Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking
To enhance the correlation of feature information and enrich the pattern of cross-correlation metrics, we propose the Siam ST algorithm, which is based on a three-stage cascade (TSC) architecture. The sliding window is introduced in the last three layers of convolution blocks, which can obtain the g...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024176438 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573157433671680 |
|---|---|
| author | Zheng Yang Kaiwen Liu Quanlong Li Yandong Hou Zhiyu Yan |
| author_facet | Zheng Yang Kaiwen Liu Quanlong Li Yandong Hou Zhiyu Yan |
| author_sort | Zheng Yang |
| collection | DOAJ |
| description | To enhance the correlation of feature information and enrich the pattern of cross-correlation metrics, we propose the Siam ST algorithm, which is based on a three-stage cascade (TSC) architecture. The sliding window is introduced in the last three layers of convolution blocks, which can obtain the global information of images and fully capture the target feature. The TSC structure is developed by using the regional proposal network. It makes the features of the current frame interact with the previous frame. As a result, our method has a high effect of robustness and association features extraction. Therefore, our ablation experiments are conducted on the VOT2016 dataset, and comparison experiments are conducted on four datasets, VOT2018, LaSOT, Tracking Net, and UAV123. Our proposed algorithm demonstrates a significant improvement compared to SiamRPN++ across four datasets. |
| format | Article |
| id | doaj-art-8545d6fc6203475e965f51aa130a96ba |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-8545d6fc6203475e965f51aa130a96ba2025-02-02T05:27:53ZengElsevierHeliyon2405-84402025-01-01112e41612Three-stage cascade architecture-based siamese sliding window network algorithm for object trackingZheng Yang0Kaiwen Liu1Quanlong Li2Yandong Hou3Zhiyu Yan4School of Electrical Engineering, Yellow River Conservancy Technical Institute, Dongjing street, Kaifeng, 475004, Henan, ChinaSchool of Artificial Intelligence, Henan University, Mingli street, Zhengzhou, 450000, Henan, ChinaSchool of Artificial Intelligence, Henan University, Mingli street, Zhengzhou, 450000, Henan, ChinaSchool of Artificial Intelligence, Henan University, Mingli street, Zhengzhou, 450000, Henan, ChinaSchool of Electrical Engineering, Yellow River Conservancy Technical Institute, Dongjing street, Kaifeng, 475004, Henan, China; Corresponding author.To enhance the correlation of feature information and enrich the pattern of cross-correlation metrics, we propose the Siam ST algorithm, which is based on a three-stage cascade (TSC) architecture. The sliding window is introduced in the last three layers of convolution blocks, which can obtain the global information of images and fully capture the target feature. The TSC structure is developed by using the regional proposal network. It makes the features of the current frame interact with the previous frame. As a result, our method has a high effect of robustness and association features extraction. Therefore, our ablation experiments are conducted on the VOT2016 dataset, and comparison experiments are conducted on four datasets, VOT2018, LaSOT, Tracking Net, and UAV123. Our proposed algorithm demonstrates a significant improvement compared to SiamRPN++ across four datasets.http://www.sciencedirect.com/science/article/pii/S2405844024176438Single object trackingDeep learningSiamese networksSliding windowThree-level cascade |
| spellingShingle | Zheng Yang Kaiwen Liu Quanlong Li Yandong Hou Zhiyu Yan Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking Heliyon Single object tracking Deep learning Siamese networks Sliding window Three-level cascade |
| title | Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking |
| title_full | Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking |
| title_fullStr | Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking |
| title_full_unstemmed | Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking |
| title_short | Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking |
| title_sort | three stage cascade architecture based siamese sliding window network algorithm for object tracking |
| topic | Single object tracking Deep learning Siamese networks Sliding window Three-level cascade |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024176438 |
| work_keys_str_mv | AT zhengyang threestagecascadearchitecturebasedsiameseslidingwindownetworkalgorithmforobjecttracking AT kaiwenliu threestagecascadearchitecturebasedsiameseslidingwindownetworkalgorithmforobjecttracking AT quanlongli threestagecascadearchitecturebasedsiameseslidingwindownetworkalgorithmforobjecttracking AT yandonghou threestagecascadearchitecturebasedsiameseslidingwindownetworkalgorithmforobjecttracking AT zhiyuyan threestagecascadearchitecturebasedsiameseslidingwindownetworkalgorithmforobjecttracking |