Add attention mechanism into traditional robot stereo vision system, thus got the possible workpiece position quickly by saliency image, highly accelerate the computing process. First, to get the camera intrinsic matrix and extrinsic matrix, camera stereo calibration needed be done. Then use those parameter matrixes to rectify the newly captured images, disparity map can be got based on the OpenCV library, meanwhile, saliency image was computed by Itti algorithm. Workpiece spatial pose to left camera coordinates can be got with triangulation measurement principal. After a series of coordinates transformation workpiece spatial pose to world coordinates can be got. With the robot inverse solution function, the robot joint rotation angle can be got thus driver the robot to work. At last, experiment results show the effectiveness of this method.
Intelligent Path Recognition against Image Noises for Vision Guidance of Automated Guided Vehicles in a Complex Workspace