基于视觉感知机理的舰船目标检测

大气与环境光学学报 ›› 2010, Vol. 5 ›› Issue (5): 373-379.

基于视觉感知机理的舰船目标检测

施鹏，庄连生，敖欢欢，俞能海

(中国科学技术大学电子工程与信息科学系, 安徽合肥 230027 )

收稿日期:2010-04-07 出版日期:2010-09-28 发布日期:2010-09-14
通讯作者: 施鹏(1985-)，男，安徽省芜湖市人，研究生，主要研究方向为图像处理、遥感技术、模式识别、软件设计。 E-mail:ynh@ustc.edu.cn
作者简介:施鹏(1985-)，男，安徽省芜湖市人，研究生，主要研究方向为图像处理、遥感技术、模式识别、软件设计。
基金资助:
国家863计划资助

Ship Detection Based on Human Vision Perception

SHI Peng, ZHUANG Lian-sheng, AO Huan-huan，YU Neng-hai

(Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China)

Received:2010-04-07 Published:2010-09-28 Online:2010-09-14

摘要/Abstract

摘要：

提出了一种基于视觉感知机理的光学遥感图像舰船目标检测的算法。该算法的核心思想在于设计并利用一组Gabor滤波器组来模拟人眼的视觉特性对基于可见光的遥感图像进行处理，从而达到对复杂海况背景抑制并对较暗舰船目标增强的目的。同时，该算法融合了海陆分割、云判处理等子模块，并充分考虑了人眼视觉的底层特性，从颜色、纹理、形态等各个角度进行疑似目标的筛选与剔除，得到最终的检测结果。实验结果显示，该算法具有较高的检测率和较强的鲁棒性，针对各类海况（包含暗舰船目标的情况）平均检测率达到85%以上，高于传统算法的51.3%。

关键词: 遥感, 舰船检测, Garbor滤波器组, 人眼视觉

Abstract:

A ship detection algorithm based on human vision perception is proposed. The key idea is using designed Gabor filters to simulate human vision perception for dealing with visible images, in order to reduce the negative influence of complex sea surface background and enhance the dark ship target. This algorithm includes several models to realize the separating of land and sea areas, the wiping of the cloud and the reduction of false alarms ratio using color, texture and morphologic characters. Experiment results show that the algorithm can effectively detect the ship targets in the complex sea environment, especially for dark ships, and the missed alarms ratio and false alarms ratio are very low, the ship target detection probability can be as high as 85%, higher than the 51.3% in traditional algorithm.

Key words: remote sensing, ship detection, Gabor filters, human vision perception

中图分类号:

TP79

施鹏庄连生敖欢欢俞能海. 基于视觉感知机理的舰船目标检测[J]. 大气与环境光学学报, 2010, 5(5): 373-379.

SHI Peng, ZHUANG Lian-Sheng, AO Huan-Huan, YU Neng-Hai. Ship Detection Based on Human Vision Perception[J]. Journal of Atmospheric and Environmental Optics, 2010, 5(5): 373-379.

参考文献

[1] Hajduch G, Leilde P, Kerbaol V. Ship detection on Envisat ASAR data: results, limitations and perspectives [C]. Proceedings of SEASAR 2006, 2006, 1: 23-26.
[2] Xiao Liping, Cao Ju, Gao Xiaoying. Detection for ship in complicated background of sea and land [J]. Opto-Electronic Engineering, 2007, 34(6): 6-10(in Chinese).
肖利平, 曹炬, 高晓颖. 复杂海地背景下的舰船目标检测 [J]. 光电工程, 2007, 34(6): 6-10.
[3] Chu Zhaoliang, Wang Qinghua, Chen Hailin, et al. Ship auto detection method based on minimum error threshold segmentation [J]. Computer Engineering, 2007, 33(11): 239-242(in Chinese).
储昭亮，王庆华，陈海林，等. 基于极小误差阈值分割的舰船自动检测方法[J]. 计算机工程，2007，33(11)：239-242.
[4] Lu Wei, Yu Xuchu, Ma Yonggang, et al. Research of sea fleet targets detection approach in hyperspectral image [J]. Hydrographic Surveying and Charting, 2005, 25(4): 11-15(in Chinese).
路威, 余旭初, 马永刚, 等. 高光谱遥感影像海上舰船目标检测算法的研究 [J]. 海洋测绘, 2005, 25(4): 11-15.
[5] Hu Junhua, Xu Shoushi, Chen Hailin, et al. Detection of ships in harbor in remote sensing image based on local self-similarity [J]. Journal of Image and Graphics, 2009, 14(4): 32-38(in Chinese).
胡俊华, 徐守时, 陈海林, 等. 基于局部自相似性的遥感图像港口舰船检测 [J]. 中国图像图形学报, 2009, 14(4): 32-38.
[6] Zhao Yinghai, Wu Xiuqing, Wen Ningyun，et al. Ship target detection scheme for optical remote sensing images [J]. Opto-Electronic Engineering, 2008, 35(8): 105-109, 126(in Chinese).
赵英海, 吴秀清, 闻凌云, 等. 可见光遥感图像中舰船目标检测方法 [J]. 光电工程, 2008, 35(8): 105-109, 126.
[7] Tian Minghui, Wan Shouhong, Yue Lihua. Ship detection in remote sensing images with complex sea surface background [J]. Journal of Chinese Computer Systems, 2008, 29(11): 196-200(in Chinese).
田明辉, 万寿红, 岳丽华遥感图像中复杂海面背景下的海上舰船检测 [J]. 小型微型计算机系统 2008, 29(11): 196-200.
[8] Jiang Yunhui, Chen Huaixin. Ship detection method based on wavelet directional filter in cloudy remote sensing images [J]. Telecommunication Engineering, 2008, 48(1): 90-93(in Chinese).
蒋运辉, 陈怀新. 基于小波方向滤波的有云层遥感图像舰船检测方法 [J]. 电讯技术, 2008, 48(1): 90-93.
[9] Kamarainen J K, Kyrki V, Kälviäinen H. Invariance properties of Gabor filter-based features-overview and applications [C]. IEEE Transactions on Image Processing, 2006, 15(5): 1088-1099.
[10] Movellan J R. Tutorial on Gabor Filters [M/OL]. [2009-09-07] http://mplab.ucsd.edu/wordpress/tutorials/gabor.pdf.
[11] Moreno P, Bernardino A, José Santos-Victor. Gabor Parameter Selection for Local Feature Detection [C]. Proc. of the 2nd IBPRIA, 2005.
[12] Zhao Yingnan, Meng Fanbing, Jing Zhong. Research on design of Gabor Kernels’ windows [J]. Computer Science, 2009, 36(1): 117-119(in Chinese).
赵英男, 孟凡斌, 金忠. Gabor 核函数窗的设置研究 [J]. 计算机科学, 2009, 36(1): 117-119.
[13] Zhao Yingnan, Yang Jingyu, Meng Xianquan. A practical design for parameters of Gaobr filters [J]. Computer Engineering, 2006, 32(19): 179-181(in Chinese).
赵英男, 杨静宇, 孟宪权. 一种实用的Gabor 滤波器组参数设置方法 [J]. 计算机工程, 2006, 32(19): 179-181.
[14] Hao Y L, Shang Guan W, Zhu Y, et al. Contented-based satellite cloud image processing and information retrieval [C]. Lecture Notes in Computer Science, 2007, 4688: 767-776. [15] Haralick R M. Statiscal and structured approaches to texture [C]. Proc. of the IEEE, 1979, 67(5): 786-804.