Affiliation:
1. Changchun Institute of Optics, Fine Mechanics and Physics (CIOMP), Chinese Academy of Sciences, Changchun 130033, China
2. University of Chinese Academy of Sciences, Beijing 101408, China
Abstract
UAV visual-object-tracking technology based on Siamese neural networks has great scientific research and practical application value, and it is widely used in geological surveying, reconnaissance monitoring, and environmental monitoring. Due to the limited onboard computational resources and complex real-world environments of drones, most of the existing tracking systems based on Siamese neural networks struggle to combine excellent performance with high efficiency. Therefore, the key issue is to study how to improve the accuracy of target tracking under the challenges of real-time performance and the above factors. In response to this problem, this paper proposes a real-time UAV tracking system based on interframe saliency transformer and lightweight multidimensional attention network (SiamITL). Specifically, interframe saliency transformer is used to continuously perceive spatial and temporal information, making the network more closely related to the essence of the tracking task. Additionally, a lightweight multidimensional attention network is used to better capture changes in both target appearance and background information, improving the ability of the tracker to distinguish between the target and background. SiamITL is effective and efficient: extensive comparative experiments and ablation experiments have been conducted on multiple aerial tracking benchmarks, demonstrating that our algorithm can achieve more robust feature representation and more accurate target state estimation. Among them, SiamITL achieved success and accuracy rates of 0.625 and 0.818 in the UAV123 benchmark, respectively, demonstrating a certain level of leadership in this field. Furthermore, SiamITL demonstrates the potential for real-time operation on the embedded platform Xavier, highlighting its potential for practical application in real-world scenarios.
Funder
the Department of Science and Technology of Jilin Province
the Science & Technology Development Project of Jilin Province
Subject
General Earth and Planetary Sciences
Reference42 articles.
1. All-Day Object Tracking for Unmanned Aerial Vehicle;Li;IEEE Trans. Mob. Comput.,2022
2. Zhang, Z., Wang, C., Song, J., and Xu, Y. (2022). Object Tracking Based on Satellite Videos: A Literature Review. Remote Sens., 14.
3. Deep learning for unmanned aerial vehicle-based object detection and tracking: A survey;Wu;IEEE Geosci. Remote Sens. Mag.,2021
4. Vision-based object detection and tracking for autonomous navigation of underwater robots;Lee;Ocean. Eng.,2012
5. Deep learning for visual tracking: A comprehensive survey;Cheng;IEEE Trans. Intell. Transp. Syst.,2021