| abstract |
In various examples, two or more cameras in an automotive surround view system produce two or more input images to be merged or combined into a single composite image. In one embodiment, to improve the quality of a stitched image, a feedback module calculates two or more metrics representing errors between the stitched image and one or more input images. If a calculated characteristic indicates structural errors in the stitched image, the feedback module calculates and applies one or more geometric transformations to be applied to the one or more input images. If a calculated metric indicates chromatic aberrations in the stitched image, the feedback module calculates and applies one or more photometric transformations to apply to one or more input images. |