Group stochastic search for object detection and tracking

Murray Evans

doi:10.1109/AVSS.2005.1577259

Group stochastic search for object detection and tracking

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

2 Citations (SciVal)

Abstract

A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320×240 resolution video at up to 15 fps.

Original language	English
Title of host publication	Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance 2005
Subtitle of host publication	AVSS2005
DOIs	https://doi.org/10.1109/AVSS.2005.1577259
Publication status	Published - Oct 2005

Access to Document

10.1109/AVSS.2005.1577259

Cite this

@inproceedings{2e8b12cd888746489c7d18d14393fea5,

title = "Group stochastic search for object detection and tracking",

abstract = "A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320×240 resolution video at up to 15 fps.",

author = "Murray Evans",

year = "2005",

month = oct,

doi = "10.1109/AVSS.2005.1577259",

language = "English",

isbn = "0-7803-9385-6",

booktitle = "Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance 2005",

}

TY - GEN

T1 - Group stochastic search for object detection and tracking

AU - Evans, Murray

PY - 2005/10

Y1 - 2005/10

N2 - A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320×240 resolution video at up to 15 fps.

AB - A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320×240 resolution video at up to 15 fps.

U2 - 10.1109/AVSS.2005.1577259

DO - 10.1109/AVSS.2005.1577259

M3 - Chapter in a published conference proceeding

SN - 0-7803-9385-6

BT - Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance 2005

ER -

Group stochastic search for object detection and tracking

Abstract

Access to Document

Fingerprint

Cite this