Multi-laser-ray rapid detection method

Abstract

The invention discloses a multi-laser-ray rapid detection method. The method comprises the following steps: taking a platform where a detected object is located as a reference surface, and erecting abinocular stereo camera module group above the reference surface, wherein the positions of the binocular stereo camera and a linear laser emitter are kept relatively fixed; performing three-dimensional correction; and obtaining left and right view parallax according to line laser matching point pairs, and calculating to obtain three-dimensional information; calibrating a pose relationship of theplurality of binocular stereo cameras, and converting the coordinate into the same coordinate system through an RT relationship; and fusing real-time pose data at the same moment according to a calibration result, calculating a three-dimensional position of each coordinate system of the corresponding calibration object, and solving the pose relationship between the binocular stereo cameras to obtain complete three-dimensional data. In the invention, depth images of the measured object are synchronously acquired through cooperative work and a time sequence, and the three-dimensional coordinatesand attitude information of the measured object are calculated by using a calibration and data fusion method so that rapid detection output can be realized, visual blind areas are reduced, and precision is higher.

Description

technical field [0001] The invention relates to the technical field of three-dimensional detection, in particular to a multi-laser line rapid detection method. Background technique [0002] Binocular vision is an important branch of computer. Binocular vision can imitate the process of human eyes and human stereoscopic vision perception. It is one of the core topics of computer vision research. In recent years, binocular vision technology has been widely used in obstacle detection, target object detection and other fields. [0003] Binocular stereo vision uses one or two CCD or CMOS digital cameras to shoot the same surface of the measured object from different angles, and obtain the three-dimensional coordinates of the point by calculating the parallax of the space point in the two images. This measurement method requires determining the corresponding position of the same point in space on two or more images taken from different angles. To scan an object, it is necessary ...

AI Technical Summary

Problems solved by technology

[0004] In the range of ordinary binocular vision shooting, because the line laser is emitted from the top or side, one inspection can only obtain the 3D information of the object surface in a certain viewing plane, and there will be certain blind spots because of the inability to shoot in all directions, especially for many High objects cannot meet the requirements of high-precision detection

Images