基于颜色聚类的光学伪装效果评估背景选取方法

doi:10.3969/j.issn.1000-1093.2021.03.018

兵工学报 ›› 2021, Vol. 42 ›› Issue (3): 617-624.doi: 10.3969/j.issn.1000-1093.2021.03.018

基于颜色聚类的光学伪装效果评估背景选取方法

余松林¹，陈玉华¹，何鹄²，王吉军¹，李岩¹

（1.军事科学院国防工程研究院，北京 100850； 2.32184部队，北京 100093）

上线日期:2021-04-26
通讯作者: 王吉军(1977—)，男，高级工程师，硕士 E-mail:13810293603@139.com
作者简介:余松林(1983—)，男，工程师，硕士。E-mail: yslgjj@126.com
基金资助:
装备发展部装备试验鉴定技术研究项目(2000070059)

Background Selection Method of Optical Camouflage Effect Evaluation Based on Color Clustering

YU Songlin¹， CHEN Yuhua¹， HE Hu²， WANG Jijun¹， LI Yan¹

(1.Institute of Defense Engineering，PLA Academy of Military Science，Beijing 100850，China；2.Unit 32184 of PLA，Beijing 100093，China)

Online:2021-04-26

摘要/Abstract

摘要： 在基于可见光图像的单个目标伪装效果评估中，当目标处于反差较大的两种背景交界区域附近时，直接采用8邻域背景选取方法，将会导致评估结果出现较大偏差。针对这一问题，提出一种基于颜色聚类的背景选取方法。通过该方法对8邻域图像进行颜色聚类后，将目标近邻区域中不包含的颜色类从8邻域图像中剔除，再减去目标区域后即为选择的背景。实验结果表明：采用4～6个颜色聚类中心时，可以有效去除无关的背景区域，增强单个目标伪装效果评估的客观性和准确性；新方法对不同目标位置的适用性较强。

关键词: 光学图像, 伪装效果评估, 背景选取, 颜色聚类

Abstract: In the camouflage effect evaluation of single target based on optical images，a large deviation in the evaluation results may be caused by taking the 8-neighborhood image of the target region as the background region when the target is near the boundary between different background areas with large contrast.To solve this problem，a background selection method based on color clustering is proposed.The color classes that are not included in the target neighborhood are removed from the color clustered 8-neighborhood image by the proposed method，and then the target region is subtracted to get the selected background. Experimental results show that the irrelevant background regions can be effectively removed when the image is clustered by 4-6 color cluster centers，so as to enhance the objectivity and accuracy of camouflage effect evaluation. The proposed method is suitable for different target location relationships.

Key words: opticalimage, camouflageeffectevaluation, backgroundselection, colorclustering

中图分类号:

E951.4

余松林，陈玉华，何鹄，王吉军，李岩. 基于颜色聚类的光学伪装效果评估背景选取方法[J]. 兵工学报, 2021, 42(3): 617-624.

YU Songlin， CHEN Yuhua， HE Hu， WANG Jijun， LI Yan. Background Selection Method of Optical Camouflage Effect Evaluation Based on Color Clustering[J]. Acta Armamentarii, 2021, 42(3): 617-624.

