Depth imaging method, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention relates to the technical field of machine vision, and discloses a depth imaging method, electronic equipment and a computer readable storage medium. The depth imaging method comprises the following steps: extracting features of an obtained object image and features of a preset reference image to obtain a feature image corresponding to the object image and a feature image corresponding to the reference image; calculating relevance between the object image and the reference image according to the feature image corresponding to the object image, the feature image corresponding to the reference image and a preset search range, wherein the search range comprises a search range in a row direction and a search range in a column direction; acquiring a column deviation between the object image and the reference image according to the relevance; and obtaining the depth map corresponding to the object map according to the column deviation between the object map and the reference map, thereby greatly improving the robustness of the depth imaging method to the row deviation, and improving the quality of the obtained depth map.

Description

technical field [0001] The embodiments of the present application relate to the technical field of machine vision, and in particular to a depth imaging method, electronic equipment, and a computer-readable storage medium. Background technique [0002] Depth perception technology based on machine vision has the characteristics of non-contact, fast speed, high precision, and wide application range. In the field, the popularization of depth perception technology has further expanded people's ability to perceive three-dimensional information, which has important application value in current scientific research and engineering technology. The image obtained based on depth perception imaging technology is called a depth map, and the pixel value of the depth map It can reflect the distance from the object in the scene to the camera. [0003] Most of the currently commonly used monocular structured light depth imaging methods based on convolutional networks simply output the column...

AI Technical Summary

Problems solved by technology

[0004] However, the monocular structured light camera will inevitably encounter bumps, impacts, scratches, etc. during use. These bumps, impacts, and scratches will cause changes in the internal structure of the monocular structured light camera. The influence of temperature changes, structural changes and temperature changes will cause a large line deviation between the object map and the reference map. The existence of line deviation will lead to a serious decline in the quality of the calculated depth map, which is not conducive to extended depth imaging. The application scenarios and scope of use of the method

Images