Stereo object tracking with fusion of texture, color and disparity information
作者：
Highlights：
• We perform visual object tracking on stereo videos.
• We use Kalman filter and sub-sampling for object position prediction.
• We use 2-dimensional color–disparity histograms for coarse background subtraction.
• We use Local steering kernels for object texture description.
• We ensure disparity-consistent representation of the tracking results.
摘要
Highlights•We perform visual object tracking on stereo videos.•We use Kalman filter and sub-sampling for object position prediction.•We use 2-dimensional color–disparity histograms for coarse background subtraction.•We use Local steering kernels for object texture description.•We ensure disparity-consistent representation of the tracking results.
论文关键词：Stereo object tracking,Color disparity histograms,Local steering kernels
论文评审过程：Received 21 August 2013, Revised 17 March 2014, Accepted 17 March 2014, Available online 29 March 2014.
论文官网地址：https://doi.org/10.1016/j.image.2014.03.004