参考文献

［1］甘源滢，刘春桐，李洪才，等.光学图像伪装效果评估研究现状及关键问题[J].应用光学，2019，40(6):1050-1058.
GAN Y Y，LIU C T，LI H C，et al. Research status and key issues of optical image camouflage effectiveness evaluation[J].Journal of Applied Optics，2019，40(6):1050-1058.(in Chinese)
[2］胡江华.伪装技术[M].北京:国防工业出版社，2012.
HU J H.Camouflage technology[M].Beijing:National Defense Industry Press，2012.(in Chinese)
[3］初苗，田少辉，余隋怀.基于视觉机制的伪装仿真效果评价方法研究[J].计算机仿真，2014，31(3):60-64.
CHU M，TIAN S H，YU S H.Research on simulated camouflage evaluation based on human visual attention mechanism[J].Compu-ter Simulation，2014，31(3):60-64.(in Chinese)
[4］崔宝生，薛士强，姬艳军，等.图像特征的伪装效果评估技术[J].红外与激光工程，2010，39(6):1178-1183.
CUI B S，XUE S Q，JI Y J，et al. Camouflage effectiveness evaluation based on image feature[J].Infrared and Laser Engineering，2010，39(6):1178-1183. (in Chinese)
[5] ZHAO D H，WANG P Y，ZHANG H B，et al.Camouflage effectiveness assessment based on fusion with constant color background[J].Journal of Physics:Conference Series，2018，1060:012009.
[6］邓冠男，贾永鑫，刘乙鑫.基于颜色特征的单主体图像感兴趣区域提取方法[J].东北电力大学学报，2020，40(4):89-94.
DENG G N，JIA Y X，LIU Y X.Method for extracting region of interest in single subject image based on color features[J].Journal of Northeast Electric Power University，2020，40(4):89-94.(in Chinese)
[7］林伟，陈玉华，王吉远，等.基于图像特征与心理感知量的伪装效果评价方法[J].兵工学报，2013，34(4): 412-417.
LIN W，CHEN Y H，WANG J Y，et al.Camouflage assessment method based on image features and psychological perception quantity[J].Acta Armamentarii，2013，34(4):412-417.(in Chinese)
[8］ GONZALEZ R C，WOODS R E.数字图像处理[M].第3版.阮秋琦，阮宇智，译.北京:电子工业出版社，2017.
GONZALEZ R C，WOODS R E.Digital image processing[M].3rd ed.RUAN Q Q，RUAN Y Z，Translated.Beijing:Publishing House of Electronics Industry，2017.(in Chinese)
[9］秦志新.计算机技术在图像形态学处理中的应用探讨[J].普洱学院学报，2019，35(6):24-26.
QIN Z X.Application of computer technology in image morphology processing[J].Journal of Pu'er University， 2019，35(6):24-26.(in Chinese)
[10］马啸，邵利民，徐冠雷，等.基于K均值聚类算法的雾霾天气自动识别[J].舰船电子工程，2018，38(12):124-128.
MA X，SHAO L M，XU G L，et al.Automatic smog weather recognition based on K-means clustering algorithm[J].Ship Electronic Engineering，2018，38(12):124-128.(in Chinese)
[11］曾接贤，王军婷，符祥.K均值聚类分割的多特征图像检索方法[J].计算机工程与应用，2013，49(2):226-230.
ZENG J X，WANG J T，FU X.Multi-feature image retrieval me-thod based on K-means clustering segmentation[J].Computer Engineering and Applications，2013，49(2):226-230.(in Chinese)
[12］张红霞，章银娥.基于Lab空间的K均值聚类彩色图像分割方法[J].赣南师范大学学报，2019，40(6):44-48.
ZHANG H X，ZHANG Y E.Color image segmentation based on K-means clustering in Lab space[J].Journal of Gannan Normal University，2019，40(6):44-48.(in Chinese)
[13］陈强.基于聚类技术的多阈值图像分割技术[J].太赫兹科学与电子信息学报，2018，16(4):715-718.
CHEN Q. Multi-threshold image segmentation based on clustering method[J].Journal of Terahertz Science and Electronic Information Technology，2018，16(4):715-718.(in Chinese)
[14］姜晋冉，盛乐园，成红梅，等.迷彩伪装效果的综合评估[J].阜阳师范学院学报(自然科学版)，2016，33(1):6-10.
JIANG J R，SHENG L Y，CHENG H M，et al.Comprehensive evaluation of camouflage effect[J].Journal of Fuyang Normal University(Natural Science)，2016，33(1):6-10.(in Chinese)
[15］刘统飞.基于高分辨率遥感影像空-谱特征联合的地表覆盖变化检测方法研究[D].西安:西安理工大学，2020.
LIU T F.Research on land cover change detection method based on spatial-spectral feature combination using high resolution remote sensing image[D].Xi'an:Xi'an University of Technology，2020.(in Chinese)

[1]	马世欣，刘春桐，李洪才，王浩，何祯鑫. 基于高光谱图像探测与感知的伪装效果评估方法[J]. 兵工学报, 2019, 40(7): 1485-1494.
[2]	张丽娟，杨进华，苏伟，姜成昊，王晓坤，谭芳. 基于改进的期望值最大化自适应光学图像多帧迭代去卷积算法[J]. 兵工学报, 2014, 35(11): 1765-1773.

基于颜色聚类的光学伪装效果评估背景选取方法

Background Selection Method of Optical Camouflage Effect Evaluation Based on Color Clustering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价