Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation

Yasuyuki SUGAYA; Kenichi KANATANI

Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation

Yasuyuki SUGAYA, Kenichi KANATANI

Full Text Views

0

Cite this

Summary :

Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.

Publication: IEICE TRANSACTIONS on Information Vol.E87-D No.7 pp.1935-1942

Publication Date: 2004/07/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Yasuyuki SUGAYA, Kenichi KANATANI, "Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation" in IEICE TRANSACTIONS on Information, vol. E87-D, no. 7, pp. 1935-1942, July 2004, doi: .
Abstract: Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.
URL: https://global.ieice.org/en_transactions/information/10.1587/e87-d_7_1935/_p

Copy

@ARTICLE{e87-d_7_1935,
author={Yasuyuki SUGAYA, Kenichi KANATANI, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation},
year={2004},
volume={E87-D},
number={7},
pages={1935-1942},
abstract={Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 1935
EP - 1942
AU - Yasuyuki SUGAYA
AU - Kenichi KANATANI
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2004
AB - Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.
ER -