Method for obtaining depth information by structured light camera, electronic device and storage medium

Abstract

The embodiment of the present invention relates to the field of image processing, and discloses a method for obtaining depth information by a structured light camera, an electronic device, and a storage medium. The internal and external parameters of the light camera; the calculated depth value is obtained based on the internal and external parameters, and according to the calculated depth value, the calibrated focal length, and the measured actual depth value, the calibrated real focal length is obtained by using an equivalent conversion; based on the equivalent of the projector The deviation between the optical center and the optical center of the lens is used to calibrate the position of the projector in the structured light camera to obtain the calibrated position of the projector; the depth value is calculated based on the real focal length and the calibrated position of the projector. In this solution, the real focal length of the structured light camera is obtained through calibration, and the deviation between the equivalent optical center of the projector and the optical center of the lens is considered, and a depth calculation method based on the linear propagation of the optical path is obtained to improve the accuracy of depth calculation.

Description

Method, electronic device and storage medium for acquiring depth information by structured light camera technical field The present invention relates to the field of image processing, in particular to a method for obtaining depth information by a structured light camera, an electronic equipment and storage media. Background technique [0002] With the development of 3D vision technology, people's application of depth value is more and more in-depth. Structured light cameras can pass Project a specific speckle and receive the speckle information with a single infrared lens for depth calculation to obtain the third-dimensional information of the object. current Most of the depth calculation models of structured light cameras use the principle of triangular similarity to solve the depth value, but this model is based on a It can only be established under ideal conditions. For applications with certain absolute accuracy requirements, this calculation method is no longer ...

AI Technical Summary

Problems solved by technology

The current depth calculation model of structured light cameras mostly uses the principle of triangular similarity to calculate the depth value, but this model can only be established under an ideal condition. For applications with certain absolute precision requirements, this calculation method is no longer accurate. Effective, so a depth calculation method that can tolerate the influence of assembly errors and other reasons under non-ideal conditions is needed for applications with high absolute precision

Images