基于海岸线背景的海面小目标检测方法

周静; 田金文

红外与激光工程, 2005, 34 (4): 486, 网络出版: 2006-05-25

基于海岸线背景的海面小目标检测方法

Method of detecting small target in port-sea background

论文大纲

周静 ^*田金文

作者单位

华中科技大学,图像识别与人工智能研究所,图像信息处理与智能控制教育部重点实验室,湖北,武汉,430074

小目标检测水域分割区域标记区域提取区域填充 Small target detection Water-area segmentation Area mark Area extraction Area filling

摘要

针对海岸线背景下的海面小目标的自动检测问题展开讨论,提出一种目标所在感兴趣区域的自动提取算法,将水域和复杂背景分离,并对分割后的二值图像进行标记,海面区域即水域应该是标记块中面积最大的一块,利用此特征提取出感兴趣区域--水域.对感兴趣区域进行轮廓跟踪后再用原始灰度进行扫描填充,在得到的简单背景下对目标进行局部中值滤波,进而用F-R准则将感兴趣舰船目标检测出来.最后拟利用感兴趣舰船目标区域的方差值计算感兴趣目标出现的置信度估计值,若置信度大于90%,则认为是真目标.实验结果给出了实验处理时间和所识别出的各个目标的置信度,表明了本文算法的有效性.

Abstract

A new method is presented to detect small target in the port-sea background image.The image contains land and water area,and the target is in the water area, so the algorithm of automatic segmenting the area that we are interested in is presented.Firstly the land and water area are divided,then the black-white image which has been segmented is marked and the biggest block is distilled as the water area.Secondly the area＇s contour is scouted and it is filled with the original pixels. A local median median filter is executed to filter the rest bundance background elements.Eventually the real small target can be segmented by the F-R rule.And the experimental result shows that the method is effective

参考文献

[1] . Dim target detection using high order correlation method[J]. IEEE Transactions on Aerospace and Electronic Systems, 1993, 29(3): 841-856.

[2] Gan Wang,Rafael M Inigo,Eugene S McVey. A single-pixel target detection & tracking system[A].IEEE Inter Confer on Pattern Recognition [C]. 1990.99-103.

[3] WANG Tao,NIU Bi-qin,XIANG Jian-yong,et al.A segmentation algorithm of infrared object images in complex back-ground[J].Infrared andLaser Engineering(王涛,牛碧芹,向建勇,等.复杂场景中的红外目标图像分割算法.红外与激光工程),1995,24(1):35-38.

[4] PENG Jia-xiong,ZHOU Wen-lin.Infrared background suppression for segmenting and detecting small target[J].Acta Electronic Sinica (彭嘉雄,周文琳.红外背景抑制与小目标分割检测.电子学报),1999,27(12):47-51.

[5] . A connected component labeling algorithm using the run-length code[J]. Journal of Huazhong University of Science and Technology(张桂林,陈益新,曹伟煊.基于跑长码的连通区域标记算法.华中理工大学学报), 1994, 22(5): 11-13.

[6] . A novel edge-labeled algorithm for simple connected area scan filling[J]. Journal of Air Force Engineering University(Natural Science Edition)(李波,王刚,刘东华,等.基于边界标注的单连通区域扫描线填充新方法.空军工程大学学报(自然科学版)), 1994, 9(4): 294-299.

[7] WANG Yang,ZHENG Qin-bo,ZHANG Jun-ping. Real-time detection of small target in IR grey image based on mathematical morphology[J].Infrared and Laser Engineering(汪洋,郑亲波,张钧屏.基于数学形态学的红外图像小目标检测.红外与激光工程),2003,2(32):28-31.

[8] . An approach of fuzzy set division based on the BAYES decision theory[J]. Chinese Journal of Computers(蔡一兵,蔡金燕,杨士元.一种基于贝叶斯决策理论的模糊集划分方法.计算机学报), 1998, 11: 1054-1056.

[9] . Multifeature fusion based on Fisher discriminant criterion[J]. Computer Engineer(王正群,孙兴华.基于Fisher准则的多特征融合.计算机工程), 2002, 3(28): 41-42.

[10] . A new CFAR detector with greatest option[J]. Journal of Electronics(何友,关键,Herman RohRohling(一种新的最大选择恒虚警检测器.电子科学学刊), 1996, 18(5): 467-472.

周静, 田金文. 基于海岸线背景的海面小目标检测方法[J]. 红外与激光工程, 2005, 34(4): 486. 周静, 田金文. Method of detecting small target in port-sea background[J]. Infrared and Laser Engineering, 2005, 34(4): 486.

基于海岸线背景的海面小目标检测方法

关于本站 Cookie 的使用提示

全站搜索

基于海岸线背景的海面小目标检测方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索