首页 > 论文 > 光学学报 > 39卷 > 10期(pp:1001002--1)

基于颜色空间融合与上下文显著性的红外偏振图像目标增强

Target Enhancement of Infrared Polarization Image Based on Color Space Fusion and Context-Aware Saliency

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在海面目标的军事侦察与导弹制导等领域,前视红外成像发挥着重要作用[1]。但是,在较小的目标背景温差、复杂天气及背景、远距离成像等因素影响下,红外图像中存在目标尺寸较小、信号较弱、对比度低、检测弱小目标较困难的问题[2]。红外偏振度信息是独立于强度信息的另一维度信息[3],利用目标与背景的红外偏振特征差异进行成像,突出目标边缘、轮廓等细节信息(多表现为高频特征),是对红外强度图像中低频信息的有利补充。融合红外辐射强度图像与红外偏振图像信息,有利于在增强目标的同时抑制噪声或背景[4],提高融合图像对目标探测及识别的能力。

Abstract

It is difficult to detect and identify dim and small targets on the sea surface in complex backgrounds, such as low contrast, shore island background, and foreground occlusion. This study proposes a method based on infrared polarization images to detect dim and small targets on the sea surface. Herein, we propose an improved hue-saturation-intensity (HIS) color space fusion algorithm based on the perceived color of the human visual system, which combines infrared polarization information and infrared intensity information of sea surface image. We design a sea surface region segmentation method based on the infrared polarization image, and the sea surface region is segmented as a candidate target enhancement region. The context-aware saliency algorithm is used to calculate the saliency of the sea surface HSI color space fusion image. The sea surface HSI color space fusion image is corrected using the saliency map to obtain a dim and small target enhanced image. The contrast of target and background and the local signal-to-noise ratio are used to evaluate the features of the fusion enhanced image. Results obtained show that in comparison with the existing methods, the proposed method can enhance dim and small targets and suppress the background interference. The evaluation index of the proposed method is higher than that of other existing methods, which provides support for the detection and identification of surface ship targets.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/AOS201939.1001002

所属栏目:大气光学与海洋光学

基金项目:十三五装备预研项目;

收稿日期:2019-03-20

修改稿日期:2019-06-03

网络出版日期:2019-10-01

作者单位    点击查看

宫剑:海军航空大学航空作战勤务学院, 山东 烟台 264000
吕俊伟:海军航空大学航空作战勤务学院, 山东 烟台 264000
刘亮:海军航空大学航空作战勤务学院, 山东 烟台 264000

联系人作者:宫剑(gongjian0811@outlook.com); 吕俊伟(ljwei369@163.com); 刘亮(liul513@126.com);

备注:十三五装备预研项目;

【1】Chen S W, Zhang S X, Yang X G et al. Contour extraction method of FLIR ground standby target. Systems Engineering and Electronics. 39(7), 1647-1652(2017).
陈世伟, 张胜修, 杨小冈 等. 前视红外地面待机目标轮廓提取方法. 系统工程与电子技术. 39(7), 1647-1652(2017).

【2】Zhang S, An B W and Pan S D. Infrared dim target detection based on temporal-spatial non-local similarity. Acta Photonica Sinica. 47(11), (2018).
张素, 安博文, 潘胜达. 基于时空非局部相似性的海上红外弱小目标检测. 光子学报. 47(11), (2018).

【3】Chen W L, Sun Q J, Wang S H et al. Gesture analysis based on the polarization characteristics for the target edge contour. Journal of Infrared and Millimeter Waves. 35(6), 758-765(2016).
陈伟力, 孙秋菊, 王淑华 等. 基于目标边缘轮廓偏振特征的姿态分析初探. 红外与毫米波学报. 35(6), 758-765(2016).

【4】Liu J, Zhang J X and Dai Y. Image enhancement based on multi-guided filtering. Acta Physica Sinica. 67(23), (2018).
刘杰, 张建勋, 代煜. 基于多引导滤波的图像增强算法. 物理学报. 67(23), (2018).

【5】Zhang J H, Zhang Y and Shi Z G. Enhancement of dim targets in a sea background based on long-wave infrared polarisation features. IET Image Processing. 12(11), 2042-2050(2018).

【6】Zhang J H, Zhang Y and Shi Z G. Long-wave infrared polarization feature extraction and image fusion based on the orthogonality difference method. Journal of Electronic Imaging. 27(2), (2018).

【7】Yi W, Zeng Y and Yuan Z. Fusion of GF-3 SAR and optical images based on the nonsubsampled contourlet transform. Acta Optica Sinica. 38(11), (2018).
易维, 曾湧, 原征. 基于NSCT变换的高分三号SAR与光学图像融合. 光学学报. 38(11), (2018).

【8】Zhao Y, Zhang L, Zhang D et al. Object separation by polarimetric and spectral imagery fusion. Computer Vision and Image Understanding. 113(8), 855-866(2009).

【9】Zhou P C, Zhang H K and Xue M G. Polarization image fusion method using color transfer and clustering-based segmentation. Acta Photonica Sinica. 40(1), 149-153(2011).
周浦城, 张洪坤, 薛模根. 基于颜色迁移和聚类分割的偏振图像融合方法. 光子学报. 40(1), 149-153(2011).

【10】Goferman S, Zelnik-Manor L and Tal A. Context-aware saliency detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 34(10), 1915-1926(2012).

【11】Li S, Jin W Q, Xia R Q et al. Radiation correction method for infrared polarization imaging system with front-mounted polarizer. Optics Express. 24(23), 26414-26430(2016).

【12】Wang X, Liang J N, Long H B et al. Experimental study on long wave infrared polarization imaging of typical background and objectives. Infrared and Laser Engineering. 45(7), (2016).
王霞, 梁建安, 龙华宝 等. 典型背景和目标的长波红外偏振成像实验研究. 红外与激光工程. 45(7), (2016).

【13】Xu J and Ge B Z. Simulation and analysis of polarization properties of single particle light scattering. Acta Optica Sinica. 39(4), (2019).
徐捷, 葛宝臻. 单颗粒光散射偏振特性的模拟和分析. 光学学报. 39(4), (2019).

【14】Sun X W, Xu Q S, Cai Y et al. Sea sky line detection based on edge phase encoding in complicated background. Acta Optica Sinica. 37(11), (2017).
孙熊伟, 徐青山, 蔡熠 等. 基于边缘相位编码的复杂背景下海天线检测. 光学学报. 37(11), (2017).

【15】Wang B, Su Y M, Wan L et al. Sea sky line detection method of unmanned surface vehicle based on gradient saliency. Acta Optica Sinica. 36(5), (2016).
王博, 苏玉民, 万磊 等. 基于梯度显著性的水面无人艇的海天线检测方法. 光学学报. 36(5), (2016).

【16】Xu W B, Chen W L and Li J W. Identification method of camouflaged objects based on long-wave infrared hyperspectral polarization characteristic. Spectroscopy and Spectral Analysis. 39(1), 235-240(2019).
徐文斌, 陈伟力, 李军伟. 长波红外高光谱偏振特性的伪装目标识别方法. 光谱学与光谱分析. 39(1), 235-240(2019).

引用该论文

Jian Gong,Junwei Lü,Liang Liu. Target Enhancement of Infrared Polarization Image Based on Color Space Fusion and Context-Aware Saliency[J]. Acta Optica Sinica, 2019, 39(10): 1001002

宫剑,吕俊伟,刘亮. 基于颜色空间融合与上下文显著性的红外偏振图像目标增强[J]. 光学学报, 2019, 39(10): 1001002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF