Binocular stereo vision multi-thread tracking and positioning method

Abstract

The invention discloses a binocular stereo vision multi-thread tracking and positioning method. A crossbeam is fixed on a tripod, a first camera and a second camera are respectively fixed at the two ends of the crossbeam, a lens of the first camera is provided with a first infrared optical filter, a lens of the second camera is provided with a second infrared optical filter, the first camera is connected to a first collection card via a first shooting connection line, the second camera is connected to a second collection card via a second shooting connection line, the first and second collection cards are inserted into a computer, the computer is connected with a display, and the first and second cameras are connected with an external trigger end respectively through a first general input / output line and a second general input / output line. Hardware and software systems are more compatible due to improvement, image data collection and processing and space reconstruction can be implemented in parallel, and the requirement of instantaneity is met.

Description

technical field [0001] The invention relates to a positioning method, in particular to a binocular stereo vision multi-thread tracking and positioning method. Background technique [0002] Binocular stereo vision measurement technology is one of the most widely used computer vision technologies. This technology is a stereo vision system designed to imitate the human eye system. Its main principle is: two cameras shoot the same target at different angles, and obtain two The image, that is, the stereo image pair, calculates the parallax of the target in the two cameras, and the spatial coordinates of the target can be obtained according to the reconstruction principle. Binocular stereo vision is the most basic and simplest method to obtain spatial coordinates. This technology is often used to track and locate targets. [0003] At present, the main problem of the binocular stereo vision tracking and positioning system is that it cannot take into account the measurement accurac...

AI Technical Summary

Problems solved by technology

[0003] At present, the main problem of the binocular stereo vision tracking and positioning system is that it cannot take into account the measurement accuracy and measurement speed

Higher measurement accuracy requires higher-precision processing of images, and ordinary PCs have limited computing power, which will inevitably lead to more time consumption

Replacing PCs with hardware processing platforms to achieve high-speed computing is an effective way to solve this problem, but this method increases the difficulty of development

In addition, the single-threaded working mode of the software architecture makes the PC only work serially, which greatly affects the real-time performance of the processing

Images