Efficient tracking and ego-motion recovery using gait analysis

Huiyu Zhou, Andrew M. Wallace, Patrick R. Green

Research output: Contribution to journalArticle

Abstract

We present a strategy based on human gait to achieve efficient tracking, recovery of ego-motion and 3-D reconstruction from an image sequence acquired by a single camera attached to a pedestrian. In the first phase, the parameters of the human gait are established by a classical frame-by-frame analysis, using an generalized least squares (GLS) technique. The gait model is non-linear, represented by a truncated Fourier series. In the second phase, this gait model is employed within a "predict-correct" framework using a maximum a posteriori, expectation-maximization (MAP-EM) strategy to obtain robust estimates of the ego-motion and scene structure, while continuously refining the gait model. Experiments on synthetic and real image sequences show that the use of the gait model results in more efficient tracking. This is demonstrated by improved matching and retention of features, and a reduction in execution time, when processing video sequences. © 2009 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)2367-2384
Number of pages18
JournalSignal Processing
Volume89
Issue number12
DOIs
Publication statusPublished - Dec 2009

Fingerprint

Gait analysis
Recovery
Fourier series
Refining
Cameras
Processing
Experiments

Keywords

  • 3-D reconstruction
  • Efficiency
  • Ego-motion
  • Human gait
  • Tracking

Cite this

Zhou, Huiyu ; Wallace, Andrew M. ; Green, Patrick R. / Efficient tracking and ego-motion recovery using gait analysis. In: Signal Processing. 2009 ; Vol. 89, No. 12. pp. 2367-2384.
@article{6bed8f9906d74f82a398551559580e7e,
title = "Efficient tracking and ego-motion recovery using gait analysis",
abstract = "We present a strategy based on human gait to achieve efficient tracking, recovery of ego-motion and 3-D reconstruction from an image sequence acquired by a single camera attached to a pedestrian. In the first phase, the parameters of the human gait are established by a classical frame-by-frame analysis, using an generalized least squares (GLS) technique. The gait model is non-linear, represented by a truncated Fourier series. In the second phase, this gait model is employed within a {"}predict-correct{"} framework using a maximum a posteriori, expectation-maximization (MAP-EM) strategy to obtain robust estimates of the ego-motion and scene structure, while continuously refining the gait model. Experiments on synthetic and real image sequences show that the use of the gait model results in more efficient tracking. This is demonstrated by improved matching and retention of features, and a reduction in execution time, when processing video sequences. {\circledC} 2009 Elsevier B.V. All rights reserved.",
keywords = "3-D reconstruction, Efficiency, Ego-motion, Human gait, Tracking",
author = "Huiyu Zhou and Wallace, {Andrew M.} and Green, {Patrick R.}",
year = "2009",
month = "12",
doi = "10.1016/j.sigpro.2009.04.010",
language = "English",
volume = "89",
pages = "2367--2384",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",
number = "12",

}

Efficient tracking and ego-motion recovery using gait analysis. / Zhou, Huiyu; Wallace, Andrew M.; Green, Patrick R.

In: Signal Processing, Vol. 89, No. 12, 12.2009, p. 2367-2384.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient tracking and ego-motion recovery using gait analysis

AU - Zhou, Huiyu

AU - Wallace, Andrew M.

AU - Green, Patrick R.

PY - 2009/12

Y1 - 2009/12

N2 - We present a strategy based on human gait to achieve efficient tracking, recovery of ego-motion and 3-D reconstruction from an image sequence acquired by a single camera attached to a pedestrian. In the first phase, the parameters of the human gait are established by a classical frame-by-frame analysis, using an generalized least squares (GLS) technique. The gait model is non-linear, represented by a truncated Fourier series. In the second phase, this gait model is employed within a "predict-correct" framework using a maximum a posteriori, expectation-maximization (MAP-EM) strategy to obtain robust estimates of the ego-motion and scene structure, while continuously refining the gait model. Experiments on synthetic and real image sequences show that the use of the gait model results in more efficient tracking. This is demonstrated by improved matching and retention of features, and a reduction in execution time, when processing video sequences. © 2009 Elsevier B.V. All rights reserved.

AB - We present a strategy based on human gait to achieve efficient tracking, recovery of ego-motion and 3-D reconstruction from an image sequence acquired by a single camera attached to a pedestrian. In the first phase, the parameters of the human gait are established by a classical frame-by-frame analysis, using an generalized least squares (GLS) technique. The gait model is non-linear, represented by a truncated Fourier series. In the second phase, this gait model is employed within a "predict-correct" framework using a maximum a posteriori, expectation-maximization (MAP-EM) strategy to obtain robust estimates of the ego-motion and scene structure, while continuously refining the gait model. Experiments on synthetic and real image sequences show that the use of the gait model results in more efficient tracking. This is demonstrated by improved matching and retention of features, and a reduction in execution time, when processing video sequences. © 2009 Elsevier B.V. All rights reserved.

KW - 3-D reconstruction

KW - Efficiency

KW - Ego-motion

KW - Human gait

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=67651093942&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2009.04.010

DO - 10.1016/j.sigpro.2009.04.010

M3 - Article

VL - 89

SP - 2367

EP - 2384

JO - Signal Processing

JF - Signal Processing

SN - 0165-1684

IS - 12

ER -