Low complexity object detection and tracking with inter-layer graph mapping and intra-layer graph refinement in H.264/SVC bitstreams

Abstract

In this paper we present a novel method of detecting and tracking moving objects in H.264/SVC bitstreams for video surveillance applications. Efficient detection and reliable tracking of real moving objects are first performed in the spatial base layer of H.264/SVC based on a spatio-temporal graph which is constructed from the block partitions with non-zero motion vectors and/or non-zero residue information. The spatio-temporal graph is utilized in reliably maintaining the real moving objects of being detected and tracked by removing false detected objects via graph pruning and graph projection. Graph matching is then performed to precisely identify the real moving objects over time even under occlusion. For low-complex but accurate detection and reliable tracking of moving objects in spatial enhancement layer of H.264/SVC, inter-layer graph mapping and intra-layer graph refinement are used without performing graph pruning, graph projection and graph matching which are mostly performed in the spatial base layer. For this, the identified block groups of the real moving objects in the spatial base layer are then mapped to the spatial enhancement layer to provide accurate and efficient object detection and tracking in the bitstreams of higher spatial resolution. Experimental results show the proposed method can reliably detect small objects, object occlusions and object separation. It also produces efficient processing time down to 27% compared to fully performing graph processing in both spatial base and enhancement layers of H.264/SVC test bitstreams. (c) 2013 Elsevier B.V. All rights reserved.