Fast detection of weak targets in complex sea-sky background

ZENG Wen-jing; WAN Lei; ZHANG Tie-dong; XU Yu-ru

doi:10.3788/OPE.20122002.0403

您当前的位置：

首页 >

文章列表页 >

Fast detection of weak targets in complex sea-sky background

Article | 更新时间：2020-08-12

- Fast detection of weak targets in complex sea-sky background
- Optics and Precision Engineering Vol. 20, Issue 2, Pages: 403-412(2012)
- 作者机构：
  
  哈尔滨工程大学水下机器人技术国防科技重点实验室,黑龙江哈尔滨,150001
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20122002.0403
  CLC： TP391
- Received：01 September 2011，
  
  Revised：11 November 2011，
  
  Published Online：25 February 2012，
  
  Published：25 February 2012
- 稿件说明：
移动端阅览
曾文静, 万磊, 张铁栋, 徐玉如. 复杂海空背景下弱小目标的快速自动检测[J]. 光学精密工程, 2012,20(2): 403-412

ZENG Wen-jing, WAN Lei, ZHANG Tie-dong, XU Yu-ru. Fast detection of weak targets in complex sea-sky background[J]. Editorial Office of Optics and Precision Engineering, 2012,20(2): 403-412
曾文静, 万磊, 张铁栋, 徐玉如. 复杂海空背景下弱小目标的快速自动检测[J]. 光学精密工程, 2012,20(2): 403-412 DOI： 10.3788/OPE.20122002.0403.

ZENG Wen-jing, WAN Lei, ZHANG Tie-dong, XU Yu-ru. Fast detection of weak targets in complex sea-sky background[J]. Editorial Office of Optics and Precision Engineering, 2012,20(2): 403-412 DOI： 10.3788/OPE.20122002.0403.

摘要

针对海面运动载体的可见光序列图像

结合复杂海空背景图像的特点

提出了一种不以检测海天线为前提的弱小目标检测方法。首先

修复图像中被高亮度噪声损毁的部分

如曝光区域或反光区域;接着

量化子图像的区域复杂度以及单元区域上下邻域的灰度差异

据此来判断海天线区域是否存在

若存在则预测海天线区域的位置

否则放弃后续处理;然后

采取Mean-shift分割算法中先滤波后聚类的策略

使用周围纹理抑制滤波来平滑海天线区域

并以像素点和点集为单位对平滑图像进行聚类;最后

将最大面积区域与其他区域分离来二值化图像

完成目标提取。试验证明

该方法能够很好地定位目标信息

单帧处理平均耗时为35 ms

具有准确性和实时性。

Abstract

Without detection of the location of sea-sky line in advance

a feasible method combining with the characters of marine visible images and a complex sea-sky background was proposed to detect distant weak targets in the sequential images from a surface vehicle. Firstly

the images damaged by the noise such as exposures and reflections was mended by the border color of ruined range. Then

the complexity of sub-images and their neighborhood average gray difference were measured to predict the sea-sky region.If the sea-sky region was obtained

the location of the sea-sky should be predicted. Otherwise

the consequent process of images could be eliminated. The strategy of filtering and clustering in Mean-shift segmentation was adopted

in which the surround suppression filter was applied to smoothing the sea-sky region and the smoothed image was clustered by taking the pixels and points as units. Finally

the largest region was assumed to be the background and the rest was taken as target information. The experiment results prove that this method can locate the objects efficiently and the time cost is 35 ms/frame

which is robust and real-time.

