Computer vision systems and methods for supplying missing point data in point clouds derived from stereoscopic image pairs

A computer vision system for supplying missing point data in point clouds derived from stereoscopic image pairs, comprising:

• a memory storing a plurality of stereoscopic image pairs;
• and
• a processor in communication with the memory, the processor programmed to perform the steps of:
• retrieving the at least one stereoscopic image pair from the memory based on a received geospatial region of interest;
• processing the at least one stereoscopic image pair to generate a disparity map from the at least one stereoscopic image pair, the disparity map generated at least in part by determining a similarity factor value between a first region near a first pixel of a first image of the at least one stereoscopic image pair and a second region near a second pixel of a second image of the at least one stereoscopic image pair;
• processing the disparity map to identify at least one null value in the disparity map;
• discarding all matching point pairs of the at least one stereoscopic image pair corresponding to the null value in the disparity map;
• supplying the disparity map with missing point data to replace the at least one null value of the disparity map when a maximum pixel matching confidence value of a best candidate pixel of an image of the at least one stereoscopic image pair is less than a pixel matching confidence threshold, the missing point data comprising:
• (1) a replacement disparity map value interpolated from normalized weights set for a plurality of pixels surrounding a pixel in an overlap region of the at least one stereoscopic image pair;
• and (2) an interpolated confidence value for the pixel in the overlap region;
• processing the disparity map to generate a depth map from the disparity map;
• processing the depth map to generate a point cloud from the depth map, the point cloud lacking any missing point data;
• and
• storing the point cloud.