Stereo Vision System with Image Segmentation Technique for Robot Arm Applications

Three-dimensional (3D) information about the environment is essential for robot movement and object inspection in robot arm applications. The stereo vision system is one of the best methods for retrieving depth information. In this research, a pair of cameras is used as a stereo vision module to find the location of an object. The stereo vision system, which consists of camera calibration, image rectification, image segmentation, centroid computation, and object localization, is implemented. Image segmentation is performed through a process of edge-based segmentation, mathematical morphology, and largest area selection. The x,y coordinates are given by the centroid coordinate of the object in the left image, and the z coordinates are computed based on the obtained disparity value. The grayscale left and right images are 100% successful aligned horizontally through the image rectification process. The disparity error is minimized after the image segmentation process. The average error for x and y coordinates are 0.17 cm and 0.36 cm. For the z coordinate, the initial average error is 0.42 cm, but after compensation technique is performed, the average error is reduced to 0.17 cm. Based on the proposed inverse kinematic technique, the robot arm is able to pick up an object with 3D location provided by the stereo vision system.