Patent attributes
A computer-implemented method includes: obtaining a sample picture and corresponding mark data, in which the mark data includes a first damage mark outline, and in which the first damage mark outline frames a damaged object in the sample picture; determining a segmentation type for a plurality of pixels in the sample picture based on the first damage mark outline, to generate segmentation mark data; inputting the sample picture to a weak segmentation damage detection model, in which the weak segmentation damage detection model includes an outline prediction branch and a segmentation prediction branch, in which the outline prediction branch outputs outline prediction data including a damage prediction outline, the damage prediction outline framing a predicted damaged object in the sample picture, and in which the segmentation prediction branch includes segmentation prediction data including a predicted segmentation type of each pixel of the plurality of pixels.
