Shadow Removal from Videos Using Intensity Based K- Mean Clustering Algorithm

This paper introduces a hybrid approach that is based on color information that utilizes background subtraction technique, a mask and K-Mean clustering algorithm. This hybrid approach efficiently removes artifacts caused by lightening changes such as highlight, reflection, and shadows of moving objects from segmentation. We first create a mask by assigning values to R, G and B channels utilizing the shadow properties to this RGB color individually, and then we apply a K-Mean clustering algorithm to this mask for efficient removal. Simulation results from several video sequences with different scene conditions clearly reveal the effectiveness and robustness of the proposed algorithm.