Moving Object and Shadow Detection Based on RGB Color Space and Edge Ratio
Xia Dong, Kedian Wang, Guohua Jia · 2009
This Paper presents a novel method for the detection of moving object and shadow based on RGB color space and edge ratio. In the first step, we analyzed the different characteristics of object and shadow in RGB color space. In the second step, the likely object and shadow regions were detected in preliminary, according to the chromaticity distortion and brightness distortion of the pixel between current image and background image. In the third step, we identified whether the object and shadow region were misclassified, according to the area and the edge ratio of each region. If the object and shadow region are misclassified, we will amend it in this step. We have applied this method to various image sequences of both indoor and outdoor scenes. The results demonstrate the effectiveness of the proposed method.