This paper proposes an on-line rigid object tracking framework via discriminative object appearance modeling and learning. Strong classifiers are combined with 2D scale-rotation invariant local features to treat tracking as a keypoint matching problem. For on-line boosting, we correspond a Gaussian mixture model (GMM) to each weak classifier and propose a GMM-based classifying mechanism. Meanwhile, self-organizing theory is applied to perform automatic clustering for sequential updating. Benefiting from the invariance of the SURF feature and the proposed on-line classifying technique, we can easily find reliable matching pairs and thus perform accurate and stable tracking. Experiments show that the proposed method achieves better performance than previously reported trackers.
Quan MIAO
National Computer Network Emergency Response Technical Team/Coordination Center of China
Chenbo SHI
Tsinghua University
Long MENG
Shandong Mingjia Technology Limited Company
Guang CHENG
National Computer Network Emergency Response Technical Team/Coordination Center of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Quan MIAO, Chenbo SHI, Long MENG, Guang CHENG, "On-Line Rigid Object Tracking via Discriminative Feature Classification" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 11, pp. 2824-2827, November 2016, doi: 10.1587/transinf.2016EDL8098.
Abstract: This paper proposes an on-line rigid object tracking framework via discriminative object appearance modeling and learning. Strong classifiers are combined with 2D scale-rotation invariant local features to treat tracking as a keypoint matching problem. For on-line boosting, we correspond a Gaussian mixture model (GMM) to each weak classifier and propose a GMM-based classifying mechanism. Meanwhile, self-organizing theory is applied to perform automatic clustering for sequential updating. Benefiting from the invariance of the SURF feature and the proposed on-line classifying technique, we can easily find reliable matching pairs and thus perform accurate and stable tracking. Experiments show that the proposed method achieves better performance than previously reported trackers.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8098/_p
Copy
@ARTICLE{e99-d_11_2824,
author={Quan MIAO, Chenbo SHI, Long MENG, Guang CHENG, },
journal={IEICE TRANSACTIONS on Information},
title={On-Line Rigid Object Tracking via Discriminative Feature Classification},
year={2016},
volume={E99-D},
number={11},
pages={2824-2827},
abstract={This paper proposes an on-line rigid object tracking framework via discriminative object appearance modeling and learning. Strong classifiers are combined with 2D scale-rotation invariant local features to treat tracking as a keypoint matching problem. For on-line boosting, we correspond a Gaussian mixture model (GMM) to each weak classifier and propose a GMM-based classifying mechanism. Meanwhile, self-organizing theory is applied to perform automatic clustering for sequential updating. Benefiting from the invariance of the SURF feature and the proposed on-line classifying technique, we can easily find reliable matching pairs and thus perform accurate and stable tracking. Experiments show that the proposed method achieves better performance than previously reported trackers.},
keywords={},
doi={10.1587/transinf.2016EDL8098},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - On-Line Rigid Object Tracking via Discriminative Feature Classification
T2 - IEICE TRANSACTIONS on Information
SP - 2824
EP - 2827
AU - Quan MIAO
AU - Chenbo SHI
AU - Long MENG
AU - Guang CHENG
PY - 2016
DO - 10.1587/transinf.2016EDL8098
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2016
AB - This paper proposes an on-line rigid object tracking framework via discriminative object appearance modeling and learning. Strong classifiers are combined with 2D scale-rotation invariant local features to treat tracking as a keypoint matching problem. For on-line boosting, we correspond a Gaussian mixture model (GMM) to each weak classifier and propose a GMM-based classifying mechanism. Meanwhile, self-organizing theory is applied to perform automatic clustering for sequential updating. Benefiting from the invariance of the SURF feature and the proposed on-line classifying technique, we can easily find reliable matching pairs and thus perform accurate and stable tracking. Experiments show that the proposed method achieves better performance than previously reported trackers.
ER -