Skip to Content
You are currently on the new version of our website. Access the old version .
SensorsSensors
  • Article
  • Open Access

12 December 2017

16 Pages

Consistently Sampled Correlation Filters with Space Anisotropic Regularization for Visual Tracking

,
,
,
and
1
School of Optoelectronics, Image Engineering & Video Technology Lab, Beijing Institute of Technology, Beijing 100081, China
2
Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, China
*
Author to whom correspondence should be addressed.
This article belongs to the Section Physical Sensors

Abstract

Most existing correlation filter-based tracking algorithms, which use fixed patches and cyclic shifts as training and detection measures, assume that the training samples are reliable and ignore the inconsistencies between training samples and detection samples. We propose to construct and study a consistently sampled correlation filter with space anisotropic regularization (CSSAR) to solve these two problems simultaneously. Our approach constructs a spatiotemporally consistent sample strategy to alleviate the redundancies in training samples caused by the cyclical shifts, eliminate the inconsistencies between training samples and detection samples, and introduce space anisotropic regularization to constrain the correlation filter for alleviating drift caused by occlusion. Moreover, an optimization strategy based on the Gauss-Seidel method was developed for obtaining robust and efficient online learning. Both qualitative and quantitative evaluations demonstrate that our tracker outperforms state-of-the-art trackers in object tracking benchmarks (OTBs).

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.