| 摘要 |
A method of merging a plurality of disparity maps. The method comprises calculating a plurality of disparity maps each from images captured by another of a plurality of pairs of image sensors having stereoscopic fields of view (SFOVs) with at least one overlapping portion, the SFOVs covering a scene with a plurality of objects, identifying at least one of the plurality of objects in the at least one overlapping portion, the at least one object being mapped in each the disparity map, calculating accuracy of disparity values depicting the object in each the disparity map, merging depth data from the plurality of disparity maps according to the accuracy so as to provide a combined depth map wherein disparity values of the object are calculated according to one of the plurality of disparity maps, and outputting the depth data. |
