Stereo matching method based on neighborhood related information

Abstract

The invention relates to the field of binocular stereo imaging, and provides a matching cost algorithm with high precision and strong anti-interference capability in order to improve the performance of a Census algorithm under the condition of repeated texture and discontinuity of parallax. Therefore, the technical scheme adopted by the invention is as follows: based on neighborhood related information, as for two to-be-matched input pictures, taking the left view as a reference, taking a window with n * n pixels; calculating the Census transformation matching cost of the model; and taking ann * n window in the right view, moving the window from left to right and from top to bottom, respectively recording values of matching costs of the window, selecting a point with the minimum matchingcost as a matching point of the left image, traversing each point in the left image according to the method, and respectively finding out the corresponding matching point of the point in the right image, thereby completing matching of the left view and the right view. The method is mainly applied to three-dimensional imaging processing occasions.

Description

technical field [0001] The invention relates to the field of binocular stereo imaging, in particular to the core algorithm of stereo matching. The accuracy and robustness of the matching algorithm are improved by combining the Census algorithm based on neighborhood-related information with the AD algorithm. Background technique [0002] Stereo vision technology has been widely used in the fields of virtual reality, three-dimensional measurement, stereo camera, object recognition and robot navigation. Among them, stereo matching is a key technology of stereo vision. Its algorithm has high complexity and needs to process a large amount of data. At present, there is no general algorithm that can meet the requirements of most scenes. [0003] Among many matching algorithms, the AD algorithm is based on the gray value of the pixel, that is, it is assumed that the same feature point of the two images has the same gray value, but the actual situation often does not meet this condi...

AI Technical Summary

Problems solved by technology

Among them, stereo matching is the key technology of stereo vision. Its algorithm is complex and needs to process a large amount of data. At present, there is no general algorithm that can meet the requirements of most scenes.

[0003] Among many matching algorithms, the AD algorithm is based on the gray value of the pixel, that is, it is assumed that the same feature point of the two images has the same gray value, but the actual situation often does not meet this condition, so the algorithm is sensitive to noise and brightness in the image. more sensitive

The matching algorithm based on Census transform uses the size relationship with the gray value of neighboring pixels as the similarity measure, so it has strong anti-interference ability, but repeated or similar local structures in the image will cause false matching

Images