Height measurement method, terminal equipment and computer storage medium

Abstract

The invention discloses a height measurement method, terminal equipment and a computer storage medium, and the method comprises the steps: obtaining a binocular image which comprises a left eye image and a right eye image; inputting the binocular image into a preset network model, obtaining a disparity map and an instance segmentation map, wherein the disparity map is the pixel-level difference of the same point positions in the left eye image and the right eye image; determining a ground area and a target area by using the disparity map and the instance segmentation map, and acquiring a depth map by using the disparity map and camera parameters; obtaining a three-dimensional coordinate of a target point in the target area through the depth map, and obtaining a plane coordinate of the ground area; and obtaining the height of the target based on the three-dimensional coordinate of the target point and the plane coordinate. According to the method, the plane coordinates of the ground area are fitted, and the ground point does not need to be selected manually, so that the height measurement method is intelligent and rapid, and the height measurement efficiency is improved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular to a height measurement method, a terminal device and a computer storage medium. Background technique [0002] Binocular stereo vision is widely used in various computer vision technology fields. It is an important form of computer vision. It is based on the principle of parallax and uses imaging equipment to obtain two images of the measured target from different positions. It is a method to obtain the three-dimensional geometric information of the target by calculating the position deviation between the corresponding points of the image. The measurement method based on binocular vision has the advantages of high efficiency, appropriate precision, simple system structure and low cost. Compared with monocular vision, the binocular vision method is more stable in obtaining the geometric information of the scene. [0003] When perceiving target features, height...

AI Technical Summary

Problems solved by technology

[0004] However, due to the large number of manually selected points, the artificial error generated during the height measurement process is large, and the selection process is cumbersome, resulting in low efficiency of height measurement and a certain impact on accuracy.

Images