Method and device for generating depth map

Abstract

The invention discloses a method and a device for generating a depth map, which belongs to the technical field of computer vision. The method comprises the following steps: performing gray-scale transformation by using a left view and a right view of an input image pair as a reference image and a target image respectively; computing upper, lower, left and right gradient matrixes of the reference image after the gray-scale transformation; computing a cost function matrix according to parallax, and processing borders; computing an original information storage matrix, and initializing upper, lower, left and right information storage matrixes; performing iterative calculation in a GPU memory by using a CUDA belief propagation algorithm to acquire upper, lower, left and right information storage matrixes after iteration, and computing a belief matrix according to the result of the iteration; and computing the depth map according to the belief matrix. The device comprises a gray-scale transformation module, a gradient computation module, a cost function matrix computation module, an original information storage matrix computation module, an iteration module, a belief matrix computation module and a depth map computation module. The method and the device improve computing efficiency of the depth map and realize high-quality and fast generation of the depth map.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a method and device for generating a depth map. Background technique [0002] Three-dimensional images and displays are an important form of expression for future information systems. Three-dimensional images and displays are clearly layered and colorful, and have a strong visual impact, allowing viewers to stay longer and leave a deep impression; The images and displays are real and lifelike, the characters are ready to appear, there is an immersive feeling, and there is a high artistic appreciation value. Just because three-dimensional images and videos have the characteristics that these plane images and videos do not have, they have broad application prospects in fields such as computer display, television, video, robotics, measurement, inspection, medical treatment, advertising media, and electronic games. [0003] The reason why the human eye sees the world...

AI Technical Summary

Problems solved by technology

The method based on local correlation has many problems such as serious noise, poor effect on the weak texture area of ​​the image and poor robustness, and it is difficult to obtain high-quality stereoscopic reconstruction effect; the method based on dynamic programming is prone to stripe effect at the edge of the object

And for real-time applications, the amount of calculation is still too large

[0007] It can be seen that the existing depth map generation technology still has the following problems: first, the algorithm that can generate high-quality depth maps is very slow; second, the depth map obtained by the algorithm that can quickly generate depth maps is of poor quality

Images