首页 > 论文 > 激光与光电子学进展 > 56卷 > 10期(pp:101007--1)

非负矩阵分解在空间目标图像识别中的应用

Application of Non-Negative Matrix Factorization in Space Object Recognition

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

摘要

将非负矩阵分解(NMF)算法应用到空间目标图像识别中,对两种传统NMF算法的迭代规则进行了改进,得到了稀疏NMF算法,并分别在二维(2D)和(2D)2维度应用了这3种算法。在实验室模拟了空间光学环境,获得了多组空间目标缩比模型图像,图像预处理后建立了训练样本库和测试样本库,运用不同NMF算法对训练样本进行了特征基提取,采用最小距离分类器进行了测试样本的分类,各种NMF算法识别率均在78%以上,最高可达90%。实验结果验证了所提算法的有效性,与其他已有的目标图像识别方法相比,具有准确率较高、速度快、资源开销少的优点。

Abstract

In this study, we applies the non-negative matrix factorization (NMF) algorithm to space object image recognition. First, we obtain the sparse NMF algorithm by improving the iterative rules of two traditional NMF algorithms and separately apply the three algorithms to the two-dimension (2D) and (2D)2 dimensions. Then, we simulate the space optical environment and acquire multiple sets of space-object-scaling model images in the laboratory. After image preprocessing, we establish the training and the testing sample databases, and extract the features of the training samples using different NMF algorithms. Finally, the minimum distance classifier is used to classify the testing samples. The results show that the recognition rates of various NMF algorithms are all above 78%, and the maximum is up to 90%. The experimental results confirm the effectiveness of the proposed algorithm. Compared with the existing methods for space object image recognition, the NMF algorithm is advantageous owing to its high accuracy, fast speed and low resource cost.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop56.101007

所属栏目:图像处理

基金项目:中国科学院战略优先研究项目(XDA17040200)

收稿日期:2018-11-27

修改稿日期:2018-12-08

网络出版日期:2018-12-21

作者单位    点击查看

孙静静:中国科学院光电研究院中国科学院计算光学成像技术重点实验室, 北京 100094中国科学院大学, 北京 100049
赵飞:中国科学院光电研究院中国科学院计算光学成像技术重点实验室, 北京 100094

联系人作者:赵飞(zhaofei@aoe.ac.cn); 孙静静(sunjingjing16@mails.ucas.ac.cn);

【1】Zeng X X. Research on recognition method of typical space target based on image[D]. Changsha: National University of Defense Technology, 2015.
曾祥鑫. 基于图像的空间典型目标分类识别方法研究[D]. 长沙: 国防科学技术大学, 2015.

【2】Zhang J, Zhou X D, Zhang S F, et al. Recognition of satellite targets based on combined invariant moments and artificial neural network[J]. Journal of Naval Aeronautical and Astronautical University, 2008, 23(1): 29-32.
张健, 周晓东, 章世锋, 等. 基于组合不变矩与神经网络的卫星目标识别[J]. 海军航空工程学院学报, 2008, 23(1): 29-32.

【3】Zeng W M, Wu Q X, Jiang C S. Recognition method of aerial targets based on combined invariant moments[J]. Electronics Optics & Control, 2009, 16(7): 21-24, 44, 97.
曾万梅, 吴庆宪, 姜长生. 基于组合不变矩特征的空中目标识别方法[J]. 电光与控制, 2009, 16(7): 21-24, 44, 97.
Zeng W M, Wu Q X, Jiang C S. Recognition method of aerial targets based on combined invariant moments[J]. Electronics Optics & Control, 2009, 16(7): 21-24, 44, 97.
曾万梅, 吴庆宪, 姜长生. 基于组合不变矩特征的空中目标识别方法[J]. 电光与控制, 2009, 16(7): 21-24, 44, 97.

【4】Wang X X, Yang Y S, Jing Z L. Spacetarget recognition based on improved kernel FCM[J]. Chinese Space Science and Technology, 2012, 32(2): 35-42.
王晓雪, 杨永胜, 敬忠良. 基于改进核聚类算法的空间目标识别方法[J]. 中国空间科学技术, 2012, 32(2): 35-42.

【5】Jiang F Y, Sun R, Zhang X D, et al. Space target image categorization based on the second representation[J]. Journal of Electronics & Information Technology, 2013, 35(5): 1247-1251.
蒋飞云, 孙锐, 张旭东, 等. 基于二次表示的空间目标图像分类[J]. 电子与信息学报, 2013, 35(5): 1247-1251.

