Among ITS applications, it is very important to acquire detailed statistics of traffic flows. We propose the spatio-temporal Markov random field model (S-T MRF) for segmentation of spatio-temporal images. This S-T MRF model optimizes the segmentation boundaries of occluded vehicles arid their motion vectors simultaneously by referring to textures and segment labeling correlations along the temporal axis as well as the spatial axis. Consequently, S-T MRF has been proven to be successful for vehicle tracking even against severe occlusions. In addition, in this paper, we define a method for obtaining illumination-invariant images by estimating MRF energy among neighbor pixel intensities. We then succeeded in seamlessly integrating the method for MRF energy images into our S-T MRF model. Thus, vehicle tracking was performed successfully by S-T MRF, even against sudden variations in illumination and against shading effects. Finally, in order to verify the effectiveness of our tracking algorithm based on the S-T MRF for practical uses, we developed an automated system for acquiring traffic statistics out of a flow of traffic images. This system has been operating continuously for ten months, and thus effectiveness of the tracking algorithm based on the S-T MRF model has been proven.
Occlusion robust and illumination invariant vehicle tracking for acquiring detailed statistics from traffic images
IEICE Transactions on Information and Systems ; E85-D , 11 ; 1753-1766
2002
14 Seiten, 26 Quellen
Article (Journal)
English
Scale and Occlusion Invariant Tracking-by-Detection
British Library Conference Proceedings | 2015
|Occlusion Robust Adaptive Template Tracking
British Library Conference Proceedings | 2001
|Occlusion robust adaptive template tracking
IEEE | 2001
|Illumination-invariant tracking via graph cuts
IEEE | 2005
|