Interval least-squares filtering with applications to video target tracking

Baohua Li, Changchun Li, Jennie Si, Glen Abousleman

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

3 Citations (Scopus)

Abstract

This paper focuses on applying an interval recursive least-squares (RLS) filter to a video target tracking problem. An RLS filter can be sensitive to variations in filter parameters and disturbance to state observations to make the solutions impractical in practical problems. Specially, in the application of video target tracking using an RLS filter, inaccurate parameters in the affine model may result in noticeable deviations from true target positions to lose the target. To make results robust, each filter parameter and state observation is allowed to vary in an interval. Motivated by this idea, an interval RLS filter is proposed to produce state estimation and prediction by narrow intervals. Simulations show that an interval RLS filter is robust to state and observation noise and variations in filter parameters and state observations, and outperforms an interval Kalman filter. Using an interval RLS filter, a video target tracking algorithm is developed to estimate the target position in each frame. The proposed tracking algorithm using an interval RLS filter is robust to noise in video sequences and error of the affine models, and outperforms that using an RLS filter. Performance evaluations using real-world video sequences are provided to demonstrate effectiveness of the proposed algorithm.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6968
DOIs
StatePublished - 2008
EventThe International Society for Optical Engineering (SPIE) - Orlando, FL, United States
Duration: Mar 17 2008Mar 19 2008

Other

OtherThe International Society for Optical Engineering (SPIE)
CountryUnited States
CityOrlando, FL
Period3/17/083/19/08

Fingerprint

Target tracking
intervals
filters
State estimation
Kalman filters
tracking problem
state estimation
disturbances
deviation
evaluation

Keywords

  • Interval estimation
  • Interval kalman filter
  • Recursive least-squares filter
  • Robust filter
  • Video target tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Li, B., Li, C., Si, J., & Abousleman, G. (2008). Interval least-squares filtering with applications to video target tracking. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6968). [69681D] https://doi.org/10.1117/12.777226

Interval least-squares filtering with applications to video target tracking. / Li, Baohua; Li, Changchun; Si, Jennie; Abousleman, Glen.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6968 2008. 69681D.

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

Li, B, Li, C, Si, J & Abousleman, G 2008, Interval least-squares filtering with applications to video target tracking. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6968, 69681D, The International Society for Optical Engineering (SPIE), Orlando, FL, United States, 3/17/08. https://doi.org/10.1117/12.777226
Li B, Li C, Si J, Abousleman G. Interval least-squares filtering with applications to video target tracking. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6968. 2008. 69681D https://doi.org/10.1117/12.777226
Li, Baohua ; Li, Changchun ; Si, Jennie ; Abousleman, Glen. / Interval least-squares filtering with applications to video target tracking. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6968 2008.
@inproceedings{89e826020d3043beb7bc3e86606220c1,
title = "Interval least-squares filtering with applications to video target tracking",
abstract = "This paper focuses on applying an interval recursive least-squares (RLS) filter to a video target tracking problem. An RLS filter can be sensitive to variations in filter parameters and disturbance to state observations to make the solutions impractical in practical problems. Specially, in the application of video target tracking using an RLS filter, inaccurate parameters in the affine model may result in noticeable deviations from true target positions to lose the target. To make results robust, each filter parameter and state observation is allowed to vary in an interval. Motivated by this idea, an interval RLS filter is proposed to produce state estimation and prediction by narrow intervals. Simulations show that an interval RLS filter is robust to state and observation noise and variations in filter parameters and state observations, and outperforms an interval Kalman filter. Using an interval RLS filter, a video target tracking algorithm is developed to estimate the target position in each frame. The proposed tracking algorithm using an interval RLS filter is robust to noise in video sequences and error of the affine models, and outperforms that using an RLS filter. Performance evaluations using real-world video sequences are provided to demonstrate effectiveness of the proposed algorithm.",
keywords = "Interval estimation, Interval kalman filter, Recursive least-squares filter, Robust filter, Video target tracking",
author = "Baohua Li and Changchun Li and Jennie Si and Glen Abousleman",
year = "2008",
doi = "10.1117/12.777226",
language = "English (US)",
isbn = "9780819471598",
volume = "6968",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Interval least-squares filtering with applications to video target tracking

AU - Li, Baohua

AU - Li, Changchun

AU - Si, Jennie

AU - Abousleman, Glen

PY - 2008

Y1 - 2008

N2 - This paper focuses on applying an interval recursive least-squares (RLS) filter to a video target tracking problem. An RLS filter can be sensitive to variations in filter parameters and disturbance to state observations to make the solutions impractical in practical problems. Specially, in the application of video target tracking using an RLS filter, inaccurate parameters in the affine model may result in noticeable deviations from true target positions to lose the target. To make results robust, each filter parameter and state observation is allowed to vary in an interval. Motivated by this idea, an interval RLS filter is proposed to produce state estimation and prediction by narrow intervals. Simulations show that an interval RLS filter is robust to state and observation noise and variations in filter parameters and state observations, and outperforms an interval Kalman filter. Using an interval RLS filter, a video target tracking algorithm is developed to estimate the target position in each frame. The proposed tracking algorithm using an interval RLS filter is robust to noise in video sequences and error of the affine models, and outperforms that using an RLS filter. Performance evaluations using real-world video sequences are provided to demonstrate effectiveness of the proposed algorithm.

AB - This paper focuses on applying an interval recursive least-squares (RLS) filter to a video target tracking problem. An RLS filter can be sensitive to variations in filter parameters and disturbance to state observations to make the solutions impractical in practical problems. Specially, in the application of video target tracking using an RLS filter, inaccurate parameters in the affine model may result in noticeable deviations from true target positions to lose the target. To make results robust, each filter parameter and state observation is allowed to vary in an interval. Motivated by this idea, an interval RLS filter is proposed to produce state estimation and prediction by narrow intervals. Simulations show that an interval RLS filter is robust to state and observation noise and variations in filter parameters and state observations, and outperforms an interval Kalman filter. Using an interval RLS filter, a video target tracking algorithm is developed to estimate the target position in each frame. The proposed tracking algorithm using an interval RLS filter is robust to noise in video sequences and error of the affine models, and outperforms that using an RLS filter. Performance evaluations using real-world video sequences are provided to demonstrate effectiveness of the proposed algorithm.

KW - Interval estimation

KW - Interval kalman filter

KW - Recursive least-squares filter

KW - Robust filter

KW - Video target tracking

UR - http://www.scopus.com/inward/record.url?scp=44949092693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949092693&partnerID=8YFLogxK

U2 - 10.1117/12.777226

DO - 10.1117/12.777226

M3 - Conference contribution

AN - SCOPUS:44949092693

SN - 9780819471598

VL - 6968

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -