| abstract |
PROBLEM TO BE SOLVED: To provide an improved image composition in a multi-view automobile and a robot engineering system. In various embodiments, two or more cameras in an automotive surround view system generate two or more input images that will be stitched or combined into a single stitch image. In one embodiment, in order to improve the quality of the stitch image, the feedback module calculates two or more scores representing the error between the stitch image and one or more input images. If the calculated score indicates a structural error in the stitched image, the feedback module calculates and applies one or more geometric variants to apply to one or more input images. If the calculated score indicates a color error in the stitched image, the feedback module calculates and applies one or more photometric variants to apply to one or more input images. [Selection diagram] Fig. 1 |