SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion
UAVs have entered various fields of life, and object tracking is one of the key technologies for UAV applications. However, there are various challenges in practical applications, such as the scale change of video images, motion blur and too high shooting angle leading to the tracked objects being t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10400425/ |
| _version_ | 1827346998709190656 |
|---|---|
| author | Yanli Hou Xilin Gai Xintao Wang Yongqiang Zhang |
| author_facet | Yanli Hou Xilin Gai Xintao Wang Yongqiang Zhang |
| author_sort | Yanli Hou |
| collection | DOAJ |
| description | UAVs have entered various fields of life, and object tracking is one of the key technologies for UAV applications. However, there are various challenges in practical applications, such as the scale change of video images, motion blur and too high shooting angle leading to the tracked objects being too small, resulting in poor tracking accuracy. To cope with the problem that small targets are poorly tracked by UAVs due to less effective information output from the deep residual network, a SiamMFF tracking method that introduces an efficient multi-scale feature fusion strategy is proposed. The method aggregates features at different scales, and at the same time, replaces the ordinary convolution with deformable convolution to increase the sense field of convolution operation to enhance the feature extraction capability. The experimental results show that the proposed algorithm improves the success rate and accuracy of small target tracking. |
| first_indexed | 2024-03-07T23:41:00Z |
| format | Article |
| id | doaj.art-0f325936c4444d26aa728cb0cecb134e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T23:41:00Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0f325936c4444d26aa728cb0cecb134e2024-02-20T00:00:41ZengIEEEIEEE Access2169-35362024-01-0112247252473410.1109/ACCESS.2024.335438110400425SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature FusionYanli Hou0Xilin Gai1https://orcid.org/0009-0001-0693-9807Xintao Wang2Yongqiang Zhang3School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, ChinaChina Mobile Hebei Company Ltd., Zhangjiakou Branch, Beijing, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, ChinaUAVs have entered various fields of life, and object tracking is one of the key technologies for UAV applications. However, there are various challenges in practical applications, such as the scale change of video images, motion blur and too high shooting angle leading to the tracked objects being too small, resulting in poor tracking accuracy. To cope with the problem that small targets are poorly tracked by UAVs due to less effective information output from the deep residual network, a SiamMFF tracking method that introduces an efficient multi-scale feature fusion strategy is proposed. The method aggregates features at different scales, and at the same time, replaces the ordinary convolution with deformable convolution to increase the sense field of convolution operation to enhance the feature extraction capability. The experimental results show that the proposed algorithm improves the success rate and accuracy of small target tracking.https://ieeexplore.ieee.org/document/10400425/Siamese networkobject trackingunmanned aerial vehicle(UAV)deformable convolutionmulti-scale feature fusion |
| spellingShingle | Yanli Hou Xilin Gai Xintao Wang Yongqiang Zhang SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion IEEE Access Siamese network object tracking unmanned aerial vehicle(UAV) deformable convolution multi-scale feature fusion |
| title | SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion |
| title_full | SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion |
| title_fullStr | SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion |
| title_full_unstemmed | SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion |
| title_short | SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion |
| title_sort | siammff uav object tracking algorithm based on multi scale feature fusion |
| topic | Siamese network object tracking unmanned aerial vehicle(UAV) deformable convolution multi-scale feature fusion |
| url | https://ieeexplore.ieee.org/document/10400425/ |
| work_keys_str_mv | AT yanlihou siammffuavobjecttrackingalgorithmbasedonmultiscalefeaturefusion AT xilingai siammffuavobjecttrackingalgorithmbasedonmultiscalefeaturefusion AT xintaowang siammffuavobjecttrackingalgorithmbasedonmultiscalefeaturefusion AT yongqiangzhang siammffuavobjecttrackingalgorithmbasedonmultiscalefeaturefusion |