EKF-based recursive dual estimation of structure & motion from stereo data

Hongshcng Zhang, Shahriar Negahdaripour

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Extended Kalman filters (EKF) have been proposed to estimate ego-motion and to recursively update scene structure in the form of 3-D positions of selected prominent features from motion and stereo sequences. Previous methods typically accommodate no more than a few dozen features for real-time processing. To maintain motion estimation accuracy, this calls for high contrast images to compute image feature locations with precision. Within manmade environments, various prominent corner points exist that can be extracted and tracked with required accuracy. However, prominent features are more difficult to localize precisely in natural scenes. Statistically, more feature points become necessary to maintain the same level of motion estimation accuracy and robustness. However, this imposes a computational burden beyond the capability of EKF-based techniques for real-time processing. A sequential dual EKF estimator utilizing stereo data is proposed for improved computation efficiency. Two important issues, unbiased estimation and stochastic stability are addressed. Furthermore, the dynamic feature set is handled in a more effective, efficient and robust way. Experimental results to demonstrate the merits of the new theoretical and algorithmic developments are presented.

Original languageEnglish
Title of host publicationProceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Pages73-80
Number of pages8
DOIs
StatePublished - Dec 1 2007
Event3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 - Chapel Hill, NC, United States
Duration: Jun 14 2006Jun 16 2006

Other

Other3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
CountryUnited States
CityChapel Hill, NC
Period6/14/066/16/06

Fingerprint

Extended Kalman filters
Motion estimation
Processing

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications

Cite this

Zhang, H., & Negahdaripour, S. (2007). EKF-based recursive dual estimation of structure & motion from stereo data. In Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 (pp. 73-80). [4155712] https://doi.org/10.1109/3DPVT.2006.55

EKF-based recursive dual estimation of structure & motion from stereo data. / Zhang, Hongshcng; Negahdaripour, Shahriar.

Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. p. 73-80 4155712.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, H & Negahdaripour, S 2007, EKF-based recursive dual estimation of structure & motion from stereo data. in Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006., 4155712, pp. 73-80, 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, Chapel Hill, NC, United States, 6/14/06. https://doi.org/10.1109/3DPVT.2006.55
Zhang H, Negahdaripour S. EKF-based recursive dual estimation of structure & motion from stereo data. In Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. p. 73-80. 4155712 https://doi.org/10.1109/3DPVT.2006.55
Zhang, Hongshcng ; Negahdaripour, Shahriar. / EKF-based recursive dual estimation of structure & motion from stereo data. Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. pp. 73-80
@inproceedings{3b1f7f97e5c74d678e9990caa28ebc66,
title = "EKF-based recursive dual estimation of structure & motion from stereo data",
abstract = "Extended Kalman filters (EKF) have been proposed to estimate ego-motion and to recursively update scene structure in the form of 3-D positions of selected prominent features from motion and stereo sequences. Previous methods typically accommodate no more than a few dozen features for real-time processing. To maintain motion estimation accuracy, this calls for high contrast images to compute image feature locations with precision. Within manmade environments, various prominent corner points exist that can be extracted and tracked with required accuracy. However, prominent features are more difficult to localize precisely in natural scenes. Statistically, more feature points become necessary to maintain the same level of motion estimation accuracy and robustness. However, this imposes a computational burden beyond the capability of EKF-based techniques for real-time processing. A sequential dual EKF estimator utilizing stereo data is proposed for improved computation efficiency. Two important issues, unbiased estimation and stochastic stability are addressed. Furthermore, the dynamic feature set is handled in a more effective, efficient and robust way. Experimental results to demonstrate the merits of the new theoretical and algorithmic developments are presented.",
author = "Hongshcng Zhang and Shahriar Negahdaripour",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/3DPVT.2006.55",
language = "English",
isbn = "0769528252",
pages = "73--80",
booktitle = "Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

}

TY - GEN

T1 - EKF-based recursive dual estimation of structure & motion from stereo data

AU - Zhang, Hongshcng

AU - Negahdaripour, Shahriar

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Extended Kalman filters (EKF) have been proposed to estimate ego-motion and to recursively update scene structure in the form of 3-D positions of selected prominent features from motion and stereo sequences. Previous methods typically accommodate no more than a few dozen features for real-time processing. To maintain motion estimation accuracy, this calls for high contrast images to compute image feature locations with precision. Within manmade environments, various prominent corner points exist that can be extracted and tracked with required accuracy. However, prominent features are more difficult to localize precisely in natural scenes. Statistically, more feature points become necessary to maintain the same level of motion estimation accuracy and robustness. However, this imposes a computational burden beyond the capability of EKF-based techniques for real-time processing. A sequential dual EKF estimator utilizing stereo data is proposed for improved computation efficiency. Two important issues, unbiased estimation and stochastic stability are addressed. Furthermore, the dynamic feature set is handled in a more effective, efficient and robust way. Experimental results to demonstrate the merits of the new theoretical and algorithmic developments are presented.

AB - Extended Kalman filters (EKF) have been proposed to estimate ego-motion and to recursively update scene structure in the form of 3-D positions of selected prominent features from motion and stereo sequences. Previous methods typically accommodate no more than a few dozen features for real-time processing. To maintain motion estimation accuracy, this calls for high contrast images to compute image feature locations with precision. Within manmade environments, various prominent corner points exist that can be extracted and tracked with required accuracy. However, prominent features are more difficult to localize precisely in natural scenes. Statistically, more feature points become necessary to maintain the same level of motion estimation accuracy and robustness. However, this imposes a computational burden beyond the capability of EKF-based techniques for real-time processing. A sequential dual EKF estimator utilizing stereo data is proposed for improved computation efficiency. Two important issues, unbiased estimation and stochastic stability are addressed. Furthermore, the dynamic feature set is handled in a more effective, efficient and robust way. Experimental results to demonstrate the merits of the new theoretical and algorithmic developments are presented.

UR - http://www.scopus.com/inward/record.url?scp=47249137861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47249137861&partnerID=8YFLogxK

U2 - 10.1109/3DPVT.2006.55

DO - 10.1109/3DPVT.2006.55

M3 - Conference contribution

AN - SCOPUS:47249137861

SN - 0769528252

SN - 9780769528250

SP - 73

EP - 80

BT - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

ER -