Fast Level Set Methodを用いた複数移動物体の三次元追跡

Translated title of the contribution: 3D Tracking of Multiple Moving Objects using Fast Level Set Method

岩下 友美, 倉爪 亮, 辻 徳生, 原 健二, 長谷川 勉

Research output: Contribution to journalArticle

Abstract

The level set method (LSM) has attracted much attention as a method that realizes a topology free active contour modeling. This method utilizes an implicit representation of a contour to be tracked, and is able to handle the topological change of the contour intrinsically. Various applications including motion tracking and 3D geometrical modeling have been proposed so far. However, the calculation cost of reinitialization and updating of the implicit function is considerably expensive as compared with conventional active contour models such as"Snakes". To overcome this problem, we have proposed an efficient algorithm of the LSM named the Fast Level Set Method (FLSM) . This paper presents a 3D simultaneous motion tracking system of multiple targets using the FLSM, and shows a series of experimental results to verify the effectiveness of the system even in the event of occlusion. Characteristics of this system are as follows: (i) Topologically free, (ii) Robustness for self and mutual occlusion, (iii) Ease to calibrate several stereo cameras using ICP algorithm. In this paper, we present a robust 3D motion tracking system for target occlusion using the FLSM, and show some experimental results of tracking of multiple targets.
Original languageJapanese
Pages (from-to)813-820
Number of pages8
Journal日本ロボット学会誌
Volume23
Issue number7
DOIs
Publication statusPublished - 2005

Fingerprint

Cameras
Topology
Costs

Cite this

Fast Level Set Methodを用いた複数移動物体の三次元追跡. / 岩下友美; 倉爪亮; 辻徳生; 原健二; 長谷川勉.

In: 日本ロボット学会誌, Vol. 23, No. 7, 2005, p. 813-820.

Research output: Contribution to journalArticle

@article{e1d3ecfd310b4481be2b855cc54bfb76,
title = "Fast Level Set Methodを用いた複数移動物体の三次元追跡",
abstract = "The level set method (LSM) has attracted much attention as a method that realizes a topology free active contour modeling. This method utilizes an implicit representation of a contour to be tracked, and is able to handle the topological change of the contour intrinsically. Various applications including motion tracking and 3D geometrical modeling have been proposed so far. However, the calculation cost of reinitialization and updating of the implicit function is considerably expensive as compared with conventional active contour models such as{"}Snakes{"}. To overcome this problem, we have proposed an efficient algorithm of the LSM named the Fast Level Set Method (FLSM) . This paper presents a 3D simultaneous motion tracking system of multiple targets using the FLSM, and shows a series of experimental results to verify the effectiveness of the system even in the event of occlusion. Characteristics of this system are as follows: (i) Topologically free, (ii) Robustness for self and mutual occlusion, (iii) Ease to calibrate several stereo cameras using ICP algorithm. In this paper, we present a robust 3D motion tracking system for target occlusion using the FLSM, and show some experimental results of tracking of multiple targets.",
author = "友美 岩下 and 亮 倉爪 and 徳生 辻 and 健二 原 and 勉 長谷川",
year = "2005",
doi = "10.7210/jrsj.23.813",
language = "Japanese",
volume = "23",
pages = "813--820",
journal = "日本ロボット学会誌",
issn = "0289-1824",
publisher = "一般社団法人 日本ロボット学会",
number = "7",

}

TY - JOUR

T1 - Fast Level Set Methodを用いた複数移動物体の三次元追跡

AU - 岩下, 友美

AU - 倉爪, 亮

AU - 辻, 徳生

AU - 原, 健二

AU - 長谷川, 勉

PY - 2005

Y1 - 2005

N2 - The level set method (LSM) has attracted much attention as a method that realizes a topology free active contour modeling. This method utilizes an implicit representation of a contour to be tracked, and is able to handle the topological change of the contour intrinsically. Various applications including motion tracking and 3D geometrical modeling have been proposed so far. However, the calculation cost of reinitialization and updating of the implicit function is considerably expensive as compared with conventional active contour models such as"Snakes". To overcome this problem, we have proposed an efficient algorithm of the LSM named the Fast Level Set Method (FLSM) . This paper presents a 3D simultaneous motion tracking system of multiple targets using the FLSM, and shows a series of experimental results to verify the effectiveness of the system even in the event of occlusion. Characteristics of this system are as follows: (i) Topologically free, (ii) Robustness for self and mutual occlusion, (iii) Ease to calibrate several stereo cameras using ICP algorithm. In this paper, we present a robust 3D motion tracking system for target occlusion using the FLSM, and show some experimental results of tracking of multiple targets.

AB - The level set method (LSM) has attracted much attention as a method that realizes a topology free active contour modeling. This method utilizes an implicit representation of a contour to be tracked, and is able to handle the topological change of the contour intrinsically. Various applications including motion tracking and 3D geometrical modeling have been proposed so far. However, the calculation cost of reinitialization and updating of the implicit function is considerably expensive as compared with conventional active contour models such as"Snakes". To overcome this problem, we have proposed an efficient algorithm of the LSM named the Fast Level Set Method (FLSM) . This paper presents a 3D simultaneous motion tracking system of multiple targets using the FLSM, and shows a series of experimental results to verify the effectiveness of the system even in the event of occlusion. Characteristics of this system are as follows: (i) Topologically free, (ii) Robustness for self and mutual occlusion, (iii) Ease to calibrate several stereo cameras using ICP algorithm. In this paper, we present a robust 3D motion tracking system for target occlusion using the FLSM, and show some experimental results of tracking of multiple targets.

U2 - 10.7210/jrsj.23.813

DO - 10.7210/jrsj.23.813

M3 - 記事

VL - 23

SP - 813

EP - 820

JO - 日本ロボット学会誌

JF - 日本ロボット学会誌

SN - 0289-1824

IS - 7

ER -