Depth information extraction-based wall flatness detection method

Abstract

The invention discloses a depth information extraction-based wall flatness detection method and belongs to the distance measurement technique based on binocular vision. According to the technical scheme of the invention, the depth information from a camera to a wall surface is extracted by a binocular camera. Two sets of image pairs of a to-be-detected region, namely two depth information graphs, are respectively acquired from different angles, and then the corresponding depth information is obtained. During the acquisition process of the depth information graphs, the existing Hhartley correction method is improved, and the real-time performance and the accuracy of the correction process are improved. Meanwhile, one depth information graph is rotated and translated, so that the coordinates of the imaging spaces of the two depth information graphs are overlapped. In this way, a reinforced depth information graph is generated. The mode of the depth value of the reinforced depth information graph is adopted as the distance value of the to-be-detected region. Based on the size relationship between the distance value and a preset threshold, the flatness of the to-be-detected region is judged. The method can be applied to the intelligent plastering operation and has the advantages of simple, convenient and intelligent operation, high flatness detection timeliness and high accuracy.

Description

technical field [0001] The invention belongs to the field of binocular vision, and in particular relates to a technology for extracting depth information from walls. Background technique [0002] Binocular stereo vision (Binocular Stereo Vision) is an important form of machine vision. It is based on the principle of parallax and uses imaging equipment to obtain two images of the measured object from different positions. By calculating the position deviation between the corresponding points of the image, the A method for obtaining three-dimensional geometric information of an object. [0003] Obtaining the depth information of an object based on binocular stereo vision mainly includes the following steps: camera system calibration (obtaining the internal and external parameters of the camera), image acquisition, and image correction (based on the internal and external parameters of the camera, image correction is performed on the collected image pairs so that The correspondi...

AI Technical Summary

Problems solved by technology

Although the characteristics of SIFT feature points are strong, for binocular vision with high real-time requirements, it has the following shortcomings: (1) the calculation time of feature points is long; (2) the number of generated feature points is too large Many, when performing feature point matching, its calculation is complex, and error matching is prone to occur; (3) SIFT feature points are not intuitive feature points of the image, reflecting the poor intuitiveness of the image structure

At present, depth information is mainly obtained through active infrared light equipment, but this method is easily affected by external light, and at the same time, the equipment is expensive, the operation is complicated, and the algorithm complexity is high

Images