A monocular narrow-band multi-spectral stereo vision system and its application method

Abstract

The invention provides a monocular narrow-band multi-spectrum stereoscopic vision system and a using method thereof. The system includes an optical imaging lens with axial chromatic aberration, a narrow-band multi-spectral image sensor with channel number N≥4, and an image processing unit for processing and analyzing narrow-band multi-spectral images. The monocular narrow-band multi-spectral stereoscopic vision system provided by the present invention can obtain multiple narrow-band spectral images with natural calibration of the XY spatial positions of the image plane and different focus definition in one exposure. Depth Z information of any spatial position XY of the image can be obtained by using the matching algorithm such as defocus blur, which overcomes the shortcomings of binocular stereo vision, which has a large amount of calculation and the laser 3D vision system is expensive. Car navigation and obstacle avoidance have a wide range of applications.

Description

technical field [0001] The present invention relates to machine vision, and more specifically relates to the technical field of 3D sensor measurement. Background technique [0002] The natural world is three-dimensional, with plane (X, Y) position information and Z depth information. There are three main methods for people to recognize depth information: through the parallax information of the left and right eyes, through the motion information of the eyes relative to the movement of the object, and through the surface color information of the object. There are also those that detect depth through object surface texture information. In the past 20 to 30 years, the 3D vision methods studied by the academic circle mainly include obtaining depth information by analyzing the disparity information of the left and right eyes. Although 3D vision has been discussed for a long time in the literature, most machine vision systems today often rely on the analysis of two two-dimensiona...

AI Technical Summary

Problems solved by technology

[0003] The main technical problem to be solved by the present invention is to provide a monocular narrow-band multi-spectral stereo vision system and its application method, which can overcome the shortcomings of the existing machine vision methods, especially the dual-camera stereo vision method, which have a large amount of calculation and poor real-time performance. The 3D laser vision system is expensive. The detection result is a sparse cloud and cannot have realistic 2D image information.