Multistage threshold image segmentation method

Abstract

The invention discloses a multi-level threshold image segmentation method, which comprises the following steps of: firstly, initializing a grey wolf group; calculating the fitness of each grey wolf individual, and determining the positions of an alpha wolf, a beta wolf and a delta wolf; and updating the positions of the alpha wolf, the beta wolf and the delta wolf according to the distances between the remaining grey wolf individuals and the alpha wolf, the beta wolf and the delta wolf, updating the positions of the remaining grey wolf individuals through a particle swarm algorithm, and finally obtaining an optimal threshold through multiple iterations to perform image segmentation.

Description

technical field [0001] The invention relates to the field of aerospace technology, in particular to a multi-level threshold image segmentation method. Background technique [0002] In deep space exploration missions, probes need to land in complex terrain areas, so on-orbit fast obstacle detection technology is very important. Obstacle detection based on optical images is one of the important navigation algorithms in the current planetary landing process. The obstacle detection algorithm refers to the algorithm based on visual images and ground surface detection, which can realize online rapid detection of obstacles such as rocks and ravines, and lay the foundation for landing obstacle avoidance and path planning. [0003] Early studies on planetary landing obstacle detection were all oriented towards large planets and larger asteroids. The distinctive craters were used as surface features to guide landing guidance and control, while the identification of craters was manuall...

AI Technical Summary

Problems solved by technology

These algorithms can detect rocks, but because the surface texture is uneven, their color and albedo are different, and for non-cratered surfaces, it is difficult to find their actual boundary outlines

In addition, because the result of threshold segmentation is very dependent on the selection of the threshold, the traditional method mainly searches for the best threshold through exhaustion, which takes a long time and requires a lot of calculation, so it cannot handle images with complex content.

Images