Infrared Target Tracking Using Naïve-Bayes-Nearest-Neighbor

Shujuan GAO; Insuk KIM; Seong Tae JHANG

doi:10.1587/transinf.2014EDL8183

Infrared Target Tracking Using Naïve-Bayes-Nearest-Neighbor

Shujuan GAO, Insuk KIM, Seong Tae JHANG

Full Text Views

0

Cite this

Summary :

Robust yet efficient techniques for detecting and tracking targets in infrared (IR) images are a significant component of automatic target recognition (ATR) systems. In our previous works, we have proposed infrared target detection and tracking systems based on sparse representation method. The proposed infrared target detection and tracking algorithms are based on sparse representation and Bayesian probabilistic techniques, respectively. In this paper, we adopt Naïve Bayes Nearest Neighbor (NBNN) that is an extremely simple, efficient algorithm that requires no training phase. State-of-the-art image classification techniques need a comprehensive learning and training step (e.g., using Boosting, SVM, etc.) In contrast, non-parametric Nearest Neighbor based image classifiers need no training time and they also have other more advantageous properties. Results of tracking in infrared sequences demonstrated that our algorithm is robust to illumination changes, and the tracking algorithm is found to be suitable for real-time tracking of a moving target in infrared sequences and its performance was quite good.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.2 pp.471-474

Publication Date: 2015/02/01

Publicized: 2014/11/18

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDL8183

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Shujuan GAO
  The University of Suwon
Insuk KIM
  The University of Suwon
Seong Tae JHANG
  The University of Suwon

Keyword

target detection, Naïve Bayes Nearest Neighbor, infrared sequences, night vision

Cite this

Copy

Shujuan GAO, Insuk KIM, Seong Tae JHANG, "Infrared Target Tracking Using Naïve-Bayes-Nearest-Neighbor" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 2, pp. 471-474, February 2015, doi: 10.1587/transinf.2014EDL8183.
Abstract: Robust yet efficient techniques for detecting and tracking targets in infrared (IR) images are a significant component of automatic target recognition (ATR) systems. In our previous works, we have proposed infrared target detection and tracking systems based on sparse representation method. The proposed infrared target detection and tracking algorithms are based on sparse representation and Bayesian probabilistic techniques, respectively. In this paper, we adopt Naïve Bayes Nearest Neighbor (NBNN) that is an extremely simple, efficient algorithm that requires no training phase. State-of-the-art image classification techniques need a comprehensive learning and training step (e.g., using Boosting, SVM, etc.) In contrast, non-parametric Nearest Neighbor based image classifiers need no training time and they also have other more advantageous properties. Results of tracking in infrared sequences demonstrated that our algorithm is robust to illumination changes, and the tracking algorithm is found to be suitable for real-time tracking of a moving target in infrared sequences and its performance was quite good.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8183/_p

Copy

@ARTICLE{e98-d_2_471,
author={Shujuan GAO, Insuk KIM, Seong Tae JHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Infrared Target Tracking Using Naïve-Bayes-Nearest-Neighbor},
year={2015},
volume={E98-D},
number={2},
pages={471-474},
abstract={Robust yet efficient techniques for detecting and tracking targets in infrared (IR) images are a significant component of automatic target recognition (ATR) systems. In our previous works, we have proposed infrared target detection and tracking systems based on sparse representation method. The proposed infrared target detection and tracking algorithms are based on sparse representation and Bayesian probabilistic techniques, respectively. In this paper, we adopt Naïve Bayes Nearest Neighbor (NBNN) that is an extremely simple, efficient algorithm that requires no training phase. State-of-the-art image classification techniques need a comprehensive learning and training step (e.g., using Boosting, SVM, etc.) In contrast, non-parametric Nearest Neighbor based image classifiers need no training time and they also have other more advantageous properties. Results of tracking in infrared sequences demonstrated that our algorithm is robust to illumination changes, and the tracking algorithm is found to be suitable for real-time tracking of a moving target in infrared sequences and its performance was quite good.},
keywords={},
doi={10.1587/transinf.2014EDL8183},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Infrared Target Tracking Using Naïve-Bayes-Nearest-Neighbor
T2 - IEICE TRANSACTIONS on Information
SP - 471
EP - 474
AU - Shujuan GAO
AU - Insuk KIM
AU - Seong Tae JHANG
PY - 2015
DO - 10.1587/transinf.2014EDL8183
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2015
AB - Robust yet efficient techniques for detecting and tracking targets in infrared (IR) images are a significant component of automatic target recognition (ATR) systems. In our previous works, we have proposed infrared target detection and tracking systems based on sparse representation method. The proposed infrared target detection and tracking algorithms are based on sparse representation and Bayesian probabilistic techniques, respectively. In this paper, we adopt Naïve Bayes Nearest Neighbor (NBNN) that is an extremely simple, efficient algorithm that requires no training phase. State-of-the-art image classification techniques need a comprehensive learning and training step (e.g., using Boosting, SVM, etc.) In contrast, non-parametric Nearest Neighbor based image classifiers need no training time and they also have other more advantageous properties. Results of tracking in infrared sequences demonstrated that our algorithm is robust to illumination changes, and the tracking algorithm is found to be suitable for real-time tracking of a moving target in infrared sequences and its performance was quite good.
ER -