基于视觉注意机制的海洋监视卫星图像舰船目标检测

许志涛; 刘金国; 龙科慧; 徐东; 周怀得

doi:doi:10.3788/lop50.121001

激光与光电子学进展, 2013, 50 (12): 121001, 网络出版: 2013-11-19

基于视觉注意机制的海洋监视卫星图像舰船目标检测

Ship Targets Detection of Ocean Surveillance Satellite Images Based on Visual Attention

论文大纲

许志涛 ^1,2,*刘金国 ¹龙科慧 ¹徐东 ¹周怀得 ¹

作者单位

¹ 中国科学院长春光学精密机械与物理研究所, 吉林长春 130033

² 中国科学院大学, 北京 100049

摘要

将Itti模型应用于海洋监视卫星图像舰船目标的检测中。简要阐述了Itti模型的算法处理过程，并将视觉注意点的提取转移过程建立为电容阵列充电模型。针对Itti模型的诸多问题，比如所提取的显著区域形状大小固定、小半径检测实时性差、大半径检测包含背景区域多等，提出了改进算法：引入离散矩变换，增强了图像纹理特征响应；采用阈值分割的方法由显著点搜寻显著区域，提高了检测精度和实时性。运用Matlab对算法进行测试，实验结果表明，改进算法所提取的显著区域形状大小基本与目标一致，实时性好，且显著区域包含背景少。与Itti模型相比，改进算法更适合应用于海洋监视卫星图像舰船目标检测提取。

Abstract

An improved Itti′s model is applied on the ship targets detection of ocean surveillance satellite images. We illustrate the algorithm process of Itti′s model, and introduce a capacitor array charging model to describe the extracting and transferring process of the focus of attention. To solve the problems existing in the traditional Itti′s model such as the fixed shape and size of the extracted salient region, the poor real-time detecting performance when the radius of salient region goes too small, and excessive background areas contained in the salient region when the radius is set too large, the algorithm is improved in some aspects in this paper. Firstly, the discrete moment transform is introduced to the algorithm to enhance the response of image texture features. Then, the threshold segmentation method is chosen to extract the salient region with the focus of attention, and thus both the detection accuracy and real-time performance are improved greatly. According to the Matlab test results of the improved algorithm, it is verified that both the shape and size of the salient region are consistent well with the ship targets; the background contained in the salient region is also reduced significantly. Moreover, the improved algorithm has a good real-time performance. It comes to the conclusion that compared with Itti′s model, the improved algorithm is more effective and suitable for the extraction of ship targets detection of ocean satellite images.

参考文献

[1] 唐沐恩, 林挺强, 文贡坚. 遥感图像中舰船检测方法综述[J]. 计算机应用研究, 2011, 28(1): 29-36.

Tang Muen, Lin Tingqiang, Wen Gongjian. Overview of ship detection methods in remote sensing image[J]. Application Research of Computers, 2011, 28(1): 29-36.

[2] 曾文静, 万磊, 张铁栋, 等. 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 Wenjing, Wan Lei, Zhang Tiedong, et al.. Fast detection of weak targets in complex sea-sky background[J]. Optics and Precision Engineering, 2012, 20(2): 403-412.

[3] 隋玉萍, 何昕, 魏仲慧. ROI的海洋监视卫星遥感图像压缩算法[J]. 光学精密工程，2008, 16(7): 1323-1329.

Sui Yuping, He Xin, Wei Zhonghui. A compression algorithm of remote sensing image based on ROI for ocean surveillance satellite[J]. Optics and Precision Engineering, 2008, 16(7): 1323-1329.

[4] 王保云, 张荣, 袁圆, 等. 可见光遥感图像中舰船目标检测的多阶阈值分割方法[J]. 中国科学技术大学学报, 2011, 41(4): 293-298.

Wang Baoyun, Zhang Rong, Yuan Yuan, et al.. A new multi-level threshold segmentation method for ship targets detection in optical remote sensing images[J]. J University of Science and Technology of China, 2011, 41(4): 293-298.

[5] 许军毅, 计科峰, 雷琳, 等. 基于GLRT的光学卫星遥感图像舰船目标检测[J]. 遥感技术与应用, 2012, 27(4): 616-622.

Xu Junyi, Ji Kefeng, Lei Lin, et al.. Ship target detection from optical satellite remote sensing image based on GLRT[J]. Remote Sensing Technology and Application, 2012, 27(4): 616-622.

[6] 陈海亮, 雷琳, 周石林. 一种抗碎云干扰的海上舰船目标检测方法[J]. 计算机工程与科学, 2010, 32(12): 46-49.

Chen Hailiang, Lei Lin, Zhou Shilin. A method of anti-disturbance by ragged clouds for detecting ships on the sea[J]. Computer Engineering & Science, 2010, 32(12): 46-49.

[7] 张建军, 史廷彦, 杨丽春. 基于目标特征的光学遥感图像舰船检测方法[J]. 指挥控制与仿真, 2013, 35(2): 137-144.

Zhang Jianjun, Shi Tingyan, Yang Lichun. A method of ships detection from optical remote sensing images based on feature detection[J]. Command Control & Simulation, 2013, 35(2): 137-144.

[8] 王卫卫, 席灯炎, 杨塨鹏, 等. 利用结构纹理分解的海洋舰船目标检测[J]. 西安电子科技大学学报(自然科学版), 2012, 39(4): 131-137.

Wang Weiwei, Xi Dengyan, Yang Gongpeng, et al.. Warship target detection algorithm based on cartoon-texture decompositon[J]. J Xidian University (Natural Science), 2012, 39(4): 131-137.

[9] 施鹏, 庄连生, 敖欢欢. 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 Liansheng, Ao Huanhuan. Ship detection based on human vision perception[J]. J Atmospheric and Enviromental Optics, 2010, 5(5): 373-379.

[10] Laurent Itti, Christof Kock, Ernst Niebur. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

[11] Laurent Itti, Christof Kock. Computational modeling of visual attention[J]. Nature Reviews Neuroscience, 2001, 2(3): 194-203.

[12] 张立保, 王鹏飞. 高分辨率遥感影像感兴趣区域快速检测[J]. 中国激光, 2012, 39(7): 0714001.

Zhang Libao, Wang Pengfei. Fast detection of regions of interest in high resolution remote sensing image[J]. Chinese J Lasers, 2012, 39(7): 0714001.

[13] 张立保. 基于区域增长的遥感影像视觉显著目标快速检测[J]. 中国激光, 2012, 39(11): 1114001.

Zhang Libao. Fast detection of regions of visual saliency regions in remote sensing image based on region growing[J]. Chinese J Lasers, 2012, 39(11): 1114001.

[14] 赵宏伟, 陈霄, 刘萍萍, 等. 视觉显著目标的自适应分割[J]. 光学精密工程, 2013, 21(2): 531-538.

Zhao Hongwei, Chen Xiao, Liu Pingping, et al.. Adaptive segmentation for visual salient object[J]. Optics and Precision Engineering, 2013, 21(2): 531-538.

[15] C Kock, S Ullman. Shifts in selective visual attention: towards the underlying neural circuitry[J]. Human Neurobiology, 1985, 4(4): 219-227.

[16] John K Tsotsos, Sean M Culhane, Winky Yan Kei Wai, et al.. Modeling visual attention via selective tuning[J]. Artificial Intelligence, 1995, 78(1-2): 507-545.

[17] Vito Di Gesu, Cesare Valenti, Laurent Strinati. Local operators to detect regions of interest[J]. Pattern Recognition Lett, 1997, 18(11-13): 1077-1081.

许志涛, 刘金国, 龙科慧, 徐东, 周怀得. 基于视觉注意机制的海洋监视卫星图像舰船目标检测[J]. 激光与光电子学进展, 2013, 50(12): 121001. 许志涛, 刘金国, 龙科慧, 徐东, 周怀得. Ship Targets Detection of Ocean Surveillance Satellite Images Based on Visual Attention[J]. Laser & Optoelectronics Progress, 2013, 50(12): 121001.

基于视觉注意机制的海洋监视卫星图像舰船目标检测

关于本站 Cookie 的使用提示

全站搜索

基于视觉注意机制的海洋监视卫星图像舰船目标检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索