain Ruhi, Zurana Mehrin Sheetal, Farahatul Aziz Prithu, Farisha Hossain |
| format |
Thesis |
| author |
Ruhi, Zurana Mehrin Sheetal, Farahatul Aziz Prithu, Farisha Hossain |
| author_sort |
Ruhi, Zurana Mehrin |
| title |
A comparative study of deep learning methods for automating road condition characterization |
| title_short |
A comparative study of deep learning methods for automating road condition characterization |
| title_full |
A comparative study of deep learning methods for automating road condition characterization |
| title_fullStr |
A comparative study of deep learning methods for automating road condition characterization |
| title_full_unstemmed |
A comparative study of deep learning methods for automating road condition characterization |
| title_sort |
comparative study of deep learning methods for automating road condition characterization |
| publisher |
Brac University |
| publishDate |
2021 |
| url |
http://hdl.handle.net/10361/14359 |
| work_keys_str_mv |
AT ruhizuranamehrin acomparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization AT sheetalfarahatulaziz acomparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization AT prithufarishahossain acomparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization AT ruhizuranamehrin comparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization AT sheetalfarahatulaziz comparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization AT prithufarishahossain comparativestudyofdeeplearningmethodsforautomatingroadconditioncharacterization |
| _version_ |
1814308615205421056 |