Method and device for estimating cast shadow regions and/or highlight regions in images

摘要

The present invention relates to a method for estimating cast shadow regions and highlight regions in a scene, said scene being represented by a low dynamic range image, called LDR image, and a high dynamic range, called HDR image, said method comprising the steps of: —computing (S1) a detail map, called LDR detail map, of the LDR image, said LDR detail map associating a detail level to each pixel of the LDR image, —computing (S2) a detail map, called HDR detail map, of the HDR image, said HDR detail map associating a detail level to each pixel of the HDR image, and —detecting (S3) regions of the scene where the detail level in the HDR detail map is greater than the detail level in the LDR detail map, said detected regions corresponding to cast shadow regions or highlights region of the scene.