Paper presents tracking a single moving region in the compressed domain using a spatiotemporal Markov random field (ST-MRF) model. An ST-MRF model naturally integrates the spatial and temporal aspects of the region’s motion. Built upon such a model, the proposed method uses only the motion vectors (MVs) and block coding modes (BCMs) from the compressed bitstream to perform tracking. First, the MVs are pre-processed through intra-coded block motion approximation and global motion compensation (GMC). It is for region tracking in H.264/AVC-compressed video, which could be used to enhance important region analysis and, more generally, scene interpretation, in the compressed domain. It is well known that motion has a strong impact on saliency in dynamic scenes.
CITATION STYLE
Ashwini, & Kusuma, T. (2020). Analysis of global motion compensation and polar vector median for object tracking using ST-MRF in video surveillance. In Advances in Intelligent Systems and Computing (Vol. 1085, pp. 453–464). Springer. https://doi.org/10.1007/978-981-15-1366-4_36
Mendeley helps you to discover research relevant for your work.