The Research On Location Of Dynamic Target Based On Binocular Vision And Grabbing System

Binocular Stereo Vision can obtain and rebuild the 3D information of objects, it is widely used in robot recognition and location, medical image analysis, agriculture, construction industry and so on, thus, researching on Binocular Stereo Vision has great significance both in theory and practice. This thesis is based on the basic theory of Binocular Stereo Vision, using camera calibration and image processing techniques, developing the recognition and location of objects and grabbing system, which is based on Binocular Stereo Vision, and designing the three-axis grabbing platform YASKAWA-MH6 S to do experiments on recognition, location and grabbing, Main researching content as followed:Camera calibration, building the imaging model of camera, considering the impact of camera distortion in the process of imaging, adopting the classical Zhang Zhen-you two steps calibration, obtaining the internal and external parameters of binocular camera, and acquiring the rotation matrix and translation vector between camera and real world coordinate.Feature extraction and objects recognition algorithm, through experiments to verify the extraction result used Surf algorithm under noise interference, using template matching algorithm which is based on feature point extraction to recognize.Due to the numerous error matching points, they will influence the result of matching, and because of the image searching in the process of matching is under 2D conditions, the execution efficiency of algorithm is low, this thesis improves the algorithm in the process of stereo matching, adopting stereo matching algorithm which is based on relative Euclidean distance and polar constraint to remove the error matching points, the rapidity and effectiveness of searching, through experiments to check the analysis.By the method of D-H parameters of six degrees of freedom mechanical arm kinematics modeling, and on the basis of the forward kinematics and inverse kinematics of manipulator are analyzed and the solving, on the control in this paper is a master-slave control mode, communication uses the network transmission, master machine adopts computer platform, responsible for image acquisition, target attitude algorithm, it is concluded that to control the movement of robot arm the joint Angle, the machine adopts industrial mechanical arm controller. Transport the objects position information to grab system of 3d reconstruction for fetching experiment, and analyze the scraping of the error, this system was verified in actual industrial production ha s a certain application value.