3D soft-tissue tracking using spatial-color joint probability distribution and thin-plate spline model

作者：

Highlights：

• A robust and efficient 3D tracking scheme is proposed.

• Target region is represented using a joint spatial-color probability distribution.

• A novel mean-shift-based iterative algorithm is derived to estimate inter-frame motion.

• Stereo-image pair is matched using an improved thin-plate spline model.

• In vivo videos captured by the daVinci platform and a synthesized video with known ground truth are used for extensive validation.

摘要

Highlights•A robust and efficient 3D tracking scheme is proposed.•Target region is represented using a joint spatial-color probability distribution.•A novel mean-shift-based iterative algorithm is derived to estimate inter-frame motion.•Stereo-image pair is matched using an improved thin-plate spline model.•In vivo videos captured by the daVinci platform and a synthesized video with known ground truth are used for extensive validation.

论文关键词：Robotic surgery,Visual tracking,Motion compensation,Stereo vision,Kernel function

论文评审过程：Received 11 December 2012, Revised 27 January 2014, Accepted 23 March 2014, Available online 4 April 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.03.020