Edge detection method and device, electronic equipment, and computer-readable storage medium

An edge detection device of an object in an image, the device comprising:

• an obtaining module configured to process the image to obtain a line drawing of a grayscale contour in the image;
• a first merge module configured to merge a plurality of similar lines in the line drawing to obtain a plurality of initial merged lines, and a boundary matrix is determined according to the plurality of initial merged lines;
• a second merge module configured to obtain a plurality of target lines according to the plurality of initial merged lines, comprising:
• merging a plurality of similar initial merged lines in the plurality of initial merged lines to obtain at least one of the target lines, and using one or a plurality of unmerged initial merged lines also as one or a plurality of the target lines;
• a first determination module configured to determine a plurality of reference boundary lines from the plurality of target lines according to the boundary matrix;
• an identification module configured to process the image via a pre-trained boundary line region identification model to obtain a plurality of boundary line regions of the object in the image, wherein the boundary line region identification model is a model based on a neural network;
• a second determination module configured to determine, for each of the boundary line regions, a target boundary line corresponding to the boundary line region from the plurality of reference boundary lines;
• a third determination module configured to determine an edge of the object in the image according to the plurality of target boundary lines determined by the plurality of boundary line regions.