A Model-free Vision-based Robot Control for Minimally Invasive Surgery using ESM Tracking and Pixels Color Selection

Abstract

This paper deals with the visual servoing of textured surfaces inside the human abdomen with a laparoscope for the robot-assisted minimally invasive surgery (MIS). The well-known image-based visual servoing (IBVS) is one of the most common approaches used for model-based servoing. When no CAD model is available, the efficient second-order minimization (ESM) tracking developed by Malis (2002, 2004) for grey-level images is one of the powerful recent techniques which is extended here to color images so as to handle occluded parts of the region of interest (ROI). Firstly, the ROI is splitted into small areas and a histogram-based color feature comparison of image areas is presented. For each frame and for each area, a metric based on the Bhattacharyya criterion is used to select the contributing areas for the computation of the planar homography between views. Secondly, since for any MIS technique, the endoscopic lens is passing through an insertion point on the abdominal wall, a specific control strategy is developed to perform the ESM tracking with a 4-DOF surgical robot. The method presented in this paper has been validated with several video sequences. Experimental results show that the tracking method is efficient even with more than 75 % of the tracked ROI occluded. Finally, the model-free visual servoing has been performed with the AESOP surgical robot and a training box. Even if the convergence rate is a little bit slow, the desired region is always reached.