全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

特征点和不变矩结合的遥感图像飞机目标识别

DOI: 10.11834/jig.20140414

Keywords: 飞机目标识别,遥感图像,特征点分布,不变矩

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的传统的飞机目标识别算法一般是通过目标分割,然后提取不变特征进行训练来完成目标的识别。但是,对于实际情况比较复杂的遥感图像飞机目标,至今没有一种适合多种机型的分割识别算法。针对现有识别算法的不足,提出一种基于特征点空间分布、颜色不变矩和Zernike不变矩相结合的遥感图像飞机目标识别算法。方法首先,对预处理后的遥感图像和模板图像进行小波变换,在低分辨率图像下采用圆投影特征进行粗匹配,确定候选目标;粗匹配结束后,提取高分辨率图像的多尺度Harris-Laplace角点,并画出Delaunay三角网,同时提取出颜色不变矩和Zernike不变矩;然后使用欧氏距离作为这3种特征的相似性度量,并和样本图像进行加权匹配;最后选取欧氏距离最小的图像作为最终的识别目标。结果实验结果表明,本文算法飞机检测精度比现有算法高2.2%,飞机识别精度比现有算法高1.4%10.4%。该算法能从遥感图像中精确识别出十大飞机目标,并对背景、噪声、视角变化等多种干扰具有良好的鲁棒性。结论提出了一种基于特征点空间分布、颜色不变矩和Zernike不变矩相结合的飞机识别算法,该算法使用了图像的多种信息,包括特征点和不变矩,有效地克服了使用单一特征无法描述多种信息的不足。实验结果表明,本文采用基于特征点和不变矩的飞机识别算法比其他算法具有更强的抗干扰能力和识别精度。

References

[1]  Zhu X F, Ma C W. The study of combined invariants optimization method on aircraft recognition[C]//Symposium on Photonics and Optoelectronics. Wuhan, China: IEEE Press, 2011: 1-4.[DOI:10.1109/SOPO.2011.5780562]
[2]  Li Wei, Xiang S M, Wang H B, et al. Robust airplane detection in satellite images[C]//Proceedings of 18th International Conference on Image Processing. Brussels, Belgium: IEEE Press, 2011: 2821-2824.[DOI:10.1109/ICIP.2011.6116259]
[3]  Hsieh J W, Chen J M, Chuang C H, et al. Aircraft type recognition in satellite images[J]. IEEE Proceedings on Vision, Image and Signal Processing, 2005, 152(3): 307-315.[DOI:10.1049/ip-vis:20049020]
[4]  Liu G, Sun X, Fu K, et al. Aircraft recognition in high-resolution satellite images using coarse-to-fine shape prior[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 573-577.[DOI:10. 1109/LGRS.2012.2214022]
[5]  Wu H N, Li D J, Wang H W, et al. Research on aircraft object recognition model based on neural networks[C]//Proceedings of International Conference on Computer Science and Electronics Engineering. Hangzhou, China: IEEE Press, 2012: 160-163.[DOI:10.1109/ICCSEE.2012.330]
[6]  Fang Z X, Yao G Q, Zhang Y N. Target recognition of aircraft based on moment invariants and BP neural network[C]//Proceedings of World Automation Congress. Beijing, China: IEEE Press, 2012: 1-5.
[7]  Wang D H, He X, Wei Z H, et al. A method of aircraft image target recognition based on modified PCA features and SVM[C]//Proceedings of the 9th International Conference on Electronic Measurement & Instruments. Beijing, China: IEEE Press, 2009: 4177-4181.[DOI:10.1109/IC EMI.2009.5274100]
[8]  Zhang X, Wang Y, Han R P S. Wavelet transform Theory and its application in EMG signal processing[C]//Proceedings of the 7th International Conference on Fuzzy Systems and Knowledge Discovery. Yantai, China: IEEE Press, 2010: 2234-2238.[DOI:10.1109/FSKD.2010.5569532]
[9]  Chen G Y, Xie W F. Invariant pattern recognition using ring-projection and dual-tree complex wavelets[C]//Proceedings of International Conference on Wavelet Analysis and Pattern Recognition. Guilin, China: IEEE Press, 2011: 182-186.[DOI:10.1109/ICWAPR.2011.6014459]
[10]  Li Z Y, Liu H, Xu C. Real-time human tracking based on switching linear dynamic system combined with adaptive Meanshift tracker[C]//Proceedings of the 18th International Conference on Image Processing. Brussels, Belguim: IEEE Press, 2011: 2329-2332.[DOI:10.1109/ICIP.2011.6116106]
[11]  Zhang J Y, Chen Q, Bai X J, et al. An advanced Harris-Laplace feature detector with high repeatability[C]//Proceedings of the 2nd International Congress on Image and Signal Processing. Tianjin, China: IEEE Press, 2009: 1-5.[DOI:10.1109/CISP.2009. 5304598]
[12]  Huang Z C, Chan P P K, Ng W W Y, et al. Content-based image retrieval using color moment and Gabor texture feature[C]//Proceedings of International Conference on Machine Learning and Cybernetics. Qingdao, China: IEEE Press, 2010: 719-724.[DOI:10.1109/ICMLC.2010.55 80566]
[13]  Biswas R, Biswas S. On the fast computation of Zernike moments[C]//2010 IEEE International Symposium on Industrial Electronics. Bari, Italy: IEEE Press, 2010: 1680-1685.[DOI:10.1109/ISIE.2010.5637965]
[14]  Liu N, Yin Y L, Zhang H W. A fingerprint matching algorithm based on Delaunay Triangulation Net[C]//Proceedings of International Conference on Computer and Information Technology. Shanghai, China: IEEE Press, 2005: 591-595.[DOI:10.1109/CIT.2005.9]
[15]  Zhang Z J, Sun Z H. Gray technology of color image based on VC platform[J]. Automation Technology and Application, 2005, 24(1): 61-67.[张志军, 孙志辉. 基于VC平台的彩色图像的灰度化技术[J]. 自动化技术与应用, 2005, 24(1): 61-67.][DOI: 10.3969/j.issn.1003-7241.2005.01.019]
[16]  Wang Y G, Liu H P. Destriping multispectral image of post classification[J]. Remote Sensing Technology and Application, 2007, 22(3): 449-454.[王永刚, 刘慧平. 遥感分类图像条带噪声的去除[J]. 遥感技术与应用, 2007, 22(3): 449-454.][DOI: 10.3969/j.issn.1004-0323. 2007.03.025]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133