Stereo vision camera with double-lens single sensor

Abstract

The invention discloses a stereo vision camera with a double-lens single sensor. The camera comprises a shell and two lenses; and a light collection module, a core image processing module and two image data transmission communication modules are arranged in the shell. The light of a target enters the light collection module through the two lenses, and then is reflected to the same image sensor by a total-reflection prism in the light collection module. An FPGA chip on a core image processing board can divide the data collected by the sensor into two left and right parts, preprocess the image and selectively store the image data in a solid state disk or transmit the image data to a computer via a USB3.0 interface to be analyzed. The stereo vision camera disclosed by the invention focuses the light of the two lenses on the same image sensor by two light reflection units, so one image sensor is saved to reduce the cost of a double-eye stereo vision system and reduce the volume of the double-eye stereo vision system; and the collection synchronization problem is solved by hardware, so the measurement efficiency is improved.

Description

technical field [0001] The invention belongs to the field of machine vision, in particular to a dual-lens single-sensor stereo vision camera. Background technique [0002] According to the number of cameras used, machine vision technology can be divided into monocular vision technology, binocular vision technology and multi-eye vision technology. The theory of three-dimensional information extraction based on parallax proposed by the Massachusetts Institute of Technology in the 1980s laid the theoretical foundation for the development of binocular vision. It is based on the principle of parallax, and uses imaging equipment to obtain two images of the measured object from different positions, and obtains the three-dimensional geometric information of the object by calculating the position deviation between the corresponding points of the image. Compared with multi-eye stereo vision, binocular stereo vision technology captures information in a simpler way and is more convenie...

AI Technical Summary

Problems solved by technology

[0004] The traditional binocular stereo vision system generally uses two cameras to collect information. The binocular stereo vision system formed in this way is large in size and low in measurement efficiency. The most inconvenient thing is that the image acquisition needs to be manually synchronized, which is difficult

Images