Robust moving object detection based on ViBe with adaptive shadow detector

We propose the SAViBe+ algorithm, a new approach for moving object detection based on ViBe background subtraction algorithm with an adaptive shadow detector. Because ViBe cannot handle scenes containing gradual illumination variations, and eliminate shadows cast by moving objects, an adaptive shadow detector is designed to detect and eliminate the shadow of a moving object, adapting to variation of illumination in an automatic manner, which adopts texture and spatiotemporal information. This adaptive shadow detector is built with a texture model (TM) and a hue model (HM) to estimate the texture and intensity change of false foreground pixels respectively. A factor called Mean of Value (MofV) is proposed to work with HM to improve its efficiency. This algorithm is robust against false detection for different types of videos in indoor and outdoor scenes under various types of illumination taken by stationary cameras. Quantitative and qualitative performance evaluation carried out on the database of Change Detection Workshop(CDW’14) revealed that our scheme could operate in real-time, rapidly adapt to variation of illumination and environment online and outperform state-of-the-art methods. Key-Words: Object detection, Shadow removal, Adaptive shadow detector, Background subtraction, Motion detection, Surveillance