The Research Of Visual Positioning Technology On The Binocular Robot

With the development of the industry automation, and the improvement of the automation level of production, the robot vision becomes more and more important in the automatic production. The technology of stereovision is the most active embranchment, and it is also the important symbol of the intelligent robots.By referring to a great deal of the information available, we have used the technology of the binocular stereoscopic vision to make recognize and locate the target by the robot . Firstly, a CCD calibrating approach that it is in the midst of traditional and self-calibrating methods has been presented to separate the inner and the outer parameters. Based on perspective model, the camera inner parameters were proposed with physics method. The outer parameter model of two CCD can be constructed by selecting appropriate reference frame and analyzing experiment data. The method is simple, speediness, understandability, and practicality. Then the results of computer simulations prove that the method is correct. Secondly, using digital image processing technology basically and combining with pattern recognition technology, the stereo matching way based on the feature has been studied, and then took the preprocess method fit for the task. In image segmentation, this paper proposed Color Image Segmentation method which has been changed a bit to make it more suitable for the task. Target feature extraction for circular features with the objective, extracting characteristics of the central objectives, and then matching the feature points of left image's object and right image' object under the constraint of epipolar line. Finally,combined the camera's calibrating results and the feature points of the object,and used the imaging cameras inverse transform to recover the depth characteristics of the target points, then the object's position is known.The results of the experiment show that the method of binocular stereoscopic vision has a high precision.