Siamese Network Tracker Based on Multi-Scale Feature Fusion
The main task in visual object tracking is to track a moving object in an image sequence. In this process, the object’s trajectory and behavior can be described by calculating the object’s position, velocity, acceleration, and other parameters or by memorizing the position of the object in each fram...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-8954/11/8/434 |
| _version_ | 1797583146109108224 |
|---|---|
| author | Jiaxu Zhao Dapeng Niu |
| author_facet | Jiaxu Zhao Dapeng Niu |
| author_sort | Jiaxu Zhao |
| collection | DOAJ |
| description | The main task in visual object tracking is to track a moving object in an image sequence. In this process, the object’s trajectory and behavior can be described by calculating the object’s position, velocity, acceleration, and other parameters or by memorizing the position of the object in each frame of the corresponding video. Therefore, visual object tracking can complete many more advanced tasks, has great performance in relation to real scenes, and is widely used in automated driving, traffic monitoring, human–computer interaction, and so on. Siamese-network-based trackers have been receiving a great deal of attention from the tracking community, but they have many drawbacks. This paper analyzes the shortcomings of the Siamese network tracker in detail, uses the method of feature multi-scale fusion to improve the Siamese network tracker, and proposes a new target-tracking framework to address its shortcomings. In this paper, a feature map with low-resolution but strong semantic information and a feature map with high-resolution and rich spatial information are integrated to improve the model’s ability to depict an object, and the problem of scale change is solved by fusing features at different scales. Furthermore, we utilize the 3D Max Filtering module to suppress repeated predictions of features at different scales. Finally, our experiments conducted on the four tracking benchmarks OTB2015, VOT2016, VOT2018, and GOT10K show that the proposed algorithm effectively improves the tracking accuracy and robustness of the system. |
| first_indexed | 2024-03-10T23:32:41Z |
| format | Article |
| id | doaj.art-79ae715b22af435f92ca68e4af17c9d1 |
| institution | Directory Open Access Journal |
| issn | 2079-8954 |
| language | English |
| last_indexed | 2024-03-10T23:32:41Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Systems |
| spelling | doaj.art-79ae715b22af435f92ca68e4af17c9d12023-11-19T03:13:08ZengMDPI AGSystems2079-89542023-08-0111843410.3390/systems11080434Siamese Network Tracker Based on Multi-Scale Feature FusionJiaxu Zhao0Dapeng Niu1College of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaThe main task in visual object tracking is to track a moving object in an image sequence. In this process, the object’s trajectory and behavior can be described by calculating the object’s position, velocity, acceleration, and other parameters or by memorizing the position of the object in each frame of the corresponding video. Therefore, visual object tracking can complete many more advanced tasks, has great performance in relation to real scenes, and is widely used in automated driving, traffic monitoring, human–computer interaction, and so on. Siamese-network-based trackers have been receiving a great deal of attention from the tracking community, but they have many drawbacks. This paper analyzes the shortcomings of the Siamese network tracker in detail, uses the method of feature multi-scale fusion to improve the Siamese network tracker, and proposes a new target-tracking framework to address its shortcomings. In this paper, a feature map with low-resolution but strong semantic information and a feature map with high-resolution and rich spatial information are integrated to improve the model’s ability to depict an object, and the problem of scale change is solved by fusing features at different scales. Furthermore, we utilize the 3D Max Filtering module to suppress repeated predictions of features at different scales. Finally, our experiments conducted on the four tracking benchmarks OTB2015, VOT2016, VOT2018, and GOT10K show that the proposed algorithm effectively improves the tracking accuracy and robustness of the system.https://www.mdpi.com/2079-8954/11/8/434visual object trackingautomated drivingdeep learningartificial intelligencecomputer vision |
| spellingShingle | Jiaxu Zhao Dapeng Niu Siamese Network Tracker Based on Multi-Scale Feature Fusion Systems visual object tracking automated driving deep learning artificial intelligence computer vision |
| title | Siamese Network Tracker Based on Multi-Scale Feature Fusion |
| title_full | Siamese Network Tracker Based on Multi-Scale Feature Fusion |
| title_fullStr | Siamese Network Tracker Based on Multi-Scale Feature Fusion |
| title_full_unstemmed | Siamese Network Tracker Based on Multi-Scale Feature Fusion |
| title_short | Siamese Network Tracker Based on Multi-Scale Feature Fusion |
| title_sort | siamese network tracker based on multi scale feature fusion |
| topic | visual object tracking automated driving deep learning artificial intelligence computer vision |
| url | https://www.mdpi.com/2079-8954/11/8/434 |
| work_keys_str_mv | AT jiaxuzhao siamesenetworktrackerbasedonmultiscalefeaturefusion AT dapengniu siamesenetworktrackerbasedonmultiscalefeaturefusion |