Segmentation and factorization-based motion and structure estimation for long image sequences

Christian Debrunner; Narendra Ahuja

doi:10.1109/34.659941

Segmentation and factorization-based motion and structure estimation for long image sequences

Christian Debrunner, Narendra Ahuja

Beckman Institute for Advanced Science and Technology

Research output: Contribution to journal › Article › peer-review

Abstract

This paper presents a computer algorithm which given a dense temporal sequence of intensity images of multiple moving objects will separate the images into regions showing distinct objects and for those objects which are rotating will calculate the threedimensional structure and motion.

Original language	English (US)
Pages (from-to)	206-211
Number of pages	6
Journal	IEEE transactions on pattern analysis and machine intelligence
Volume	20
Issue number	2
DOIs	https://doi.org/10.1109/34.659941
State	Published - 1998

Keywords

Image motion factorization
Image segmentation
Motion estimation
Motion sequence segmentation
Motion understanding
Multiple motion segmentation
Point tracking
Trajectory detection

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Online availability

10.1109/34.659941

Library availability

Discover UIUC Full Text

Cite this

@article{2b2e83630ed2482fa1e14fc6508331f0,

title = "Segmentation and factorization-based motion and structure estimation for long image sequences",

abstract = "This paper presents a computer algorithm which given a dense temporal sequence of intensity images of multiple moving objects will separate the images into regions showing distinct objects and for those objects which are rotating will calculate the threedimensional structure and motion.",

keywords = "Image motion factorization, Image segmentation, Motion estimation, Motion sequence segmentation, Motion understanding, Multiple motion segmentation, Point tracking, Trajectory detection",

author = "Christian Debrunner and Narendra Ahuja",

note = "Funding Information: This paper was supported by DARPA and the U.S. National Science Foundation under grant IRI-89-02728 and the State of Illinois Department of Commerce and Community Affairs under grant 90-103.",

year = "1998",

doi = "10.1109/34.659941",

language = "English (US)",

volume = "20",

pages = "206--211",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "2",

}

TY - JOUR

T1 - Segmentation and factorization-based motion and structure estimation for long image sequences

AU - Debrunner, Christian

AU - Ahuja, Narendra

N1 - Funding Information: This paper was supported by DARPA and the U.S. National Science Foundation under grant IRI-89-02728 and the State of Illinois Department of Commerce and Community Affairs under grant 90-103.

PY - 1998

Y1 - 1998

N2 - This paper presents a computer algorithm which given a dense temporal sequence of intensity images of multiple moving objects will separate the images into regions showing distinct objects and for those objects which are rotating will calculate the threedimensional structure and motion.

AB - This paper presents a computer algorithm which given a dense temporal sequence of intensity images of multiple moving objects will separate the images into regions showing distinct objects and for those objects which are rotating will calculate the threedimensional structure and motion.

KW - Image motion factorization

KW - Image segmentation

KW - Motion estimation

KW - Motion sequence segmentation

KW - Motion understanding

KW - Multiple motion segmentation

KW - Point tracking

KW - Trajectory detection

UR - http://www.scopus.com/inward/record.url?scp=0032003655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032003655&partnerID=8YFLogxK

U2 - 10.1109/34.659941

DO - 10.1109/34.659941

M3 - Article

AN - SCOPUS:0032003655

SN - 0162-8828

VL - 20

SP - 206

EP - 211

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 2

ER -

Segmentation and factorization-based motion and structure estimation for long image sequences

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this