Real-time motion analysis with linear-programming

Moshe Ben-Ezra; Shmuel Peleg; Michael Werman

doi:10.1109/iccv.1999.790290

Real-time motion analysis with linear-programming

Moshe Ben-Ezra^*, Shmuel Peleg, Michael Werman

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Conference article › peer-review

11 Scopus citations

Abstract

A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approximate other motion measurements as well. Using an L₁ error measure for image alignment based on point-to-line correspondences and minimizing this measure using linear programming, achieves results which are more robust than the commonly used L₂ metric. While estimators based on L₁ are not theoretically robust, experiments show that the proposed method is robust enough to allow accurate motion recovery in hundreds of consecutive frames. The entire computation is performed in real-time on a PC with no special hardware.

Original language	English
Pages (from-to)	703-709
Number of pages	7
Journal	Proceedings of the IEEE International Conference on Computer Vision
Volume	2
DOIs	https://doi.org/10.1109/iccv.1999.790290
State	Published - 1999
Event	Proceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) - Kerkyra, Greece Duration: 20 Sep 1999 → 27 Sep 1999

Access to Document

10.1109/iccv.1999.790290

Cite this

@article{970b2f3cb0004b9b9710ce334248f675,

title = "Real-time motion analysis with linear-programming",

abstract = "A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approximate other motion measurements as well. Using an L1 error measure for image alignment based on point-to-line correspondences and minimizing this measure using linear programming, achieves results which are more robust than the commonly used L2 metric. While estimators based on L1 are not theoretically robust, experiments show that the proposed method is robust enough to allow accurate motion recovery in hundreds of consecutive frames. The entire computation is performed in real-time on a PC with no special hardware.",

author = "Moshe Ben-Ezra and Shmuel Peleg and Michael Werman",

year = "1999",

doi = "10.1109/iccv.1999.790290",

language = "אנגלית",

volume = "2",

pages = "703--709",

journal = "Proceedings of the IEEE International Conference on Computer Vision",

issn = "1550-5499",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) ; Conference date: 20-09-1999 Through 27-09-1999",

}

TY - JOUR

T1 - Real-time motion analysis with linear-programming

AU - Ben-Ezra, Moshe

AU - Peleg, Shmuel

AU - Werman, Michael

PY - 1999

Y1 - 1999

N2 - A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approximate other motion measurements as well. Using an L1 error measure for image alignment based on point-to-line correspondences and minimizing this measure using linear programming, achieves results which are more robust than the commonly used L2 metric. While estimators based on L1 are not theoretically robust, experiments show that the proposed method is robust enough to allow accurate motion recovery in hundreds of consecutive frames. The entire computation is performed in real-time on a PC with no special hardware.

AB - A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approximate other motion measurements as well. Using an L1 error measure for image alignment based on point-to-line correspondences and minimizing this measure using linear programming, achieves results which are more robust than the commonly used L2 metric. While estimators based on L1 are not theoretically robust, experiments show that the proposed method is robust enough to allow accurate motion recovery in hundreds of consecutive frames. The entire computation is performed in real-time on a PC with no special hardware.

UR - http://www.scopus.com/inward/record.url?scp=0033285703&partnerID=8YFLogxK

U2 - 10.1109/iccv.1999.790290

DO - 10.1109/iccv.1999.790290

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:0033285703

SN - 1550-5499

VL - 2

SP - 703

EP - 709

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

T2 - Proceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99)

Y2 - 20 September 1999 through 27 September 1999

ER -

Real-time motion analysis with linear-programming

Abstract

Access to Document

Other files and links

Fingerprint

Cite this