A Camera Calibration Strategy in the Video-based Traffic Information Detection

Abstract

In this paper an improved camera calibration algorithm is applied to the video-based traffic information detection. The geometric camera model is set up based on the pin-hole model and Direct Linear Transformation (DLT). Adopting the coplanar condition, we estimate parameters of the model and realize the transform from image coordinates to world coordinates in the end. The problem of control points is discussed. In our experiment, the algorithm has the advantage of high-accuracy and its parameters can be easily estimated. It is proved that the algorithm could meet the requirement of calibration accuracy in the application of the video-based traffic information detection.