关键词: 阴影检测, 混合高斯分布模型, Gabor小波, 阴影颜色模型, 连通区域标记

Abstract:

In order to effectively detect the shadow areas in image sequences and to eliminate the serious effect of shadows on the object tracking and recognition, this paper proposes a new shadow detection algorithm based on the Gabor wavelet and the color model. In this algorithm, first, the Gaussian mixture distribution model and shadow color model of the background are established. Next, the foreground figures are extracted by means of the difference method. Then, the potential shadow pixels are found out by means of Gabor wavelet texture analysis, which are further analyzed with the shadow color model to search real shadow pixels. Finally, the real shadow areas are distinguished after some subsequent processing steps. Experimental results demonstrate that the proposed algorithm is of high performance of shadow detection.

Key words: shadow detection, Gaussian mixture distribution model, Gabor wavelet, shadow color model, labeling connected component