Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion
In autonomous driving, target tracking is essential to environmental perception. The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception, which is of great significance in ensuring the safety of autonomous driving and promoting the landing of te...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2023-12-01
|
| Series: | Journal of Intelligent and Connected Vehicles |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/JICV.2023.9210018 |
| _version_ | 1797293752256036864 |
|---|---|
| author | Quan Yuan Haixu Shi Ashton Tan Yu Xuan Ming Gao Qing Xu Jianqiang Wang |
| author_facet | Quan Yuan Haixu Shi Ashton Tan Yu Xuan Ming Gao Qing Xu Jianqiang Wang |
| author_sort | Quan Yuan |
| collection | DOAJ |
| description | In autonomous driving, target tracking is essential to environmental perception. The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception, which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications. This study focuses on the fusion tracking algorithm based on visible and infrared images. The proposed approach utilizes a feature-level image fusion method, dividing the tracking process into two components: image fusion and target tracking. An unsupervised network, Visible and Infrared image Fusion Network (VIF-net), is employed for visible and infrared image fusion in the image fusion part. In the target tracking part, Siamese Region Proposal Network (SiamRPN), based on deep learning, tracks the target with fused images. The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234. Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images, proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images. This improvement is also attributed to the algorithm’s ability to extract infrared image features, augmenting the target tracking accuracy. |
| first_indexed | 2024-03-07T21:19:18Z |
| format | Article |
| id | doaj.art-ccc48dab130f45048119086459705246 |
| institution | Directory Open Access Journal |
| issn | 2399-9802 |
| language | English |
| last_indexed | 2024-03-07T21:19:18Z |
| publishDate | 2023-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Journal of Intelligent and Connected Vehicles |
| spelling | doaj.art-ccc48dab130f450481190864597052462024-02-27T15:40:41ZengTsinghua University PressJournal of Intelligent and Connected Vehicles2399-98022023-12-016423724910.26599/JICV.2023.9210018Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusionQuan Yuan0Haixu Shi1Ashton Tan Yu Xuan2Ming Gao3Qing Xu4Jianqiang Wang5State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, ChinaIn autonomous driving, target tracking is essential to environmental perception. The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception, which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications. This study focuses on the fusion tracking algorithm based on visible and infrared images. The proposed approach utilizes a feature-level image fusion method, dividing the tracking process into two components: image fusion and target tracking. An unsupervised network, Visible and Infrared image Fusion Network (VIF-net), is employed for visible and infrared image fusion in the image fusion part. In the target tracking part, Siamese Region Proposal Network (SiamRPN), based on deep learning, tracks the target with fused images. The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234. Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images, proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images. This improvement is also attributed to the algorithm’s ability to extract infrared image features, augmenting the target tracking accuracy.https://www.sciopen.com/article/10.26599/JICV.2023.9210018target trackingimage fusioninfrared imagedeep learningautonomous driving |
| spellingShingle | Quan Yuan Haixu Shi Ashton Tan Yu Xuan Ming Gao Qing Xu Jianqiang Wang Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion Journal of Intelligent and Connected Vehicles target tracking image fusion infrared image deep learning autonomous driving |
| title | Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| title_full | Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| title_fullStr | Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| title_full_unstemmed | Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| title_short | Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| title_sort | enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion |
| topic | target tracking image fusion infrared image deep learning autonomous driving |
| url | https://www.sciopen.com/article/10.26599/JICV.2023.9210018 |
| work_keys_str_mv | AT quanyuan enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion AT haixushi enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion AT ashtontanyuxuan enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion AT minggao enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion AT qingxu enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion AT jianqiangwang enhancedtargettrackingalgorithmforautonomousdrivingbasedonvisibleandinfraredimagefusion |