Lane line identification method and device fusing artificial fish and particle swarm optimization

Abstract

The invention provides a lane line identification method and device fusing artificial fish and a particle swarm algorithm, and electronic equipment, and belongs to the technical field of road identification. The method comprises the steps that an Otsu algorithm is adopted to fuse artificial fish and a particle swarm algorithm, each pixel value of a road image corresponds to a particle position, each particle corresponds to the artificial fish for foraging optimization, and according to the difference value between the inter-class variance value of the next particle position and the inter-class variance value of the current particle position, the current particle position is determined according to the difference value between the inter-class variance value of the next particle position and the inter-class variance value of the current particle position. And adjusting the visual field range of the artificial fish, searching an optimal segmentation threshold value based on the adjusted visual field range of the artificial fish, and segmenting lane lines in the road image according to the optimal segmentation threshold value by adopting an Otsu algorithm. According to the method, the artificial fish and the particle swarm algorithm are fused, all pixel values do not need to be traversed, a large amount of operand is saved, the operation time is shortened, and meanwhile the defect that a traditional particle swarm algorithm is caught in a local optimal solution in premature convergence is overcome.

Images