Vehicle re-identification using machine learning
Vehicle Re-ID aims to retrieve images of the same vehicle across non-overlapping cameras. The key challenges lie in the subtle inter-class discrepancy caused by near-duplicated identities and the significant intra-class distance due to diverse factors, including illumination, viewpoints, and backgro...
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | Thesis-Master by Research |
| اللغة: | English |
| منشور في: |
Nanyang Technological University
2022
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://hdl.handle.net/10356/154813 |
| _version_ | 1826130668680118272 |
|---|---|
| author | Tang, Lisha |
| author2 | Lap-Pui Chau |
| author_facet | Lap-Pui Chau Tang, Lisha |
| author_sort | Tang, Lisha |
| collection | NTU |
| description | Vehicle Re-ID aims to retrieve images of the same vehicle across non-overlapping cameras. The key challenges lie in the subtle inter-class discrepancy caused by near-duplicated identities and the significant intra-class distance due to diverse factors, including illumination, viewpoints, and background interference. This thesis starts with reviewing the development history of vehicle Re-ID and proposes a Part-Mentored Attention Network (PMANet) consisting of a Part Attention Network (PANet) for weakly-supervised vehicle part localization and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation. Firstly, PANet predicts a foreground mask and pinpoints K prominent vehicle parts without additional part-level supervision. Secondly, PMNet applies multi-scale soft attention on localized regions and compensates inaccurate part masks with part-guided learning. PANet and PMNet construct a two-stage attention structure to perform a coarse-to-fine search among identities. Finally, we address this Re-ID issue as a multi-task problem and employ Homoscedastic Uncertainty Learning to automatically balance the loss weightings. Experimental results show that our approach outperforms recent state-of-the-art methods by averagely 2.63% in CMC@1 on VehicleID and 2.2% in mAP on VeRi776. |
| first_indexed | 2024-10-01T08:00:02Z |
| format | Thesis-Master by Research |
| id | ntu-10356/154813 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T08:00:02Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1548132023-07-04T17:25:03Z Vehicle re-identification using machine learning Tang, Lisha Lap-Pui Chau School of Electrical and Electronic Engineering elpchau@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Vehicle Re-ID aims to retrieve images of the same vehicle across non-overlapping cameras. The key challenges lie in the subtle inter-class discrepancy caused by near-duplicated identities and the significant intra-class distance due to diverse factors, including illumination, viewpoints, and background interference. This thesis starts with reviewing the development history of vehicle Re-ID and proposes a Part-Mentored Attention Network (PMANet) consisting of a Part Attention Network (PANet) for weakly-supervised vehicle part localization and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation. Firstly, PANet predicts a foreground mask and pinpoints K prominent vehicle parts without additional part-level supervision. Secondly, PMNet applies multi-scale soft attention on localized regions and compensates inaccurate part masks with part-guided learning. PANet and PMNet construct a two-stage attention structure to perform a coarse-to-fine search among identities. Finally, we address this Re-ID issue as a multi-task problem and employ Homoscedastic Uncertainty Learning to automatically balance the loss weightings. Experimental results show that our approach outperforms recent state-of-the-art methods by averagely 2.63% in CMC@1 on VehicleID and 2.2% in mAP on VeRi776. Master of Engineering 2022-01-10T08:59:23Z 2022-01-10T08:59:23Z 2021 Thesis-Master by Research Tang, L. (2021). Vehicle re-identification using machine learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154813 https://hdl.handle.net/10356/154813 10.32657/10356/154813 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Tang, Lisha Vehicle re-identification using machine learning |
| title | Vehicle re-identification using machine learning |
| title_full | Vehicle re-identification using machine learning |
| title_fullStr | Vehicle re-identification using machine learning |
| title_full_unstemmed | Vehicle re-identification using machine learning |
| title_short | Vehicle re-identification using machine learning |
| title_sort | vehicle re identification using machine learning |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/154813 |
| work_keys_str_mv | AT tanglisha vehiclereidentificationusingmachinelearning |