Image processing method and system

Abstract

The invention provides an image processing method and system, and the method comprises the steps: extracting the skyline of each stereo image pair in a site image of a target planet, and carrying out the region segmentation of each stereo image pair according to the skyline; determining a homonymy point matched with a target point of any one image in any one stereo image pair in the site image; constructing a correction equation according to an area to which the image point position of the homonymy point in the image forming the stereo image pair belongs and a preset correction model; determining a coefficient of a preset correction model, and determining a target correction model according to the coefficient and the preset correction model; and inputting the to-be-corrected site image into the target correction model, and correcting the to-be-corrected site image. According to the method, the skyline in the image is automatically extracted, region segmentation is automatically performed on the image, the requirement for correction of different regions of the target planetary site image is effectively met, and compared with overall correction without region division, relative radiation correction is performed on different regions in the image in a self-adaptive manner, and a more accurate correction effect is obtained.

Description

technical field [0001] The present invention relates to the technical field of image processing, and in particular, to an image processing method and system. Background technique [0002] In the planetary surface exploration mission, the use of rover to conduct close-range surface detection on the planetary surface is an important means to achieve efficient detection. During the driving process of the rover, the precise positioning and navigation of the rover itself and the perception of the environmental terrain are the keys to the smooth implementation of the detection task. In the existing tasks, the navigation and positioning of the rover itself mainly relies on the dead reckoning method integrated with inertial navigation and odometer. This method is a conventional positioning method in the inspection and detection of rover vehicles, but when driving in soft soil and rough ground areas, the wheels of the rover vehicle slip seriously, and the positioning error of the de...

AI Technical Summary

Problems solved by technology

[0006] The image processing method and system provided by the present invention are used to solve the above-mentioned problems existing in the prior art. By automatically extracting the skyline in the image, the image is automatically segmented into regions, which effectively meets the needs of correcting different regions of the image of the target planetary station. , compared with the overall correction regardless of the region, the relative radiation correction is adaptively performed for different regions in the image to obtain a more accurate correction effect

Images