【6】Ma J G, Zhao H Z, Li B G, et al. Space target recognition algorithm based on two-dimensional wavelet transform[J]. Journal of National University of Defense Technology, 2006, 28(1): 57-61.
马君国, 赵宏钟, 李保国, 等. 基于二维小波变换的空间目标识别算法[J]. 国防科技大学学报, 2006, 28(1): 57-61.

【7】An M, Jiang Z G, Xu B. Recognitive method of space visible objects based on BFM algorithm[J]. Systems Engineering and Electronics, 2009, 31(5): 1075-1077.
安萌, 姜志国, 许波. 基于BFM算法的空间有形目标识别方法[J]. 系统工程与电子技术, 2009, 31(5): 1075-1077.

【8】Ren Y M, Zhang Y N, Li Y, et al. A space target recognition method based on compressive sensing[C]∥2011 Sixth International Conference on Image and Graphics, August 12-15, 2011, Hefei, Anhui, China. New York: IEEE, 2011: 582-586.

【9】Cao W M, Feng H, Hu L L, et al. Space target recognition based on biomimetic pattern recognition[C]∥2009 First International Workshop on Database Technology and Applications, April 25-26, 2009, Wuhan, Hubei, China. New York: IEEE, 2009: 64-67.

【10】Lee D D, Seung H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788-791.

【11】Li L, Zhang Y J. A survey on algorithms of non-negative matrix factorization[J]. Acta Electronica Sinica, 2008, 36(4): 737-743.
李乐, 章毓晋. 非负矩阵分解算法综述[J]. 电子学报, 2008, 36(4): 737-743.

【12】Ding M Y. Symmetry based two-dimensional principal component analysis and its application to face recognition[J]. Journal of Computer Applications, 2008, 28(1): 122-124.

【13】Fang W T, Ma P, Cheng Z B, et al. 2-dimensional projective non-negative matrix factorization and its application to face recognition[J]. Acta Automatica Sinica, 2012, 38(9): 1503-1512.
方蔚涛, 马鹏, 成正斌, 等. 二维投影非负矩阵分解算法及其在人脸识别中的应用[J]. 自动化学报, 2012, 38(9): 1503-1512.

【14】Gao H J, Pan C. Face recognition based on (2D)2NMF and its improvement[J]. Journal of Computer Applications, 2007, 27(7): 1660-1662, 1666.
高宏娟, 潘晨. 基于(2D)2NMF及其改进算法的人脸识别[J]. 计算机应用, 2007, 27(7): 1660-1662, 1666.

【15】Li S Z, Hou X W, Zhang H J. Learning spatially localized, parts-based representation[C]∥Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Parttern Recognition, December 8-14, 2001, USA. New York: IEEE, 2001: 207-212.

【16】Hoyer P O. Non-negative matrix factorization with sparseness constraints[J]. The Journal of Machine Learning Research, 2004, 5: 1457-1469.

【17】Wang F, Yang Y W, Tan S, et al. Fault detection method based on sparse non-negative matrix factorization[J]. CIESC Journal, 2015, 66(5): 1798-1805.
王帆, 杨雅伟, 谭帅, 等. 基于稀疏性非负矩阵分解的故障监测方法[J]. 化工学报, 2015, 66(5): 1798-1805.

【18】Xu R, Zhao F, Li H F, et al. Parallel measurement of spectral bidirectional reflectance distribution function of non-resolved space objects in laboratory[J]. Acta Photonica Sinica, 2016, 45(2): 0212002.
徐融, 赵飞, 李怀峰, 等. 非分辨空间目标光谱双向反射分布函数的实验室平行测量[J]. 光子学报, 2016, 45(2): 0212002.

【19】Wang X X. Research on recognition method of space target based on image features[D]. Shanghai: Shanghai Jiao Tong University, 2012: 5-29.
王晓雪. 基于图像特征的空间目标识别方法研究[D]. 上海: 上海交通大学, 2012: 5-19.

【20】Wang M. Automatic recognition of space targets in complex background[D]. Changchun: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, 2017.
王敏. 复杂背景下的空间目标自动识别技术[D]. 长春: 中国科学院长春光学精密机械与物理研究所, 2017.

【21】Gonzalez R C, Woods R E, Eddins S L. Digital image processing using MATLAB[M]. Beijing: Publishing House of Electronics Industry, 2005: 367-368.

引用该论文

Sun Jingjing,Zhao Fei. Application of Non-Negative Matrix Factorization in Space Object Recognition[J]. Laser & Optoelectronics Progress, 2019, 56(10): 101007

孙静静,赵飞. 非负矩阵分解在空间目标图像识别中的应用[J]. 激光与光电子学进展, 2019, 56(10): 101007

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