Stereo matching method based on deep learning

Abstract

The invention provides a stereo matching method based on deep learning. The stereo matching method based on deep learning utilizes the deep learning method to extract characteristics, wherein the receptive field of each point of the obtained characteristic spectrum very large, and at the same time, the foreground expansion effect caused by a traditional local matching method is avoided, and the problem that the local matching method is hard to select windows is solved. Besides, the high dimension characteristic spectrum obtained through deep learning fully describes the data distribution characteristics of the area and has significant guiding meaning for the subsequent similarity detection. The stereo matching method based on deep learning utilizes the deep learning method to output a W*H*D cost body according to the left and right views, utilizes the WTA strategy that the winner takes it all to obtain an initial parallax graph, and finally utilizes the original left view as the guiding image to guide filtering. The stereo matching method based on deep learning has higher accuracy, and can reasonably operates GPU parallel acceleration to enable the method to achieve high operatingspeed as the parallelization degree of the neural network is high.

Description

technical field [0001] The invention relates to stereo matching technology. Background technique [0002] Binocular vision is an important branch of computer vision, and stereo matching is the most important part of binocular vision. Binocular distance measurement generally uses two identical cameras to obtain two images of the same scene with different perspectives at the same time, and then uses the stereo matching method to find the corresponding relationship between the same object or texture in the two images, and finally restores the image based on the parallax. The distance of the object from the camera. [0003] In general, stereo matching methods can be divided into global methods and local methods. Based on the assumption of smoothness, the global method uses various methods to construct the global energy function, and uses the optimization method to calculate the minimum point of the energy function. Whereas local methods rely on local information and determine...

AI Technical Summary

Problems solved by technology

[0004] The global stereo matching algorithm uses two constraints of image smoothness and data items to solve the minimum value of the overall energy function, which usually has a large amount of calculation, and is difficult to perform parallel optimization, takes a long time, and is not suitable for real-time systems

[0005] Semi-global stereo matching has the following defects: (1) It is difficult to determine the size of the window: if the window is too large, it will require a large amount of calculation, and the foreground expansion effect will be generated in the depth discontinuity area, and the effect of the edge is very poor; if the window is too small, it cannot contain All the texture features of the object cause ambiguity in the matching results

(2) The value used to calculate the cost is only the gray value of the image or the low-order difference, which cannot describe the features well

Even if the non-parametric Census transform is used, it only enhances the robustness to noise and cannot solve the problem of insufficient feature description.

Images