Illumination Invariant and Occlusion Robust Vehicle Tracking By Spatio-Temporal MRF Model

For many years, vehicle tracking in traffic images has suffered from the problems of occlusions and sudden variations in illumination. In order to resolve these occlusion problems, we have been proposing the Spatio-Temporal Markov Random Field model(S-T MRF) for segmentation of spatio-temporal images. This S-T MRF optimizes the segmentation boundaries of occluded vehicles and their motion vectors simultaneously, by referring to textures and segment labeling correlations along the temporal axis, as well as the spatial axes. Consequently, S-T MRF has been proven to be successful for vehicle tracking even against severe occlusions found in low-angle traffic images with complicated motions, such at highway junctions. Furthermore in this paper, we defined a method to obtain the illumination invariant images by estimating MRF energy among neighbor pixel intensities. These illumination invariant images are very stable even when sudden variations in illumination are caused by such as clouds hiding sun shine in the original images. Thus, vehicle tracking was performed successfully even against sudden variations in illumination or shading effects. In addition, we succeeded in seamlessly integrating the method for MRF energy images into our S-T MRF model. In this paper, the idea of the integrated S-T MRF model and successful results of vehicle tracking against sudden variations in illumination as well as occlusions will be described in detail.