Image depth calculation method, device, storage medium and electronic equipment

Abstract

Embodiments of the present invention provide an image depth calculation method, device, storage medium and electronic equipment. The image depth calculation method includes: determining corresponding matching cost data based on at least two interrelated view images taken; Selected ones of the images generate corresponding depth maps. Therefore, a relatively high-accuracy depth map is obtained by designing the relatively miniaturized neural network model. On a terminal device with low computing power (such as a mobile phone), after obtaining at least two view images of the same scene captured by the camera device, the corresponding depth map can be generated immediately and quickly, so that the image can be processed according to the generated depth map. Perform various treatments.

Description

technical field [0001] Embodiments of the present invention relate to computer vision technology, and in particular to an image depth calculation method, device, computer-readable storage medium, and electronic equipment. Background technique [0002] Binocular stereo vision is an important form of machine vision, which uses imaging equipment to imitate two eyes to capture two images of the object under test to obtain three-dimensional geometric information of the object. Stereo vision has been more and more widely used in the fields of robot vision, medical imaging and industrial inspection. [0003] In the existing binocular stereo vision implementation scheme, the depth of field calculation has high computational complexity, and it is difficult to realize real-time depth of field calculation. Although the real-time calculation of the depth of field can be realized on the computer under the premise of losing a certain accuracy of the depth of field calculation, the same c...

AI Technical Summary

Problems solved by technology

[0003] In the existing binocular stereo vision implementation scheme, the depth of field calculation has high computational complexity, and it is difficult to realize real-time depth of field calculation

Although the real-time calculation of the depth of field can be realized on the computer under the premise of losing a certain accuracy of the depth of field calculation, the same calculation method of the depth of field is still too complex due to the high computational complexity, so the terminal equipment with low computing power (such as mobile phones) Real-time depth of field calculation cannot be realized on

Images