MVS A multi-view video synopsis framework.pdfVIP

Signal Processing: Image Communication 42 (2016) 31–44 Contents lists available at ScienceDirect Signal Processing: Image Communication journal homepage: /locate/image MVS: A multi-view video synopsis framework Ansuman Mahapatra a, Pankaj K. Sa a,n, Banshidhar Majhi a, Sudarshan Padhy b a Department of Computer Science and Engineering, National Institute of Technology Rourkela, India b Institute of Mathematics and Application, Bhubaneswar, Odisha article info Article history: Received 26 June 2015 Received in revised form 6 January 2016 Accepted 6 January 2016 Available online 14 January 2016 Keywords: Video synopsis Multi-view video Multi-camera network Video summarization abstract In this paper, we present a framework for generating a synopsis of multi-view videos that are acquired from a surveillance site, indoor or outdoor, using multiple cameras. The synopsis generation is modeled as a scheduling problem that we solve using three separate approaches: table-driven approach, contradictory binary graph coloring (CBGC) approach, and simulated annealing (SA) based approach. An action recognition module is included in the framework to recognize important actions performed by various humans present in the videos. Inclusion of such important actions in the synopsis has helped to reduce its length signi?cantly. The synopsis length is further reduced through a postprocessing step that computes the visibility score for each object track using a fuzzy inference system. Among the three proposed schemes, maximum reduction in synopsis length is obtained through the CBGC approach. The stochastic approach using SA, on the other hand, achieves a better trade-off among the multiple optimization criteria. Experimental evaluations on standard datasets demonstrate the ef?cacy of the proposed framework over its counterparts concerning the reduction in synopsis length and retention of important actions. 2016 Elsevier B.V. All rights reserved. 1. Introduction Automated analysis of sur