IEICE TRANSACTIONS on Information
Space-Time Invariants for Recognizing 3D Motions from Arbitrary Viewpoints under Perspective Projection
Summary :
Extracting visual motion is very important for understanding dynamic actions and for extracting dynamic events from video sequences. Recently, it was shown that some invariants on motions can be extracted from sequential images and applied for recognizing motions from images viewed from arbitrary viewpoints. Unfortunately, these space-time invariants were limited for planar motions viewed from affine cameras. In this paper, we propose a method for computing space-time invariants on non-planar motions viewed from two perspective cameras. The extracted invariants are applied for distinguishing 3D motions from video sequences viewed from arbitrary viewpoints.
- Publication
- IEICE TRANSACTIONS on Information Vol.E89-D No.7 pp.2268-2274
- Publication Date
- 2006/07/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e89-d.7.2268
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Ying PIAO, Kazutaka HAYAKAWA, Jun SATO, "Space-Time Invariants for Recognizing 3D Motions from Arbitrary Viewpoints under Perspective Projection" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 7, pp. 2268-2274, July 2006, doi: 10.1093/ietisy/e89-d.7.2268.
Abstract: Extracting visual motion is very important for understanding dynamic actions and for extracting dynamic events from video sequences. Recently, it was shown that some invariants on motions can be extracted from sequential images and applied for recognizing motions from images viewed from arbitrary viewpoints. Unfortunately, these space-time invariants were limited for planar motions viewed from affine cameras. In this paper, we propose a method for computing space-time invariants on non-planar motions viewed from two perspective cameras. The extracted invariants are applied for distinguishing 3D motions from video sequences viewed from arbitrary viewpoints.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2268/_p
Copy
@ARTICLE{e89-d_7_2268,
author={Ying PIAO, Kazutaka HAYAKAWA, Jun SATO, },
journal={IEICE TRANSACTIONS on Information},
title={Space-Time Invariants for Recognizing 3D Motions from Arbitrary Viewpoints under Perspective Projection},
year={2006},
volume={E89-D},
number={7},
pages={2268-2274},
abstract={Extracting visual motion is very important for understanding dynamic actions and for extracting dynamic events from video sequences. Recently, it was shown that some invariants on motions can be extracted from sequential images and applied for recognizing motions from images viewed from arbitrary viewpoints. Unfortunately, these space-time invariants were limited for planar motions viewed from affine cameras. In this paper, we propose a method for computing space-time invariants on non-planar motions viewed from two perspective cameras. The extracted invariants are applied for distinguishing 3D motions from video sequences viewed from arbitrary viewpoints.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2268},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Space-Time Invariants for Recognizing 3D Motions from Arbitrary Viewpoints under Perspective Projection
T2 - IEICE TRANSACTIONS on Information
SP - 2268
EP - 2274
AU - Ying PIAO
AU - Kazutaka HAYAKAWA
AU - Jun SATO
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2268
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - Extracting visual motion is very important for understanding dynamic actions and for extracting dynamic events from video sequences. Recently, it was shown that some invariants on motions can be extracted from sequential images and applied for recognizing motions from images viewed from arbitrary viewpoints. Unfortunately, these space-time invariants were limited for planar motions viewed from affine cameras. In this paper, we propose a method for computing space-time invariants on non-planar motions viewed from two perspective cameras. The extracted invariants are applied for distinguishing 3D motions from video sequences viewed from arbitrary viewpoints.
ER -
English
