Image correction method of binocular camera and storage medium

Abstract

The invention discloses an image correction method of a binocular camera and a storage medium. The method comprises the steps of acquiring a preset coordinate mapping table, corresponding to a corrected image and an original image, of a binocular camera camera, wherein the preset coordinate mapping table comprises an X-axis coordinate mapping table and a Y-axis coordinate mapping table, and the corresponding relation between pixel points of the corrected image and sub-pixel points of the original image is recorded in the coordinate mapping table; carrying out up-sampling interpolation calculation on the preset coordinate mapping table according to a preset multiplying power to obtain a coordinate mapping table of an original size of the original image; and according to the coordinate mapping table of the original size, searching the coordinate position of the current pixel point of the corrected image in the original image, and carrying out bilinear interpolation operation on the pixelvalues of four integer pixel points surrounding the coordinate position in the original image to obtain the pixel value of the current pixel point.

Description

technical field [0001] The invention relates to the field of image correction, in particular to an image correction method and a storage medium for a binocular camera. Background technique [0002] Binocular images are two images obtained by shooting the same scene with two parallel cameras. The image formed by the same object point in space in the image plane captured by two cameras is called a matching point pair, and the spatial position information of the object point can be extracted according to the parallax of the matching point pair. Ideally, the images formed by the same object point in the binocular camera are located in the same row, so when performing stereo matching, you only need to perform a matching search along the same row, which not only reduces the complexity of the search, but also reduces errors. probability of matching. [0003] However, in the actual process, due to the existence of lens distortion and the difficulty of strictly paralleling the two ...

AI Technical Summary

Problems solved by technology

[0008] The present invention provides an image correction method and storage medium for a binocular camera, which are used to solve the following problems in the prior art: the existing binocular geometric correction algorithm that performs lens distortion correction first and then epipolar line geometric correction is performed after two Secondary correction calculation, high computational complexity, does not meet the needs of real-time calculation

Images