A novel camera calibration technique for traffic surveillance

Abstract

An accurate and effective visual traffic surveillance system requires a reliable camera calibration technique. Although numerous camera calibration methods have been developed, they all suffer from some strict limitations that make them inappropriate for visual traffic surveillance. Some methods that are closely related to our research are briefly described and appraised. In this paper, a novel camera calibration that determines the camera parameters is proposed. These camera parameters govern the mapping relationship between the image and world coordinates. Based on the geometric properties of the calibration pattern, a set of equations that computes the camera parameters from the image coordinates of the image pattern has been derived. Computer simulations demonstrate the advantages of the proposed method. The results show that the proposed method outperforms the others in terms of practicability, accuracy, stability and simplicity.