Binary neural network stereo vision matching method realized based on FPGA

Abstract

The invention relates to a binary neural network stereo vision matching method based on an FPGA. The method comprises the following steps of 1, obtaining periodic input streams of pixels in a binocular matching grayscale image, 2, acquiring an image block from the pixel, 3, inputting the image blocks in the step 2 into a binary neural network with preset weights and parameters to obtain binary feature vectors, 4, performing cost calculation on the feature vector within the maximum search parallax to obtain a matching cost, 5, inputting the cost into semi-global cost aggregation for cost aggregation to obtain aggregated cost, 6, selecting the position with the minimum cost from the aggregated cost as parallax, and 7, carrying out consistency detection and parallax refinement calculation onthe selected parallax to obtain a parallax graph, and outputting parallax values of the pixels one by one according to a period. By means of the binarization method, computing and storage resources ofthe network can be effectively reduced, and therefore the high-precision stereo matching network can be deployed into the FPGA.

Description

technical field [0001] The invention relates to the field of visual matching, and more specifically, relates to a binary neural network stereoscopic visual matching method implemented based on FPGA. Background technique [0002] Obtaining the depth information of images in real time is a hotspot of current biological vision, and using mathematical features for feature matching is the current main method. The steps of the binocular stereo vision technology include: obtaining the internal and external parameters of the binocular camera; performing baseline correction and alignment on the binocular images according to the internal and external parameters; calculating the matching cost of the binocular images; cost aggregation; depth selection; and depth optimization. Calculating the matching cost of binocular images is the key to obtaining depth. Currently, ADCensus, SAD, and SSD are mainly used to calculate the cost. Although these methods are easy to implement, their accuracy...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problem of high resource consumption caused by the use of neural network calculation matching costs in the above-mentioned prior art, the present invention provides a binary neural network stereo vision matching method based on FPGA. The present invention reduces The resource consumption of neural networks, which can eventually be ported to embedded systems

Images