Real-time visual servoing for laparoscopic surgery. Controlling robot motion with color image segmentation

摘要

The authors propose a visual tracking method for stereo laparoscopes, which is robust, simple, and operates at a maximum rate of 17 Hz. The use of a stereo laparoscope enables the robot to track the instrument in both lateral and longitudinal motions. Due to the multiplicity of problems with shape analysis, the authors do not check for the presence of any particular shape or structure. Instead, they use color information alone for instrument segmentation. The non-uniqueness of the instrument color inspires the authors to distinguish it by use of an artificial color mark. They analyzed the color distribution of typical laparoscopic images and chose a color that did not appear to mark the instrument. With color image segmentation, the mark can be correctly located in the image and used to control the robot motion. Thus, even if only a very small part of the instrument is visible, reliable data can still be obtained for robot control. The image processing component is implemented on a commercially available image processing system MaxVideo MV200 (Datacube, Inc., Danvers, MA). The robot the authors use is the AESOP 1000 (Automated Endoscope System for Optimal Positioning) (Computer Motion, Inc., Goleta, CA).