A color low-light multi-eye stereo vision camera and its data fusion method

Abstract

The invention discloses a color low-light multi-eye stereo vision camera and a data fusion method thereof, aiming at solving the problem that traditional stereo vision systems are easily affected by light spots and shadows in scenes with complex lighting, and are applied in unmanned driving and assisted driving In other fields, it is difficult to deal with the problems of difficult environments such as night, tunnel, and strong light. The color low-light multi-eye stereo vision camera of the present invention includes a bracket, an external trigger, a signal processor, and two groups of camera components; the two groups of camera components are Set on the bracket; each group of camera components includes a low-light camera and a color camera, and the optical axes of the four cameras are parallel to each other; the low-light camera and the color camera are respectively connected to an external trigger through a trigger line, and both They are respectively connected with the signal processor through data lines. The invention can solve the problems that the traditional stereo vision system cannot work at night and the distance measuring effect is not good in complex lighting environment.

Description

technical field [0001] The invention relates to a multi-eye stereo vision camera, in particular to a color low-light multi-eye stereo vision camera and a data fusion method thereof. Background technique [0002] Stereo vision has been widely used in industrial measurement, assisted driving, 3D modeling and other fields, but ordinary stereo vision systems usually consist of color or grayscale visible light cameras, which can only work in a well-lit environment. In addition, the stereo vision system is easily affected by light spots and shadows in scenes with complex lighting. When it is applied in areas such as unmanned driving and assisted driving, it is difficult to cope with difficult environments such as nighttime, tunnels, and strong light. Existing unmanned driving systems usually rely on lidar or supplementary light at night to deal with the above difficulties, but in some special applications, the system itself is required not to emit active light. Therefore, there i...

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problems in the prior art that the stereo vision system is easily affected by light spots, shadows, etc. in scenes with complex lighting, and it is difficult to deal with difficulties such as night, tunnel, and strong light when it is applied in the fields of unmanned driving and assisted driving. To solve the technical problems of the environment, a color low-light multi-eye stereo vision camera and its data fusion method are provided

Images