APSIPA Transactions on Signal and Information Processing > Vol 4 > Issue 1

Seam carving modeling for semantic video coding in security applications

Marc Décombas, Institut Mines-Télécom, France, marc.decombas@gmail.com , Younous Fellah, Institut Mines-Télécom, France, Fréderic Dufaux, Institut Mines-Télécom, France, Beatrice Pesquet-popescu, Institut Mines-Télécom, France, Francois Capman, Laboratory MultiMedia – Thales Communications & Security, France, Erwann Renan, Laboratory MultiMedia – Thales Communications & Security, France
 
Suggested Citation
Marc Décombas, Younous Fellah, Fréderic Dufaux, Beatrice Pesquet-popescu, Francois Capman and Erwann Renan (2015), "Seam carving modeling for semantic video coding in security applications", APSIPA Transactions on Signal and Information Processing: Vol. 4: No. 1, e6. http://dx.doi.org/10.1017/ATSIP.2015.4

Publication Date: 06 Aug 2015
© 2015 Marc Décombas, Younous Fellah, Fréderic Dufaux, Beatrice Pesquet-popescu, Francois Capman and Erwann Renan
 
Subjects
 
Keywords
Seam carvingVideo compressionSeam modelingSecurity application
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 484 times

In this article:
I. INTRODUCTION 
II. RELATED WORK 
III. PROPOSED SEAM CARVING APPROACH FOR SEMANTIC CODING 
IV. PERFORMANCE ASSESSMENT RESULTS 
V. CONCLUSION AND FUTURE WORK 

Abstract

In some security applications, it is important to transmit just enough information to take the right decisions. Traditional video codecs try to maximize the global quality, irrespective of the video content pertinence for certain tasks. To better maintain the semantics of the scene, some approaches allocate more bitrate to the salient information. In this paper, a semantic video compression scheme based on seam carving is proposed. The idea is to suppress non-salient parts of the video by seam carving. The reduced sequence is encoded with H.264/AVC while the seams are encoded with our approach. The main contributions of this paper are (1) an algorithm that segments the sequence into group of pictures, depending on the content, (2) a spatio-temporal seam clustering method, (3) an isolated seam discarding technique, improving the seam encoding, (4) a new seam modeling, avoiding geometric distortion and resulting in a better control of the seam shapes, and (5) a new encoder which reduces the overall bit-rate. A full reference object-oriented quality metric is used to assess the performance of the approach. Our approach outperforms traditional H.264/AVC intra encoding with a Bjontegaard's rate improvement between 7.02 and 21.77% while maintaining the quality of the salient objects.

DOI:10.1017/ATSIP.2015.4