APSIPA Transactions on Signal and Information Processing > Vol 5 > Issue 1

Moving object detection in the H.264/AVC compressed domain

Marcus Laumer, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Germany, marcus.laumer@fau.de , Peter Amon, Siemens Corporate Technology, Germany, Andreas Hutter, Siemens Corporate Technology, Germany, André Kaup, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Germany
 
Suggested Citation
Marcus Laumer, Peter Amon, Andreas Hutter and André Kaup (2016), "Moving object detection in the H.264/AVC compressed domain", APSIPA Transactions on Signal and Information Processing: Vol. 5: No. 1, e18. http://dx.doi.org/10.1017/ATSIP.2016.18

Publication Date: 21 Nov 2016
© 2016 Marcus Laumer, Peter Amon, Andreas Hutter and André Kaup
 
Subjects
 
Keywords
Compressed domainH.264/AVCSegmentationSyntax elementsObject detection
 

Share

Open Access

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

Downloaded: 5561 times

In this article:
I. INTRODUCTION 
II. RELATED WORK 
III. STRUCTURE AND SYNTAX OF H.264/AVC 
IV. MOVING OBJECT DETECTION 
V. EXPERIMENTAL RESULTS 
VI. CONCLUSIONS 

Abstract

This paper presents a moving object detection algorithm for H.264/AVC video streams that is applied in the compressed domain. The method is able to extract and analyze several syntax elements from any H.264/AVC-compliant bit stream. The number of analyzed syntax elements depends on the mode in which the method operates. The algorithm is able to perform either a spatiotemporal analysis in a single step or a two-step analysis that starts with a spatial analysis of each frame, followed by a temporal analysis of several subsequent frames. Thereby, in each mode either only (sub-)macroblock types and partition modes or, additionally, quantization parameters are analyzed. The evaluation of these syntax elements enables the algorithm to determine a “weight” for each 4×4 block of pixels that indicates the level of motion within this block. A final segmentation after creating these weights segments each frame to foreground and background and hence indicates the positions and sizes of all moving objects. Our experiments show that the algorithm is able to efficiently detect moving objects in the compressed domain and that it is configurable to process a large number of parallel bit streams in real time.

DOI:10.1017/ATSIP.2016.18