Multi-camera stereo matching method and device

Abstract

The present invention proposes a multi-camera stereo matching method and device, wherein the method includes: building a multi-camera array according to a preset array structure; controlling an infrared speckle emitter to project structured light spots to a training scene, and obtaining multi-viewpoints through the multi-camera array Image; extract the image features of the multi-viewpoint image, and train the feature extractor according to the image features, so as to obtain the depth information of the scene according to the trained image feature extractor. The present invention can overcome the traditional RGB matching feature sparseness and the high computational complexity of feature extraction and matching, realize high-speed and accurate stereo matching, and can further improve the stereo matching result through the method of probability inference.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a multi-camera stereo matching method and device. Background technique [0002] Stereo matching technology is an important issue in the field of 3D reconstruction and computer vision. With the development and popularization of virtual reality technology and augmented reality technology, high-speed and high-precision stereo matching is becoming an increasingly urgent need. High-quality depth maps have important application value in various fields such as 3D reconstruction, automatic driving, face recognition and positioning. [0003] In related technologies, the acquisition of scene depth information is based on the matching calculation of information between RGB images and depth images, which requires a large amount of calculation, and the current commercial depth cameras all have poor depth image quality, incomplete depth, and low frame rate of depth sequences. The pro...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, the acquisition of scene depth information is based on the matching calculation of information between RGB images and depth images, which requires a large amount of calculation, and the current commercial depth cameras all have poor depth image quality, incomplete depth, and low frame rate of depth sequences. The problem is that when matching the RGB image with the depth image, the depth information corresponding to the RGB pixel cannot be matched, or the matched depth information has a large deviation, resulting in low accuracy of scene depth information acquisition.

Images