Shadow Model Construction with Features Robust to Illumination Changes

Computer vision methods need to deal with shadows explicitly because shadows often have a negative effect on the results computed. A new shadow detection method is proposed. The new method is based on a shadow model. The model is constructed by features robust to illumination changes. The method uses four features: (1) the difference of the UV components of the YUV color space between the background image and the observed image; (2) Normalized Vector Distance; (3) Peripheral Increment Sign Correlation image; and edge information. Each of these features removes shadow effects, in part. The overall method can construct an effective shadow model by using all of the features. The result is improved further by region based analysis and by online update of the shadow model. The proposed method extracts shadows accurately. Results are demonstrated by experiments using the real videos of outdoor scenes.