Shadow Detection by Integrating Multiple Features

Abstract

Cast shadows of moving foreground objects in a scene often result in problems for many applications such as surveillance, object tracking/recognition, video content analysis and intelligent transportation systems. In this paper we presented an algorithm exploiting information of color, shading, texture, neighborhoods and temporal consistency to detect shadows in a scene efficiently and reliably. The experimental results showed that the proposed method can detect umbra as well as penumbra in different kinds of scenarios under various illumination conditions.