期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 52, 期 4, 页码 2418-2429出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2020.3005453
关键词
Target tracking; Semantics; Videos; Correlation; Real-time systems; Proposals; Unmanned aerial vehicles; Detection proposals; discriminative correlation filter (DCF); semantic information; unmanned aerial vehicle (UAV) tracking
类别
资金
- National Natural Science Foundation of China [61871460]
- Shaanxi Provincial Key Research and Development Program [2020KW-003]
- Fundamental Research Funds for the Central Universities [3102019ghxm016]
- Innovation Foundation for Graduate Students School-Enterprise Cooperation of Northwestern Polytechnical University [XQ201905]
- Ser Cymru II Strategic Partner Acceleration Award Programme, U.K. [80761-AU201]
This article presents a novel semantic-aware real-time correlation tracking framework (SARCT) to improve the performance of DCF trackers in UAV videos. SARCT constructs an additional detection module to generate ROI proposals and introduces a semantic segmentation module to capture semantic information, thereby enhancing the accuracy of tracking.
Discriminative correlation filter (DCF) has contributed tremendously to address the problem of object tracking benefitting from its high computational efficiency. However, it has suffered from performance degradation in unmanned aerial vehicle (UAV) tracking. This article presents a novel semantic-aware real-time correlation tracking framework (SARCT) for UAV videos to enhance the performance of DCF trackers without incurring excessive computing cost. Specifically, SARCT first constructs an additional detection module to generate ROI proposals and to filter any response regarding the target irrelevant area. Then, a novel semantic segmentation module based on semantic template generation and semantic coefficient prediction is further introduced to capture semantic information, which can provide precise ROI mask, thereby effectively suppressing background interference in the ROI proposals. By sharing features and specific network layers for object detection and semantic segmentation, SARCT reduces parameter redundancy to attain sufficient speed for real-time applications. Systematic experiments are conducted on three typical aerial datasets in order to evaluate the performance of the proposed SARCT. The results demonstrate that SARCT is able to improve the accuracy of conventional DCF-based trackers significantly, outperforming state-of-the-art deep trackers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据