Monocular fast focusing method and system

Abstract

The invention relates to the field of camera focusing, and particularly relates to a monocular fast focusing method. The method comprises the following steps: acquiring first image information of a current location and second image information that is acquired by at least rotating a preset angle for once through a camera; acquiring matching areas of the first image information and the second image information, and searching for stable matching points of the matching areas through consistency judgement; acquiring the pixel difference of the stable matching points in the first image information and the second image information; and searching for the climbing direction and climbing angle of the pixel difference according to a climbing algorithm to obtain an optimal focusing location of the camera. According to the monocular fast focusing method designed by the invention, the first image information of the current location and the second image information that is acquired by at least rotating the preset angle for once is acquired through the camera, the information is subjected to related processing and calculation, and then the optimal focusing location of the camera can be acquired, fast focusing can be achieved, the focusing efficiency and accuracy can be improved, and the user experience can be enhanced.

Description

technical field [0001] The invention relates to the field of camera focusing, in particular to a monocular fast focusing method and system. Background technique [0002] In terms of ranging principle, monocular cameras and binocular cameras are completely different. The monocular camera needs to identify the target, that is to say, to identify whether the obstacle is a car, a person or something else before measuring the distance. On this basis, distance measurement is performed, while the binocular camera is more like the eyes of human beings, and the distance is mainly determined by the parallax calculation of the two images. In other words, the binocular camera does not need to know what the obstacle is, as long as it can measure the distance through calculation. [0003] Binocular vision is widely used in robot navigation, precision industrial measurement, object recognition, virtual reality, scene reconstruction, and survey fields. Binocular vision is a method of sim...

AI Technical Summary

Problems solved by technology

[0004] For the above description, the cost of the monocular camera is lower than that of the binocular camera, and the control is more convenient; while the distance measurement and focusing of the binocular camera are faster, but relatively speaking, the cost of the binocular camera is larger, and it is not easy to integrate small design

Images