What Characterizes a Shadow Boundary under the Sun and Sky?

Despite decades of study, robust shadow detection remains difficult, especially within a single color image. We describe a new approach to detect shadow boundaries in images of outdoor scenes lit only by the sun and sky. The method first extracts visual features of candidate edges that are motivated by physical models of illumination and occluders. We feed these features into a Support Vector Machine (SVM) that was trained to discriminate between mostlikely shadow-edge candidates and less-likely ones. Finally, we connect edges to help reject non-shadow edge candidates, and to encourage closed, connected shadow boundaries. On benchmark shadow-edge data sets from Lalonde et al. and Zhu et al., our method showed substantial improvements when compared to other recent shadowdetection methods based on statistical learning.

• Type: Journal
• Year: 2011
• Where: ICCV
• Authors: Xiang Huang, Gang Hua, Jack Tumblin, Lance Williams
• Keywords: Computer Vision, ICCV 2011, Shadow Boundaries, Shadow Edge, Support Vector Machine