Technical Reports (CIS)

Document Type

Technical Report

Date of this Version

November 1992


University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-92-82.


Many existing computer vision modules assume that shadows in an image have been accounted for prior to their application. In spite of this, relatively little work has been done on recognizing shadows or on recognizing a single surface material when directly lit and in shadow. This is in part because shadows cannot be infallible recognized until a scene's lighting and geometry are known. However, color is a strong cue to the presence of shadows. We present a general color image segmentation algorithm whose output is amenable to the recovery of shadows as determined by an analysis of the physics of shadow radiance. Then, we show how an observer that can cast its own shadows can infer enough information about a scene's illumination to refine the segmentation results to determine where the shadows in the scene are with reasonable confidence. Having an observer that can actively cast shadows frees us from restrictive assumptions about the scene illumination or the reliance on high level scene knowledge. We present results of our methods on images of complex indoor and outdoor scenes.



Date Posted: 25 July 2007