Nonlinear robust velocity estimation of vehicles from a snowfall traffic scene

Discusses a robust velocity estimation method for moving vehicles in road traffic image sequences under snowy and misty weather conditions. In such environments, it is difficult to detect the velocity of vehicles because of discontinuities, occlusions, noise, and brightness variations. It should also be noted that falling snow results in indefinite shapes and motion, which occludes the region of interest. In order to estimate and recognize moving vehicles in images, a two-stage method has been proposed. Firstly, a non-linear smoothing is applied based on an anisotropic diffusion method. Secondly, a minimization of an objective function with movements and photometric variations is carried out. The fitting residual error in the function is reduced by a nonlinear robust function in discontinuity regions. Thus the velocity of moving vehicles can be estimated, stably and robustly, even in low contrast images. To verify this, a simple recognition experiment is performed to estimate the number of moving vehicles in images. The high recognition rate shows the validity and power of the proposed scheme.