Abstract

Detecting shadows from images can significantly improve the performance of several vision tasks such as ob ject detection and track- ing. Recent approaches have mainly used illumination invariants which can fail severely when the qualities of the images are not very good, as is the case for most consumer-grade photographs, like those on Google or Flickr. We present a practical algorithm to automatically detect shadows cast by ob jects onto the ground, from a single consumer photograph. Our key hypothesis is that the types of materials constituting the ground in outdoor scenes is relatively limited, most commonly including asphalt, brick, stone, mud, grass, concrete, etc. As a result, the appearances of shadows on the ground are not as widely varying as general shadows and thus, can be learned from a labelled set of images. Our detector consists of a three-tier process including (a) training a decision tree clas- sifier on a set of shadow sensitive features computed around each image edge, (b) a CRF-based optimization to group detected shadow edges to generate coherent shadow contours, and (c) incorporating any existing classifier that is specifically trained to detect grounds in images. Our re- sults demonstrate good detection accuracy (85%) on several challenging images. Since most ob jects of interest to vision applications (like pedes- trians, vehicles, signs) are attached to the ground, we believe that our detector can find wide applicability.