Skip to Main Content
In vision-based systems, cast shadow detection is one of the key problems that must be alleviated in order to achieve robust segmentation of moving objects. Most methods for shadow detection require significant human input and they work in static settings. This paper proposes a novel approach for adaptive shadow detection by using semi-supervised learning which is a technique that has been widely utilized in various pattern recognition applications and exploits the use of labeled and unlabeled data to improve classification. The approach can be summarized as follows: First, we extract color, texture, and gradient features that are useful for differentiating between moving objects and their shadows. Second, we use a semi-supervised learning approach for adaptive shadow detection. Experimental results obtained with benchmark video sequences demonstrate that the proposed technique improves both the shadow detection rate (classify shadow points as shadows) and the shadow discrimination rate (not to classify object points as shadows) under different scene conditions.