Background initialisation by spatio-temporal motion estimation

Sriram Varadarajan, H. Wang, Bryan Scotney, O Nibouche

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Estimating the initial background of a scene is a key prerequisite for several applications in video analytics. In this paper, we present a simple approach that takes into account spatio-temporal motion intensities while estimating the true background. We tested the algorithm on real video sequences from the Scene Background Initialization (SBI) benchmark dataset, and the results show that the algorithm is competitive compared to the state of the art.
LanguageEnglish
Title of host publication14th IEEE International Conference on Advanced Video and Signal Based Surveillance
ISBN (Electronic)978-1-5386-2939-0
DOIs
Publication statusPublished - 23 Oct 2017
Event14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) - Lecce, Italy
Duration: 29 Aug 20171 Sep 2017
https://ieeexplore.ieee.org/xpl/conhome/8055736/proceeding

Conference

Conference14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
CityItaly
Period29/08/171/09/17
Internet address

Fingerprint

Motion estimation

Keywords

  • Video sequences
  • Measurement
  • Estimation
  • Image color analysis
  • Clustering algorithms
  • Neural networks
  • Adaptation models

Cite this

Varadarajan, S., Wang, H., Scotney, B., & Nibouche, O. (2017). Background initialisation by spatio-temporal motion estimation. In 14th IEEE International Conference on Advanced Video and Signal Based Surveillance https://doi.org/10.1109/AVSS.2017.8078485
Varadarajan, Sriram ; Wang, H. ; Scotney, Bryan ; Nibouche, O. / Background initialisation by spatio-temporal motion estimation. 14th IEEE International Conference on Advanced Video and Signal Based Surveillance. 2017.
@inproceedings{a1cd808e1bed4b8db55c15a0c70c411a,
title = "Background initialisation by spatio-temporal motion estimation",
abstract = "Estimating the initial background of a scene is a key prerequisite for several applications in video analytics. In this paper, we present a simple approach that takes into account spatio-temporal motion intensities while estimating the true background. We tested the algorithm on real video sequences from the Scene Background Initialization (SBI) benchmark dataset, and the results show that the algorithm is competitive compared to the state of the art.",
keywords = "Video sequences, Measurement, Estimation, Image color analysis, Clustering algorithms, Neural networks, Adaptation models",
author = "Sriram Varadarajan and H. Wang and Bryan Scotney and O Nibouche",
year = "2017",
month = "10",
day = "23",
doi = "10.1109/AVSS.2017.8078485",
language = "English",
isbn = "978-1-5386-2940-6",
booktitle = "14th IEEE International Conference on Advanced Video and Signal Based Surveillance",

}

Varadarajan, S, Wang, H, Scotney, B & Nibouche, O 2017, Background initialisation by spatio-temporal motion estimation. in 14th IEEE International Conference on Advanced Video and Signal Based Surveillance. 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Italy, 29/08/17. https://doi.org/10.1109/AVSS.2017.8078485

Background initialisation by spatio-temporal motion estimation. / Varadarajan, Sriram; Wang, H.; Scotney, Bryan; Nibouche, O.

14th IEEE International Conference on Advanced Video and Signal Based Surveillance. 2017.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Background initialisation by spatio-temporal motion estimation

AU - Varadarajan, Sriram

AU - Wang, H.

AU - Scotney, Bryan

AU - Nibouche, O

PY - 2017/10/23

Y1 - 2017/10/23

N2 - Estimating the initial background of a scene is a key prerequisite for several applications in video analytics. In this paper, we present a simple approach that takes into account spatio-temporal motion intensities while estimating the true background. We tested the algorithm on real video sequences from the Scene Background Initialization (SBI) benchmark dataset, and the results show that the algorithm is competitive compared to the state of the art.

AB - Estimating the initial background of a scene is a key prerequisite for several applications in video analytics. In this paper, we present a simple approach that takes into account spatio-temporal motion intensities while estimating the true background. We tested the algorithm on real video sequences from the Scene Background Initialization (SBI) benchmark dataset, and the results show that the algorithm is competitive compared to the state of the art.

KW - Video sequences

KW - Measurement

KW - Estimation

KW - Image color analysis

KW - Clustering algorithms

KW - Neural networks

KW - Adaptation models

U2 - 10.1109/AVSS.2017.8078485

DO - 10.1109/AVSS.2017.8078485

M3 - Conference contribution

SN - 978-1-5386-2940-6

BT - 14th IEEE International Conference on Advanced Video and Signal Based Surveillance

ER -

Varadarajan S, Wang H, Scotney B, Nibouche O. Background initialisation by spatio-temporal motion estimation. In 14th IEEE International Conference on Advanced Video and Signal Based Surveillance. 2017 https://doi.org/10.1109/AVSS.2017.8078485