The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cet article, nous proposons un nouveau système de suivi d'objets basé sur un classificateur. Notre tracker est la combinaison d'un détecteur basé sur les fonctionnalités rectangulaires (RF) [17], [18] et d'une méthode de suivi basée sur le flux optique [1]. Nous montrons que le gradient des RF étendus peut être calculé rapidement en utilisant la méthode de l'image intégrale. Le tracker proposé a été testé sur des séquences vidéo réelles. Nous avons appliqué notre tracker pour des expériences de suivi de visage et de suivi de voiture. Notre tracker fonctionnait à plus de 100 ips tout en conservant une précision comparable à celle d'un détecteur RF. Notre routine de suivi qui ne contient pas de traitement d'E/S d'image peut être effectuée à une vitesse d'environ 500 à 2,500 XNUMX ips avec une précision de suivi suffisante.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Akinori HIDAKA, Kenji NISHIDA, Takio KURITA, "Object Tracking by Maximizing Classification Score of Detector Based on Rectangle Features" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 8, pp. 2163-2170, August 2008, doi: 10.1093/ietisy/e91-d.8.2163.
Abstract: In this paper, we propose a novel classifier-based object tracker. Our tracker is the combination of Rectangle Feature (RF) based detector [17],[18] and optical-flow based tracking method [1]. We show that the gradient of extended RFs can be calculated rapidly by using Integral Image method. The proposed tracker was tested on real video sequences. We applied our tracker for face tracking and car tracking experiments. Our tracker worked over 100 fps while maintaining comparable accuracy to RF based detector. Our tracking routine that does not contain image I/O processing can be performed about 500 to 2,500 fps with sufficient tracking accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.8.2163/_p
Copier
@ARTICLE{e91-d_8_2163,
author={Akinori HIDAKA, Kenji NISHIDA, Takio KURITA, },
journal={IEICE TRANSACTIONS on Information},
title={Object Tracking by Maximizing Classification Score of Detector Based on Rectangle Features},
year={2008},
volume={E91-D},
number={8},
pages={2163-2170},
abstract={In this paper, we propose a novel classifier-based object tracker. Our tracker is the combination of Rectangle Feature (RF) based detector [17],[18] and optical-flow based tracking method [1]. We show that the gradient of extended RFs can be calculated rapidly by using Integral Image method. The proposed tracker was tested on real video sequences. We applied our tracker for face tracking and car tracking experiments. Our tracker worked over 100 fps while maintaining comparable accuracy to RF based detector. Our tracking routine that does not contain image I/O processing can be performed about 500 to 2,500 fps with sufficient tracking accuracy.},
keywords={},
doi={10.1093/ietisy/e91-d.8.2163},
ISSN={1745-1361},
month={August},}
Copier
TY - JOUR
TI - Object Tracking by Maximizing Classification Score of Detector Based on Rectangle Features
T2 - IEICE TRANSACTIONS on Information
SP - 2163
EP - 2170
AU - Akinori HIDAKA
AU - Kenji NISHIDA
AU - Takio KURITA
PY - 2008
DO - 10.1093/ietisy/e91-d.8.2163
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2008
AB - In this paper, we propose a novel classifier-based object tracker. Our tracker is the combination of Rectangle Feature (RF) based detector [17],[18] and optical-flow based tracking method [1]. We show that the gradient of extended RFs can be calculated rapidly by using Integral Image method. The proposed tracker was tested on real video sequences. We applied our tracker for face tracking and car tracking experiments. Our tracker worked over 100 fps while maintaining comparable accuracy to RF based detector. Our tracking routine that does not contain image I/O processing can be performed about 500 to 2,500 fps with sufficient tracking accuracy.
ER -