Binocular stereoscopic vision matching method combining depth characteristics

Abstract

The invention discloses a binocular stereoscopic vision matching method combining depth characteristics. The binocular stereoscopic vision matching method comprises: obtaining a depth characteristic pattern from left and right images through a convolutional neural network; calculating a truncation similarity measurement degree of pixel depth characteristics by taking the depth characteristics as the standard, and constructing a truncation matching cost function combining color, gradients and depth characteristics to obtain a matched cost volume; processing the matched cost volume by adopting a fixed window, a variable window and a self-adaptive weight polymerization or guide filtering method to obtain a cost volume polymerized by a matching cost; selecting an optimal parallax error of the cost volume by adopting WTA (Wireless Telephony Application) to obtain an initial parallax error pattern; then finding a shielding region by adopting a double-peak test, left-right consistency detection, sequence consistency detection or shielding constraint algorithm, and giving a shielding point to a parallax error value of a same-row point closest to the shielding point to obtain a parallax error pattern; and filtering the parallax error pattern by adopting a mean value or bilateral filter to obtain a final parallax error pattern. By adopting the binocular stereoscopic vision matching method combining the depth characteristics, the incorrect matching rate of three-dimensional matching can be effectively reduced, the images are smooth and image edges including edges of small objects are effectively kept.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a binocular stereo vision matching method with low error matching rate, smooth image and capable of effectively maintaining combined depth features of image edges. Background technique [0002] Because the binocular stereo vision system is closest to the human visual system, it is one of the most active directions in the field of computer vision in recent decades. The binocular stereo vision system uses a monocular or binocular camera to observe the scene, obtains two images of the same world scene under different perspectives, and processes the images through computer-aided technology to simulate the human binocular vision system to obtain the three-dimensional information of the scene the process of. In the decades since the development of binocular stereo vision, it has been widely used in robot vision, medical diagnosis, aerial surveying and mapping, mili...

AI Technical Summary

Problems solved by technology

The existing stereo matching method based on image features can only obtain the disparity value of the pixels in the feature area, and the matching result is sparse. If you want to obtain a dense disparity map, you need to use subsequent interpolation algorithms. However, this will Correspondingly reduce the accuracy of matching

The dense binocular stereo matching algorithm can be divided into two categories: local stereo matching algorithm and global stereo matching algorithm. The global stereo matching algorithm can usually obtain better stereo matching results with the help of various constraints and global optimization strategies, but this type of algorithm The disadvantages of the stereo matching algorithm are high complexity and large amount of calculation; the local stereo matching algorithm has less calculation amount than the global algorithm, and the complexity is low, but its matching accuracy is relatively low.

Images