Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (3): 165-176.DOI: 10.3778/j.issn.1002-8331.2208-0409

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Correlation Filtering Target Tracking Algorithm Based on Nonlinear Spatio-Temporal Regularization

JIANG Wentao, WANG Deqiang, ZHANG Shengchong   

  1. 1.School of Software, Liaoning Technical University, Huludao, Liaoning 125105, China
    2.Science and Technology on Electro-Optical Information Security Control Laboratory, Tianjin 300308, China
  • Online:2024-02-01 Published:2024-02-01

非线性时空正则化的相关滤波目标跟踪算法

姜文涛,王德强,张晟翀   

  1. 1.辽宁工程技术大学 软件学院,辽宁 葫芦岛 125105
    2.光电信息控制和安全技术重点实验室,天津 300308

Abstract: In order to address the problem that the tracking model tends to drift during target tracking and cannot be robustly tracked for targets with diverse morphological changes, a correlation filtering target tracking algorithm based on nonlinear spatio-temporal regularization is proposed according to the law of biological visual perception. Firstly, a temporal regularization term for nonlinear filter update that is close to the power law of human visual perception is proposed in the objective function. Compared to the fixed temporal regularization term in the STRCF (spatio-temporal regularized correlation filter), the temporal regularization term updated by the nonlinear filter can be adaptively updated according to the tracked temporal changes, and the algorithm complexity is reduced by the alternate multiplier method. Then, nonlinear HOG (histogram of oriented gradient) features are extracted and scale adaptation is performed using log-polar coordinates conforming to biological mapping. Finally, occlusion anomaly detection is performed according to the relationship between the maximum response value and average peak-to-correlation energy, which reduces the probability of model drift and enhances the anti-occlusion ability of the algorithm. The experimental results show that the accuracy and success rate of the algorithm tested on the OTB2015 dataset are 89.8% and 83.3%, respectively. Compared with STRCF, the proposed algorithm improves the accuracy rate by 2.5% and the success rate by 3.2%. In the classification comparison of 11 attributes on OTB2013 and OTB2015, the proposed algorithm has higher accuracy and stronger robustness in target tracking under the interference of rotating, low-resolution background, clutter, illumination change and other factors.

Key words: target tracking, nonlinear filter update, nonlinear HOG feature extraction, log-polar coordinate scale adaptation, biological visual perception law

摘要: 针对目标跟踪过程中跟踪模型容易漂移,以及对于多样性形态变化的目标不能进行鲁棒跟踪的问题,结合生物视觉感知规律提出了非线性时空正则化的相关滤波目标跟踪算法。在目标函数中提出贴近人类视觉感知幂定律的非线性滤波更新的时间正则项,相比于时空正则相关滤波器(spatial-temporal regularized correlation filters,STRCF)中固定的时间正则项,非线性滤波更新的时间正则项可以根据跟踪的时间变化进行自适应更新,同时采用交替乘子法降低算法复杂度。提取非线性的梯度方向直方图(histogram of oriented gradient,HOG)特征,使用符合生物映射的对数极坐标进行尺度适应。根据最大响应值与平均峰值相关能量的关系进行遮挡异常检测,降低模型漂移的机率,增强算法的抗遮挡能力。实验结果表明,该算法在OTB2015数据集上的精确率和成功率分别达到89.8%和83.3%,该算法相比于STRCF在精确率上提升了2.5%,在成功率上提升了3.2%,在OTB2013与OTB2015数据集上的11种属性的分类对比中,该算法在旋转、低分辨率、背景杂乱、光照变化等因素干扰下的目标跟踪中具有较高的精确率和较强的鲁棒性。

关键词: 目标跟踪, 非线性滤波器更新, 非线性HOG特征提取, 对数极坐标尺度适应, 生物视觉感知规律