关键词

Keywords

references

SUMIMOTO T, KURAMOTO K. Detection of a particular object from environmental images under various conditions . ISIE2000, Cholula, Puebla, Mexico:590-595.[2] HAARST T,VINCENT A,GROEN F. Color as an attribute for automated detection in maritime environments . Proceeding of 12th International Conference on Information Fusion, Seattle, WA, USA, 2009:1679-1686.[3] 李欣,赵亦工,陈冰,等. 基于模糊分类的弱小目标检测方法[J]. 光学精密工程,2009,17(9):2311-2319. LI X,ZHAO Y G,CHEN B,et al.. Approach to dim and small target detection based on fuzzy classification[J]. Opt. Precision Eng.,2009,17(9):2311-2319.(in Chinese)[4] 曹琦,王德江,张齐,等. 红外点目标检测中的能量累积[J]. 光学精密工程,2010,18(3):741-747. CAO Q,WANG D J,ZHANG Q, et al.. Energy accumulation in infrared point target detection[J]. Opt. Precision Eng., 2010,18(3):741-747. (in Chinese)[5] 董宇星,刘伟宁. 基于灰度特性的海天背景小目标检测[J]. 中国光学与应用光学, 2010, 3(3): 253-256. DONG Y X,LIU W N. Detection of sea sky line in complicated background based on grey characteristic[J]. Chinese Journal of Optics and Applied Optics.2010,3(3):253-256. (in Chinese)[6] 黄英东,范宁军,李杰. 一种基于海天线检测的舰船定位方法[J]. 弹箭与制导学报,2008,28(5):286-288. HUANG Y D,FAN N J,LI J. A method of ship position based on sea-sky line detection[J]. Journal of Projecfiles,Rockets,Missiles and Guidance,2008,28(5):286-288. (in Chinese)[7] SERGIY F, DMITRY G. Detection and tracking of marine vehicles in video[J]. IEEE,2008,12:1-4.[8] SANTHALIA G K, NITIN S, SANATYA S. A method to extract future warships in complex sea-sky background which may be virtually invisible .2009 Third Asia International Conference on Modelling & Simulation,2009:533-539.[9] 裴继红,谢维信,刘上乾. 用模糊数学方法识别舰船红外成像目标[J]. 红外与毫米波学报,1995(4):93-100. PEI J H,XIE W X,LIU S Q. Recognition of infrared imaging target of ship with the fuzzy algorithm[J]. Journal of Infrared and Millimeter Waves,1995,14(2):93-100. (in Chinese)[10] 张兆伟,马治国,钱超,等. 红外图像中海天线的提取[J]. 海军工程大学学报,2005(2):97-99. ZHANG ZH W, MA ZH G, QIAN CH, et al.. Locating horizontal region of infrared image[J]. Journal of Naval University of Engineering, 2005(2):97-99. (in Chinese)[11] 许元男,赵远,刘丽萍,等. 应用Renyi熵的显著图生成与目标探测[J]. 光学精密工程,2010,18(3):724-731. XU Y N,ZHAO Y,LIU L P, et al.. Renyi entropy-based saliency map generation and target detection[J]. Opt. Precision Eng., 2010,18(3):724-731. (in Chinese)[12] 杨波,徐光佑. 纹理相似性度量研究及基于纹理特征的图像检索[J]. 自动化学报,2004,30(6):991-998. YANG B, XU G Y. Similarity measurement and retrieval of texture images[J]. Acta Automatica Sinica, 2004,30(6):991-998. (in Chinese)[13] COSMIN G,NICOLAI P,MICHEL A. Westenberg Contour and boundary detection improved by surround suppression of texture edges[J].Image and Vision Computing,2004,22:609-622. [14] GUO S,PRIDMORE T,KONG Y,et al.. An improved hough transform voting scheme utilizing surround suppression[J].Pattern Recognition Letters,2009,30:1241-1252.[15] DORIN C, PETER M. Mean Shift:a robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619. [16] RAY H. Texture-boundary detection in real-time .University of Canterbury,2010:75-76.[17] TAO X, IKER G. An objective evaluation of the Mean Shift-based image segmentation algorithm . Proceedings of IPCV, Las Vegas Nevada, USA,2008:205-211.

Views

232

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-feature cross UAV image detection algorithm under cross-layer attentional interaction

Active learning-clustering-group convolutions network for hyperspectral images classification

Identification and suppression of stars under large range of star field density variation

Target detection using spectral unmixing

Mandibular fracture detection with 3M-YOLOv5 network based on enhanced feature extraction capability

Related Author

ZHANG Zhihao

DU Lixia

HOU Yue

HAO Ziwei

YIN Jie

LIU Jing

LI Yinqiao

LIU Yi

Related Institution

College of Electronic and Information Engineering， Lanzhou Jiaotong University

School of Electronic Engineering， Xidian University

School of Electronic Engineering， Xi’an University of Posts and Telecommunications

Unit of PLA

Jilin Provincial Key Laboratory of Intelligent Wavefront Sensing and Control

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