The Impact of Video Transcoding Parameters on Event Detection for Surveillance Systems
Authors: Emmanouil Kafetzakis, Christos Xilouris, Michail Alexandros Kourtis, Marcos Nieto, Iveel Jargalsaikhan, Suzanne Little
Date: 09.12.2013
Abstract
The process of transcoding videos apart from being intensive, can also be a rather complex procedure. The complexity refers to the choice of appropriate parameters at the transcoding engine, towards decreasing video sizes, transcoding times and network bandwidth without degrading video quality beyond some threshold that event detectors lose their accuracy. The paper explains the need for transcoding, and then studies different video quality metrics. Commonly used algorithms for motion and person detection are briefly described, with emphasis in investigating the optimum transcoding configuration parameters. The analysis of the experimental results reveals that the existing video quality metrics are not suitable for automated systems, and that the detection of persons is affected by the reduction of bit rate (more blockiness effect) and resolution (less information), while motion detection is more sensitive to frame rate.
BIB_text
author = {Emmanouil Kafetzakis, Christos Xilouris, Michail Alexandros Kourtis, Marcos Nieto, Iveel Jargalsaikhan, Suzanne Little},
title = {The Impact of Video Transcoding Parameters on Event Detection for Surveillance Systems},
keywds = {
CCTV, transcoding, event detection, video quality
}
abstract = {
The process of transcoding videos apart from being intensive, can also be a rather complex procedure. The complexity refers to the choice of appropriate parameters at the transcoding engine, towards decreasing video sizes, transcoding times and network bandwidth without degrading video quality beyond some threshold that event detectors lose their accuracy. The paper explains the need for transcoding, and then studies different video quality metrics. Commonly used algorithms for motion and person detection are briefly described, with emphasis in investigating the optimum transcoding configuration parameters. The analysis of the experimental results reveals that the existing video quality metrics are not suitable for automated systems, and that the detection of persons is affected by the reduction of bit rate (more blockiness effect) and resolution (less information), while motion detection is more sensitive to frame rate.
}
isi = {1},
date = {2013-12-09},
year = {2013},
}
