Traffic Video Vehicle Shadow Elimination Algorithm Based on Principal Component Analysis

Abstract

In order to eliminate the shadows in vehicle detection, the accuracy of traffic monitoring is improved. In this text, the foreground object is extracted by background subtraction method. The orientation of the shadow region is determined by the PCA, which can reduce the complexity of algorithm. The shadow area is similar to background to weaken shadow. The foreground is extracted again by the same method after weaken shadow. The shadow area is transformed into the background and separated from the moving object. The experimental results show the average value of three groups video of comprehensive indexes is obtained that the algorithm is improved by 10.3% and 13.3% compared with the color and edge based shadow elimination algorithm. Thus, the shadow detection and elimination algorithm work well and the performance is reliable.