Vehicle detection based on underneath vehicle shadow using edge features

This paper proposes a computer vision vehicle detection algorithm. The main focus of this proposed algorithm, in which the vehicle is detected based on dynamic traffic scenes. The scene can be recorded using on-board camera that fixed in position to monitor the front traffic. The method that proposed in this vehicle detection algorithm is based on underneath vehicle shadows. The shadows underneath vehicle have a higher intensity compared to the background and road area which advantageous as the main feature for detection. To achieve low computational complexity, the edges feature is detected using a horizontal Sobel operator, which is enhanced by using Scharr operator. Together with blob analysis to detect the wanted features and bounding box is used to label the vehicle detected in the final detection. The algorithm test result shows that the method is effective in the vehicle detection and display a highly accurate result.