METHOD AND SYSTEM FOR EXTRACTING PARKING SPACE IN UNDERGROUND PARKING LOT IN HIGH-PRECISION MAP MAKING

摘要

A method and a system for extracting a parking space in an underground parking lot in the process of making a high-precision map, the method comprising: acquiring three-dimensional laser point cloud data comprising a parking space, and projecting the three-dimensional laser point cloud data to form a two-dimensional bird's-eye view mode image (S1); determining a contrast estimation indicator of the two-dimensional bird's-eye view mode image, performing image pre-processing on the two-dimensional bird's-eye view mode image according to the contrast estimation indicator, and obtaining a binary image (S2); detecting straight line segments in the binary image, and determining a parking line rotation angle of the parking space according to a detection result (S3); rotating, using a center point of the binary image as a circle center, the binary image according to the parking line rotation angle so as to obtain a rotated image (S4); calculating the number of pixels in a parking line for each row and each column in the rotated image, and obtaining respective integral projections in a horizontal direction and a vertical direction (S5); performing a search according to the integral projections in the horizontal direction and the vertical direction so as to obtain coordinates of four corner points corresponding to the parking space (S6); and performing inverse transformation with respect to the point cloud data according to the coordinates of the four corner points to extract the parking space (S7).