An improved mean shift tracker with fast failure recovery strategy after complete occlusion

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

The effectiveness of the conventional Mean Shift tracking algorithm diminishes for fast moving targets and complete occlusion. In this paper an improved Mean Shift algorithm comprising a fast failure recovery strategy that aims to deal with randomly moving targets and complete occlusion as encountered in crowded scenes is presented. Experimental results show that after complete occlusion or target loss, the new algorithm can effectively recover and continue to successfully track targets in complex scenarios.

Conference

Conference8th IEEE International Conference on Advanced Video and Signal-Based Surveillance
CountryAustria
CityKlagenfurt
Period30/08/112/09/11

Fingerprint

Recovery

Keywords

  • mean shift tracker
  • fast failure recovery strategy
  • track targets

Cite this

Di Caterina, G., & Soraghan, J. (2011). An improved mean shift tracker with fast failure recovery strategy after complete occlusion. 1-6. Paper presented at 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria.
Di Caterina, Gaetano ; Soraghan, John. / An improved mean shift tracker with fast failure recovery strategy after complete occlusion. Paper presented at 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria.6 p.
@conference{de2b9d6045c145599f0e71ec839947b2,
title = "An improved mean shift tracker with fast failure recovery strategy after complete occlusion",
abstract = "The effectiveness of the conventional Mean Shift tracking algorithm diminishes for fast moving targets and complete occlusion. In this paper an improved Mean Shift algorithm comprising a fast failure recovery strategy that aims to deal with randomly moving targets and complete occlusion as encountered in crowded scenes is presented. Experimental results show that after complete occlusion or target loss, the new algorithm can effectively recover and continue to successfully track targets in complex scenarios.",
keywords = "mean shift tracker , fast failure recovery strategy, track targets",
author = "{Di Caterina}, Gaetano and John Soraghan",
year = "2011",
language = "English",
pages = "1--6",
note = "8th IEEE International Conference on Advanced Video and Signal-Based Surveillance ; Conference date: 30-08-2011 Through 02-09-2011",

}

Di Caterina, G & Soraghan, J 2011, 'An improved mean shift tracker with fast failure recovery strategy after complete occlusion' Paper presented at 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria, 30/08/11 - 2/09/11, pp. 1-6.

An improved mean shift tracker with fast failure recovery strategy after complete occlusion. / Di Caterina, Gaetano; Soraghan, John.

2011. 1-6 Paper presented at 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria.

Research output: Contribution to conferencePaper

TY - CONF

T1 - An improved mean shift tracker with fast failure recovery strategy after complete occlusion

AU - Di Caterina, Gaetano

AU - Soraghan, John

PY - 2011

Y1 - 2011

N2 - The effectiveness of the conventional Mean Shift tracking algorithm diminishes for fast moving targets and complete occlusion. In this paper an improved Mean Shift algorithm comprising a fast failure recovery strategy that aims to deal with randomly moving targets and complete occlusion as encountered in crowded scenes is presented. Experimental results show that after complete occlusion or target loss, the new algorithm can effectively recover and continue to successfully track targets in complex scenarios.

AB - The effectiveness of the conventional Mean Shift tracking algorithm diminishes for fast moving targets and complete occlusion. In this paper an improved Mean Shift algorithm comprising a fast failure recovery strategy that aims to deal with randomly moving targets and complete occlusion as encountered in crowded scenes is presented. Experimental results show that after complete occlusion or target loss, the new algorithm can effectively recover and continue to successfully track targets in complex scenarios.

KW - mean shift tracker

KW - fast failure recovery strategy

KW - track targets

UR - http://www.avss2011.org/

M3 - Paper

SP - 1

EP - 6

ER -

Di Caterina G, Soraghan J. An improved mean shift tracker with fast failure recovery strategy after complete occlusion. 2011. Paper presented at 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria.