Fast video target tracking in the presence of occlusion and camera motion blur

Changchun Li, Baohua Li, Jennie Si, Glen P. Abousleman

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

2 Citations (Scopus)

Abstract

This paper addresses the issue of tracking partially occluded targets in videos recorded by moving cameras of either handhold or airborne. We propose a fast geometric constraint global motion algorithm to reduce the computation overhead dramatically and the effect caused by outliers from moving targets. A recursive leastsquares filter with forgetting factor is utilized to filter out disturbances and to provide a better estimation of the target's position in the current frame as well as the prediction of the position and velocity for the next frame. The filter uses the affine model and the primary search result to construct a kinetic model. After that, a compact search region is formed based on the prediction to reduce mismatch and improve computation speed. The adaptive template matching is applied to improve the performance further. With these important steps, a tracking algorithm is developed and tested on real video sequences.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6567
DOIs
StatePublished - 2007
EventSignal Processing, Sensor Fusion, and Target Recognition XVI - Orlando, FL, United States
Duration: Apr 9 2007Apr 11 2007

Other

OtherSignal Processing, Sensor Fusion, and Target Recognition XVI
CountryUnited States
CityOrlando, FL
Period4/9/074/11/07

Fingerprint

occlusion
Target tracking
Cameras
cameras
Template matching
IIR filters
filters
predictions
Kinetics
disturbances
templates
kinetics

Keywords

  • Direction-guided search
  • Global motion
  • Kalman filter
  • Occlusion
  • Recursive least-squares filter
  • Target tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Li, C., Li, B., Si, J., & Abousleman, G. P. (2007). Fast video target tracking in the presence of occlusion and camera motion blur. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6567). [656707] https://doi.org/10.1117/12.719837

Fast video target tracking in the presence of occlusion and camera motion blur. / Li, Changchun; Li, Baohua; Si, Jennie; Abousleman, Glen P.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6567 2007. 656707.

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

Li, C, Li, B, Si, J & Abousleman, GP 2007, Fast video target tracking in the presence of occlusion and camera motion blur. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6567, 656707, Signal Processing, Sensor Fusion, and Target Recognition XVI, Orlando, FL, United States, 4/9/07. https://doi.org/10.1117/12.719837
Li C, Li B, Si J, Abousleman GP. Fast video target tracking in the presence of occlusion and camera motion blur. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6567. 2007. 656707 https://doi.org/10.1117/12.719837
Li, Changchun ; Li, Baohua ; Si, Jennie ; Abousleman, Glen P. / Fast video target tracking in the presence of occlusion and camera motion blur. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6567 2007.
@inproceedings{cd7402dceba443b291fe157f6e613303,
title = "Fast video target tracking in the presence of occlusion and camera motion blur",
abstract = "This paper addresses the issue of tracking partially occluded targets in videos recorded by moving cameras of either handhold or airborne. We propose a fast geometric constraint global motion algorithm to reduce the computation overhead dramatically and the effect caused by outliers from moving targets. A recursive leastsquares filter with forgetting factor is utilized to filter out disturbances and to provide a better estimation of the target's position in the current frame as well as the prediction of the position and velocity for the next frame. The filter uses the affine model and the primary search result to construct a kinetic model. After that, a compact search region is formed based on the prediction to reduce mismatch and improve computation speed. The adaptive template matching is applied to improve the performance further. With these important steps, a tracking algorithm is developed and tested on real video sequences.",
keywords = "Direction-guided search, Global motion, Kalman filter, Occlusion, Recursive least-squares filter, Target tracking",
author = "Changchun Li and Baohua Li and Jennie Si and Abousleman, {Glen P.}",
year = "2007",
doi = "10.1117/12.719837",
language = "English (US)",
isbn = "0819466891",
volume = "6567",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Fast video target tracking in the presence of occlusion and camera motion blur

AU - Li, Changchun

AU - Li, Baohua

AU - Si, Jennie

AU - Abousleman, Glen P.

PY - 2007

Y1 - 2007

N2 - This paper addresses the issue of tracking partially occluded targets in videos recorded by moving cameras of either handhold or airborne. We propose a fast geometric constraint global motion algorithm to reduce the computation overhead dramatically and the effect caused by outliers from moving targets. A recursive leastsquares filter with forgetting factor is utilized to filter out disturbances and to provide a better estimation of the target's position in the current frame as well as the prediction of the position and velocity for the next frame. The filter uses the affine model and the primary search result to construct a kinetic model. After that, a compact search region is formed based on the prediction to reduce mismatch and improve computation speed. The adaptive template matching is applied to improve the performance further. With these important steps, a tracking algorithm is developed and tested on real video sequences.

AB - This paper addresses the issue of tracking partially occluded targets in videos recorded by moving cameras of either handhold or airborne. We propose a fast geometric constraint global motion algorithm to reduce the computation overhead dramatically and the effect caused by outliers from moving targets. A recursive leastsquares filter with forgetting factor is utilized to filter out disturbances and to provide a better estimation of the target's position in the current frame as well as the prediction of the position and velocity for the next frame. The filter uses the affine model and the primary search result to construct a kinetic model. After that, a compact search region is formed based on the prediction to reduce mismatch and improve computation speed. The adaptive template matching is applied to improve the performance further. With these important steps, a tracking algorithm is developed and tested on real video sequences.

KW - Direction-guided search

KW - Global motion

KW - Kalman filter

KW - Occlusion

KW - Recursive least-squares filter

KW - Target tracking

UR - http://www.scopus.com/inward/record.url?scp=36049008410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36049008410&partnerID=8YFLogxK

U2 - 10.1117/12.719837

DO - 10.1117/12.719837

M3 - Conference contribution

AN - SCOPUS:36049008410

SN - 0819466891

SN - 9780819466891

VL - 6567

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

ER -