A Porcine Abdomen Cutting Robot System Using Binocular Vision Techniques Based on Kernel Principal Component Analysis

The purpose of this paper is to provide details on the implementation of an accurate and intelligent automation solution to achieve the abdomen cutting operation of the porcine carcass. The system consists of an industrial robot, a binocular camera, an end effector, and an industrial computer. Threshold segmentation is used to detect the contour of the porcine carcass. Based on the contour, the kernel principal component analysis (KPCA) is used to identify the cutting line position. A binocular camera completes the depth extraction of the centerline, and the robot trajectory is adjusted based on the curve of the porcine abdomen centerline. The results of the experiment show that the system could successfully open the porcine abdomen without viscera damage. The constructed system can improve process quality, hygiene standards efficiency, and save a lot of labor.