Illumination Invariant Segmentation of Spatio-Temporal Images by Spatio-Temporal Markov Random Field Model

For many years, object tracking in images has suffered from the problems of occlusions and illumination effects. In order to resolve occlusion problems, we have been proposing the Spatio-Temporal Markov Random Field model for segmentation of spatio-temporal images since 2000. This S-T MRF optimizes the segmentation boundaries of occluded objects and their motion vectors simultaneously, by referring to textures and segment labeling correlations along the temporal axis, as well as the spatial axes. Recently, we have extend our S-T MRF model to segment spatial MRF energy distributions of images along temporal axis, in order to resolve the problem of such illumination effects. Since, such spatio-temporal distribution of MRF energies would be so stable against illumination effects, the model is able to appropriately segment spatiotemporal images against variations in illumination and shading effects. Consequently, in the evaluation of the ST MRF by applying to vehicle tracking in traffic images, segmentation boundaries of vehicle regions were successfully determined by the S-T MRF model even in cases of serious occlusions and shading effects.