Robust hierarchical multiple hypothesis tracker for multiple object tracking

Mohd Asyraf Zulkifley, Bill Moran, David Rawlinson

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

2 Citations (Scopus)

Abstract

Robust multiple object tracking is the backbone of many higher-level applications such as people counting, behavioral analytics and biomedical imaging. We enhance multiple hypothesis tracker robustness to the problems of split, merge, occlusion and fragment through hierarchical approach. Foreground segmentation and clustered optical flow are used as the first-level tracker input. Only associated track of the first level is fed into the second level with the additional of two virtual measurements. Occlusion predictor is obtained by using the predicted data of each track to distinguish between merge and occlusion. Kalman filter is used to predict and smooth the track's state. Gaussian modelling is used to measure the quality of the hypotheses. Histogram intersection is applied to limit the size expansion of the track. The results show improvement both in terms of accuracy and precision compared to the benchmark trackers [1, 2].

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages405-408
Number of pages4
DOIs
Publication statusPublished - 2012
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL
Duration: 30 Sep 20123 Oct 2012

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CityLake Buena Vista, FL
Period30/9/123/10/12

Fingerprint

Optical flows
Kalman filters
Imaging techniques

Keywords

  • Gaussian modelling
  • Histogram intersection
  • Multiple hypothesis tracker
  • multiple object tracking
  • Occlusion predictor

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Zulkifley, M. A., Moran, B., & Rawlinson, D. (2012). Robust hierarchical multiple hypothesis tracker for multiple object tracking. In Proceedings - International Conference on Image Processing, ICIP (pp. 405-408). [6466881] https://doi.org/10.1109/ICIP.2012.6466881

Robust hierarchical multiple hypothesis tracker for multiple object tracking. / Zulkifley, Mohd Asyraf; Moran, Bill; Rawlinson, David.

Proceedings - International Conference on Image Processing, ICIP. 2012. p. 405-408 6466881.

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

Zulkifley, MA, Moran, B & Rawlinson, D 2012, Robust hierarchical multiple hypothesis tracker for multiple object tracking. in Proceedings - International Conference on Image Processing, ICIP., 6466881, pp. 405-408, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, 30/9/12. https://doi.org/10.1109/ICIP.2012.6466881
Zulkifley MA, Moran B, Rawlinson D. Robust hierarchical multiple hypothesis tracker for multiple object tracking. In Proceedings - International Conference on Image Processing, ICIP. 2012. p. 405-408. 6466881 https://doi.org/10.1109/ICIP.2012.6466881
Zulkifley, Mohd Asyraf ; Moran, Bill ; Rawlinson, David. / Robust hierarchical multiple hypothesis tracker for multiple object tracking. Proceedings - International Conference on Image Processing, ICIP. 2012. pp. 405-408
@inproceedings{c56b768b5e4d4990bd517a2a1de75ae7,
title = "Robust hierarchical multiple hypothesis tracker for multiple object tracking",
abstract = "Robust multiple object tracking is the backbone of many higher-level applications such as people counting, behavioral analytics and biomedical imaging. We enhance multiple hypothesis tracker robustness to the problems of split, merge, occlusion and fragment through hierarchical approach. Foreground segmentation and clustered optical flow are used as the first-level tracker input. Only associated track of the first level is fed into the second level with the additional of two virtual measurements. Occlusion predictor is obtained by using the predicted data of each track to distinguish between merge and occlusion. Kalman filter is used to predict and smooth the track's state. Gaussian modelling is used to measure the quality of the hypotheses. Histogram intersection is applied to limit the size expansion of the track. The results show improvement both in terms of accuracy and precision compared to the benchmark trackers [1, 2].",
keywords = "Gaussian modelling, Histogram intersection, Multiple hypothesis tracker, multiple object tracking, Occlusion predictor",
author = "Zulkifley, {Mohd Asyraf} and Bill Moran and David Rawlinson",
year = "2012",
doi = "10.1109/ICIP.2012.6466881",
language = "English",
isbn = "9781467325332",
pages = "405--408",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Robust hierarchical multiple hypothesis tracker for multiple object tracking

AU - Zulkifley, Mohd Asyraf

AU - Moran, Bill

AU - Rawlinson, David

PY - 2012

Y1 - 2012

N2 - Robust multiple object tracking is the backbone of many higher-level applications such as people counting, behavioral analytics and biomedical imaging. We enhance multiple hypothesis tracker robustness to the problems of split, merge, occlusion and fragment through hierarchical approach. Foreground segmentation and clustered optical flow are used as the first-level tracker input. Only associated track of the first level is fed into the second level with the additional of two virtual measurements. Occlusion predictor is obtained by using the predicted data of each track to distinguish between merge and occlusion. Kalman filter is used to predict and smooth the track's state. Gaussian modelling is used to measure the quality of the hypotheses. Histogram intersection is applied to limit the size expansion of the track. The results show improvement both in terms of accuracy and precision compared to the benchmark trackers [1, 2].

AB - Robust multiple object tracking is the backbone of many higher-level applications such as people counting, behavioral analytics and biomedical imaging. We enhance multiple hypothesis tracker robustness to the problems of split, merge, occlusion and fragment through hierarchical approach. Foreground segmentation and clustered optical flow are used as the first-level tracker input. Only associated track of the first level is fed into the second level with the additional of two virtual measurements. Occlusion predictor is obtained by using the predicted data of each track to distinguish between merge and occlusion. Kalman filter is used to predict and smooth the track's state. Gaussian modelling is used to measure the quality of the hypotheses. Histogram intersection is applied to limit the size expansion of the track. The results show improvement both in terms of accuracy and precision compared to the benchmark trackers [1, 2].

KW - Gaussian modelling

KW - Histogram intersection

KW - Multiple hypothesis tracker

KW - multiple object tracking

KW - Occlusion predictor

UR - http://www.scopus.com/inward/record.url?scp=84875823381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875823381&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6466881

DO - 10.1109/ICIP.2012.6466881

M3 - Conference contribution

SN - 9781467325332

SP - 405

EP - 408

BT - Proceedings - International Conference on Image Processing, ICIP

ER -