Next Article in Journal
A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
Previous Article in Journal
Assessing the Impacts of Species Composition on the Accuracy of Mapping Chlorophyll Content in Heterogeneous Ecosystems
 
 
Article

A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware

1
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China
2
University of Chinese Academy of Sciences, Beijing 100049, China
*
Author to whom correspondence should be addressed.
Academic Editors: Shiyang Tang, Zhanye Chen, Yan Huang and Ping Guo
Remote Sens. 2021, 13(22), 4672; https://doi.org/10.3390/rs13224672
Received: 22 September 2021 / Revised: 10 November 2021 / Accepted: 16 November 2021 / Published: 19 November 2021
Correlation filter (CF) based trackers have gained significant attention in the field of visual single-object tracking, owing to their favorable performance and high efficiency; however, existing trackers still suffer from model drift caused by boundary effects and filter degradation. In visual tracking, long-term occlusion and large appearance variations easily cause model degradation. To remedy these drawbacks, we propose a sparse adaptive spatial-temporal context-aware method that effectively avoids model drift. Specifically, a global context is explicitly incorporated into the correlation filter to mitigate boundary effects. Subsequently, an adaptive temporal regularization constraint is adopted in the filter training stage to avoid model degradation. Meanwhile, a sparse response constraint is introduced to reduce the risk of further model drift. Furthermore, we apply the alternating direction multiplier method (ADMM) to derive a closed-solution of the object function with a low computational cost. In addition, an updating scheme based on the APCE-pool and Peak-pool is proposed to reveal the tracking condition and ensure updates of the target’s appearance model with high-confidence. The Kalam filter is adopted to track the target when the appearance model is persistently unreliable and abnormality occurs. Finally, extensive experimental results on OTB-2013, OTB-2015 and VOT2018 datasets show that our proposed tracker performs favorably against several state-of-the-art trackers. View Full-Text
Keywords: visual tracking; sparse learning; adaptive spatial-temporal context; correlation filters; high-confidence updating visual tracking; sparse learning; adaptive spatial-temporal context; correlation filters; high-confidence updating
Show Figures

Figure 1

MDPI and ACS Style

Su, Y.; Liu, J.; Xu, F.; Zhang, X.; Zuo, Y. A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware. Remote Sens. 2021, 13, 4672. https://doi.org/10.3390/rs13224672

AMA Style

Su Y, Liu J, Xu F, Zhang X, Zuo Y. A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware. Remote Sensing. 2021; 13(22):4672. https://doi.org/10.3390/rs13224672

Chicago/Turabian Style

Su, Yinqiang, Jinghong Liu, Fang Xu, Xueming Zhang, and Yujia Zuo. 2021. "A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware" Remote Sensing 13, no. 22: 4672. https://doi.org/10.3390/rs13224672

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop