Multiple target tracking with lazy background subtraction and connected components analysis

Authors:
Robert G. Abbott;Lance R. Williams
Affiliations:
Sandia National Labs, PO Box 5800, MS 1188, 87185, Albuquerque, NM, USA;University of New Mexico, Department of Computer Science, 87131, Albuquerque, NM, USA
Venue:
Machine Vision and Applications
Year:
2009

Citing 0
Cited 3

Object detection based on a robust and accurate statistical multi-point-pair model

Pattern Recognition
Visual tracking of multiple targets by multi-bernoulli filtering of background subtracted image data

ICSI'11 Proceedings of the Second international conference on Advances in swarm intelligence - Volume Part II
Visual tracking of numerous targets via multi-Bernoulli filtering of image data

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Background subtraction, binary morphology, and connected components analysis are the first processing steps in many vision-based tracking applications. Although background subtraction has been the subject of much research, it is typically treated as a stand-alone process, dissociated from the subsequent phases of object recognition and tracking. This paper presents a method for decreasing computational cost in visual tracking systems by using track state estimates to direct and constrain image segmentation via background subtraction and connected components analysis. We also present a multiple target tracking application that uses the technique to achieve a large reduction in computation costs.