RESEARCH OF CORRESPONDENCE POINTS MATCHING ON BINOCULAR STEREO VISION MEASUREMENT SYSTEM BASED ON WAVELET

摘要

A method is presented to solve correspondence points matching on binocular stereo vision measurement system. It is based on that the multi-scale zero-crossings of wavelet transform can obtain the locations of the signal sharp variation points at scales for a particular class of wavelets. After studying the physical model of binocular stereo vision measurement system, a coarse to fine matching algorithm is applied to solve the problem of correspondence points matching. First we match the bigger scale zero-crossings,compute the disparity and then match the smaller scale zerocrossings under the restriction of disparity using the distance information. Thus the complexity of correspondence points matching is decreased and the matching mistake is reduced. The thickness of cement clinker in the cooler is measured using this method. The experiment result indicates that the distributing status of cement clinker thickness can be calculated accurately. Error measured in this method is lower than that measured in the old method.