An adaptive visual tracking method based on multiple features

A. De Stasio, Michele Ceccarelli

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

Abstract

Object tracking naturally plays a key role in any visual surveillance system, and there are a number of tracking algorithms for different applications. Here we present an object tracking system based on the Multiple Hypothesis Testing approach. The main characteristic of our approach consists in the development of a probabilistic data association mechanism which makes use of multiple features about each observed objects in the scene. The appearance and disappearance of object is based on a hypothesis matrix. Each matrix element, represents the possibility that a given object at a certain time instant matches another object at a successive time instant. In practice the matching between objects is obtained by comparing Kalman predicted features and observed features between successive time steps. Therefore, our algorithm dynamically creates and destroys tracks on the basis of the hypothesis matrix.

Original languageEnglish
Title of host publicationIST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques
Pages49-53
Number of pages5
Volume2006
DOIs
Publication statusPublished - 22 Dec 2006
Externally publishedYes
EventIST 2006 - 2006 IEEE International Workshop on Imagining Systems and Techniques - Ninori, Italy
Duration: 29 Apr 200629 Apr 2006

Other

OtherIST 2006 - 2006 IEEE International Workshop on Imagining Systems and Techniques
CountryItaly
CityNinori
Period29/4/0629/4/06

Fingerprint

Testing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

De Stasio, A., & Ceccarelli, M. (2006). An adaptive visual tracking method based on multiple features. In IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques (Vol. 2006, pp. 49-53). [1650774] https://doi.org/10.1109/IST.2006.1650774

An adaptive visual tracking method based on multiple features. / De Stasio, A.; Ceccarelli, Michele.

IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques. Vol. 2006 2006. p. 49-53 1650774.

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

De Stasio, A & Ceccarelli, M 2006, An adaptive visual tracking method based on multiple features. in IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques. vol. 2006, 1650774, pp. 49-53, IST 2006 - 2006 IEEE International Workshop on Imagining Systems and Techniques, Ninori, Italy, 29/4/06. https://doi.org/10.1109/IST.2006.1650774
De Stasio A, Ceccarelli M. An adaptive visual tracking method based on multiple features. In IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques. Vol. 2006. 2006. p. 49-53. 1650774 https://doi.org/10.1109/IST.2006.1650774
De Stasio, A. ; Ceccarelli, Michele. / An adaptive visual tracking method based on multiple features. IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques. Vol. 2006 2006. pp. 49-53
@inproceedings{93dccd7660e444e78419f86ae82405b6,
title = "An adaptive visual tracking method based on multiple features",
abstract = "Object tracking naturally plays a key role in any visual surveillance system, and there are a number of tracking algorithms for different applications. Here we present an object tracking system based on the Multiple Hypothesis Testing approach. The main characteristic of our approach consists in the development of a probabilistic data association mechanism which makes use of multiple features about each observed objects in the scene. The appearance and disappearance of object is based on a hypothesis matrix. Each matrix element, represents the possibility that a given object at a certain time instant matches another object at a successive time instant. In practice the matching between objects is obtained by comparing Kalman predicted features and observed features between successive time steps. Therefore, our algorithm dynamically creates and destroys tracks on the basis of the hypothesis matrix.",
author = "{De Stasio}, A. and Michele Ceccarelli",
year = "2006",
month = "12",
day = "22",
doi = "10.1109/IST.2006.1650774",
language = "English",
isbn = "1424402514",
volume = "2006",
pages = "49--53",
booktitle = "IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques",

}

TY - GEN

T1 - An adaptive visual tracking method based on multiple features

AU - De Stasio, A.

AU - Ceccarelli, Michele

PY - 2006/12/22

Y1 - 2006/12/22

N2 - Object tracking naturally plays a key role in any visual surveillance system, and there are a number of tracking algorithms for different applications. Here we present an object tracking system based on the Multiple Hypothesis Testing approach. The main characteristic of our approach consists in the development of a probabilistic data association mechanism which makes use of multiple features about each observed objects in the scene. The appearance and disappearance of object is based on a hypothesis matrix. Each matrix element, represents the possibility that a given object at a certain time instant matches another object at a successive time instant. In practice the matching between objects is obtained by comparing Kalman predicted features and observed features between successive time steps. Therefore, our algorithm dynamically creates and destroys tracks on the basis of the hypothesis matrix.

AB - Object tracking naturally plays a key role in any visual surveillance system, and there are a number of tracking algorithms for different applications. Here we present an object tracking system based on the Multiple Hypothesis Testing approach. The main characteristic of our approach consists in the development of a probabilistic data association mechanism which makes use of multiple features about each observed objects in the scene. The appearance and disappearance of object is based on a hypothesis matrix. Each matrix element, represents the possibility that a given object at a certain time instant matches another object at a successive time instant. In practice the matching between objects is obtained by comparing Kalman predicted features and observed features between successive time steps. Therefore, our algorithm dynamically creates and destroys tracks on the basis of the hypothesis matrix.

UR - http://www.scopus.com/inward/record.url?scp=33845564184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845564184&partnerID=8YFLogxK

U2 - 10.1109/IST.2006.1650774

DO - 10.1109/IST.2006.1650774

M3 - Conference contribution

SN - 1424402514

SN - 9781424402519

VL - 2006

SP - 49

EP - 53

BT - IST 2006 - Proceedings of the 2006 IEEE International Workshop on Imagining Systems and Techniques

ER -