Low-Rank and Sparse Decomposition Based Frame Difference Method for Small Infrared Target Detection in Coastal Surveillance

Weina ZHOU; Xiangyang XUE; Yun CHEN

doi:10.1587/transinf.2015EDL8186

Low-Rank and Sparse Decomposition Based Frame Difference Method for Small Infrared Target Detection in Coastal Surveillance

Weina ZHOU, Xiangyang XUE, Yun CHEN

Full Text Views

0

Share
Cite this

Summary :

Detecting small infrared targets is a difficult but important task in highly cluttered coastal surveillance. The paper proposed a method called low-rank and sparse decomposition based frame difference to improve the detection performance of a surveillance system. First, the frame difference is used in adjacent frames to detect the candidate object regions which we are most interested in. Then we further exclude clutters by low-rank and sparse matrix recovery. Finally, the targets are extracted from the recovered target component by a local self-adaptive threshold. The experiment results show that, the method could effectively enhance the system's signal-to-clutter ratio gain and background suppression factor, and precisely extract target in highly cluttered coastal scene.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.2 pp.554-557

Publication Date: 2016/02/01

Publicized: 2015/11/11

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDL8186

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Weina ZHOU
  Shanghai Maritime University,Fudan University
Xiangyang XUE
  Fudan University
Yun CHEN
  Fudan University

Keyword

target detection, low-rank, sparse recovery, frame difference

Cite this

Copy

Weina ZHOU, Xiangyang XUE, Yun CHEN, "Low-Rank and Sparse Decomposition Based Frame Difference Method for Small Infrared Target Detection in Coastal Surveillance" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 2, pp. 554-557, February 2016, doi: 10.1587/transinf.2015EDL8186.
Abstract: Detecting small infrared targets is a difficult but important task in highly cluttered coastal surveillance. The paper proposed a method called low-rank and sparse decomposition based frame difference to improve the detection performance of a surveillance system. First, the frame difference is used in adjacent frames to detect the candidate object regions which we are most interested in. Then we further exclude clutters by low-rank and sparse matrix recovery. Finally, the targets are extracted from the recovered target component by a local self-adaptive threshold. The experiment results show that, the method could effectively enhance the system's signal-to-clutter ratio gain and background suppression factor, and precisely extract target in highly cluttered coastal scene.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8186/_p

Copy

@ARTICLE{e99-d_2_554,
author={Weina ZHOU, Xiangyang XUE, Yun CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Low-Rank and Sparse Decomposition Based Frame Difference Method for Small Infrared Target Detection in Coastal Surveillance},
year={2016},
volume={E99-D},
number={2},
pages={554-557},
abstract={Detecting small infrared targets is a difficult but important task in highly cluttered coastal surveillance. The paper proposed a method called low-rank and sparse decomposition based frame difference to improve the detection performance of a surveillance system. First, the frame difference is used in adjacent frames to detect the candidate object regions which we are most interested in. Then we further exclude clutters by low-rank and sparse matrix recovery. Finally, the targets are extracted from the recovered target component by a local self-adaptive threshold. The experiment results show that, the method could effectively enhance the system's signal-to-clutter ratio gain and background suppression factor, and precisely extract target in highly cluttered coastal scene.},
keywords={},
doi={10.1587/transinf.2015EDL8186},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Low-Rank and Sparse Decomposition Based Frame Difference Method for Small Infrared Target Detection in Coastal Surveillance
T2 - IEICE TRANSACTIONS on Information
SP - 554
EP - 557
AU - Weina ZHOU
AU - Xiangyang XUE
AU - Yun CHEN
PY - 2016
DO - 10.1587/transinf.2015EDL8186
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2016
AB - Detecting small infrared targets is a difficult but important task in highly cluttered coastal surveillance. The paper proposed a method called low-rank and sparse decomposition based frame difference to improve the detection performance of a surveillance system. First, the frame difference is used in adjacent frames to detect the candidate object regions which we are most interested in. Then we further exclude clutters by low-rank and sparse matrix recovery. Finally, the targets are extracted from the recovered target component by a local self-adaptive threshold. The experiment results show that, the method could effectively enhance the system's signal-to-clutter ratio gain and background suppression factor, and precisely extract target in highly cluttered coastal scene.
ER -