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...

混合编码差分进化粒子群算法及多示例学习的高光谱影像降维与分类

DOI: 10.11834/jig.20151214

Keywords: 高光谱遥感影像,分类,粒子群优化算法,差分进化算法,多示例学习,混合编码

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的高光谱遥感影像由于其巨大的波段数直接导致信息的高冗余和数据处理的复杂,这不仅带来庞大的计算量,而且会损害分类精度。因此,在对高光谱影像进行处理、分析之前进行降维变得非常必要。分类作为一种重要的获取信息的手段,现有的基于像素点和图斑对象特征辨识地物种类的方法在强噪声干扰训练样本条件下精度偏低,在对象的基础上,将光谱和空间特征相似的对象合并成比其还要大的集合,再按照各个集合的光谱和空间特征进行分类,则不容易受到噪声等因素的干扰。方法提出混合编码差分进化粒子群算法的双种群搜索策略进行降维,基于支持向量机的多示例学习算法作为分类方法,构建封装型降维与分类模型。结果采用AVIRIS影像进行实验,本文算法相比其他相近的分类方法能获得更高的分类精度,达到96.03%,比其他相近方法中最优的像元级的混合编码的分类方法精度高出0.62%。结论在针对强干扰的训练样本条件下,本文算法在降维过程中充分发挥混合编码差分进化算法的优势,分类中训练样本中的噪声可以看做多示例学习中训练包"歧义性"的特定表现形式,有效提高了分类的精度。

References

[1]  Chen Z. Research on high resolution remote sensing image classification technology[D]. Beijing:Institute of Remote Sensing Applications, 2006.[陈忠.高分辨率遥感图像分类技术研究[D].北京:中国科学院遥感应用研究所, 2006.]
[2]  Wang L G, Wei F J. Artificial physics optimization algorithm combined band selection for hyperspectral imagery[J]. Journal of Harbin Institute of Technology, 2013, 45(9):100-106.[王立国,魏芳洁.结合APO算法的高光谱图像波段选择[J].哈尔滨工业大学学报, 2013, 45(9):100-106.]
[3]  Wang L G, Wei F J. Band selection for hyperspectral imagery based on combination of genetic algorithm and ant colony algorithm[J]. Journal of Image and Graphics, 2013, 18(2):235-242.[王立国,魏芳洁.结合遗传算法和蚁群算法的高光谱图像波段选择[J].中国图象图形学报, 2013, 18(2):235-242.] [DOI:10.11834/jig.20130216.]
[4]  Zhao C H, Liu C H. Research and analysis of hyperspectral remote sensing image dimensional reduction[J]. Chinese Space Science and Technology, 2004, 10(5):28-36.[赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空军科学技术, 2004, 10(5):28-36.]
[5]  Ding S, Yuan X X, Chen L. Automatic band selection of hyperspectral remote sensing image classification using particle swarm optimization[J]. Acta Geodaeticaet Cartographica Sinica, 2010, 36(3):257-263.[丁胜,袁修孝,陈黎.粒子群优化算法用于高光谱遥感影像分类的自动波段选择[J].测绘学报, 2010, 36(3):257-263.]
[6]  Eberhart R C, Shi Y H, Kennedy J. Swarm intelligence[M]. San Francisco:Morgan Kaufman Publishers, 2001.
[7]  Wang L, Zeng Y, Chen T. Back propagation neural network with adaptive differential evolution algorithm for time series forecasting[J]. Expert Systems with Applications, 2015, 42(2):855-863.
[8]  Tarabalka Y, Fauvel M, Chanussot J, et al. SVM-and MRF-based method for accurate classification of hyperspectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(4):736-740.
[9]  Du P J, Tan K, Xing X S. Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectral remote sensing image classification[J]. Optics Communications, 2010, 283(24):4978-4984.
[10]  Huang C, Song K, Kim S, et al. Use of a dark object concept and support vector machines to automate forest cover change analysis[J]. Remote Sensing of Environment, 2008, 112(3):970-985.
[11]  Tuia D, Ratle F, Pacifici F, et al. Active learning methods for remote sensing image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(7):2218-2232.
[12]  Qi Z Q, Tian Y J, Shi Y. Multi-instance classification based on regularized multiple criteria linear programming[J]. Neural Computing & Applications, 2013, 23(3-4):857-863.
[13]  Gartner T, Flach P A, Kowalezyk A, et al. Multi-instance kernels[C]//Proceedings of the 19th International Conference on Machine Learning. Sydney, Australia:Institute of Electrical and Electronics Engineers Computer Society, 2002, 179-186.
[14]  He Y C, Wang X Z, Kou Y Z. A binary differential evolution algorithm with hybrid encoding[J]. Journal of Computer Research and Development, 2007, 44(9):1476-1484.[贺毅朝,王熙照,寇应展.一种具有混合编码的二进制差分演化算法[J].计算机研究与发展, 2007, 44(9):1476-1484.]
[15]  Vesterstrom J, Thomsen R. A Comparative Study of Differential Evolution, Particle Swarm Optimization, and Evolutionary Algorithms on Numerical Benchmark Problems[M]. New York:IEEE, 2004.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133