基于粒子群优化的遥感图像聚类研究
|
摘要
遥感技术的发展为人们观测宇宙和探知地球发挥了重要的作用。卫星数字图像为地表观测提供了丰富的观测数据。为了有效地利用遥感数据,将遥感图像的光谱信息转化为用户的类别信息,需要有效的图像分析分类和解译。在遥感图像分类领域,非监督分类过程需要的人工交互较少,仅要求寻找影像上的自然分组(也称为聚类过程)。实现计算机的遥感图像自动聚类是一个热门的具有挑战性的研究领域。随着人工智能各项技术的发展,各种智能模型、算法也应用到遥感图像聚类的探索中,对聚类精度的提高大有益处。
粒子群优化属于群体智能的一种算法,具有很好的自适应自组织能力,以及简单高效的群体位置优化能力,本论文主要针对基于粒子群优化算法的遥感图像聚类研究。鉴于传感器分辨率以及地形复杂等原因,遥感图像往往存在混合像元,为了提高聚类精度,本文提出改进的混合像元最大熵分解方法,对线性和非线性混合端元数据都适用。分解模型除了确定遥感图像端元,还对丰度分布做出估计,为模糊粒子群优化聚类算法提供隶属度划分的依据,避免了硬划分对结果准确性的影响。并且本文引入了量子计算,采用量子比特对粒子群体中的粒子进行编码,用量子旋转门操作更新粒子的状态,从而扩大搜索空间；另外在进化过程中引入由量子非门实现的变异算子,增强种群多样性,避免算法的早熟收敛。
在实验部分,选择LANDSAT多光谱遥感图像,通过主成分分析、小波分解和灰度共生矩阵等方法提取特征向量,分别使用经典粒子群优化算法和本文提出的基于量子计算的模糊粒子群优化算法,对遥感图像进行聚类实验,并对结果进行了多方面的比较。实验表明本文提出的基于量子计算的模糊粒子群优化算法取得了比较好的聚类效果。
The development of remote sensing technology has played an important role for people to discover and observe the earth. Satellite digital images provide abundant observational data to about earth observation. In order to utilize remote sensing data effectively, it is need to transform the spectral information of remote sensing image to the classification information of users. Image analysis, classification and interpretation are needed in the transformation process. In the field of remote sensing image classification, the process of the unsupervised classification namely clustering requires less iteration and only asked to find natural groups of images. It is a challenging research area of remote sensing image automation clustering by computer. With the development of artificial intelligence technology, kinds of intelligent models and algorithms are applied into the exploration of remote sensing image clustering, which improve the accuracy of clustering a lot.
Particle swarm optimization is one of the swarm intelligence algorithms, which has good adaptive self-organization, simple and efficient optimization capacity of location of groups. This thesis mainly focuses on the remote sensing image clustering based on particle swarm optimization. There are always mixed pixels in remote sensing image in view of the sensor resolution and complex terrain reasons. In order to overcome this problem to improve the accuracy of clustering, an improved mixed pixel decomposition method based on maximum entropy is proposed and it works well not only for the linear mixed end-data but also the nonlinear ones. The abundance distribution is estimated in this model in addition to the end-data determined. The estimation provides the basis of membership for the fuzzy particle swarm clustering, and it avoids the bad influence of the hard classification to the result. What's more, the quantum computation is introduced in this paper. The particles are encoded with quantum bits and updated with quantum rotating gate. Besides, a mutation operator is realized by quantum not-gate in the evolving process to avoid the premature convergence of the algorithm.
In the section of experiments, the LANDSAT multispectral remote sensing images are adopted. Firstly, eigenvector of image is extracted through the principle component analysis, wavelet decomposition and gray level co-occurrence matrix method. Subsequently, the basic PSO and QFPSO algorithm are applied in the experiment of remote sensing image clustering. Paper compares the result of the two algorithms and it proves that the QFPSO gets the better clustering result.
粒子群优化属于群体智能的一种算法,具有很好的自适应自组织能力,以及简单高效的群体位置优化能力,本论文主要针对基于粒子群优化算法的遥感图像聚类研究。鉴于传感器分辨率以及地形复杂等原因,遥感图像往往存在混合像元,为了提高聚类精度,本文提出改进的混合像元最大熵分解方法,对线性和非线性混合端元数据都适用。分解模型除了确定遥感图像端元,还对丰度分布做出估计,为模糊粒子群优化聚类算法提供隶属度划分的依据,避免了硬划分对结果准确性的影响。并且本文引入了量子计算,采用量子比特对粒子群体中的粒子进行编码,用量子旋转门操作更新粒子的状态,从而扩大搜索空间；另外在进化过程中引入由量子非门实现的变异算子,增强种群多样性,避免算法的早熟收敛。
在实验部分,选择LANDSAT多光谱遥感图像,通过主成分分析、小波分解和灰度共生矩阵等方法提取特征向量,分别使用经典粒子群优化算法和本文提出的基于量子计算的模糊粒子群优化算法,对遥感图像进行聚类实验,并对结果进行了多方面的比较。实验表明本文提出的基于量子计算的模糊粒子群优化算法取得了比较好的聚类效果。
The development of remote sensing technology has played an important role for people to discover and observe the earth. Satellite digital images provide abundant observational data to about earth observation. In order to utilize remote sensing data effectively, it is need to transform the spectral information of remote sensing image to the classification information of users. Image analysis, classification and interpretation are needed in the transformation process. In the field of remote sensing image classification, the process of the unsupervised classification namely clustering requires less iteration and only asked to find natural groups of images. It is a challenging research area of remote sensing image automation clustering by computer. With the development of artificial intelligence technology, kinds of intelligent models and algorithms are applied into the exploration of remote sensing image clustering, which improve the accuracy of clustering a lot.
Particle swarm optimization is one of the swarm intelligence algorithms, which has good adaptive self-organization, simple and efficient optimization capacity of location of groups. This thesis mainly focuses on the remote sensing image clustering based on particle swarm optimization. There are always mixed pixels in remote sensing image in view of the sensor resolution and complex terrain reasons. In order to overcome this problem to improve the accuracy of clustering, an improved mixed pixel decomposition method based on maximum entropy is proposed and it works well not only for the linear mixed end-data but also the nonlinear ones. The abundance distribution is estimated in this model in addition to the end-data determined. The estimation provides the basis of membership for the fuzzy particle swarm clustering, and it avoids the bad influence of the hard classification to the result. What's more, the quantum computation is introduced in this paper. The particles are encoded with quantum bits and updated with quantum rotating gate. Besides, a mutation operator is realized by quantum not-gate in the evolving process to avoid the premature convergence of the algorithm.
In the section of experiments, the LANDSAT multispectral remote sensing images are adopted. Firstly, eigenvector of image is extracted through the principle component analysis, wavelet decomposition and gray level co-occurrence matrix method. Subsequently, the basic PSO and QFPSO algorithm are applied in the experiment of remote sensing image clustering. Paper compares the result of the two algorithms and it proves that the QFPSO gets the better clustering result.
引文
[1]李朝锋,曾生根,许磊.遥感图像智能处理[M].电子工业出版社,2007：1-2.
[2]Jonathan Lee, Ronald C. Aneural network Approach to Cloud Classification[C]. IEEE Transactions on Geosciences and Remote Sensing,1990(05):331-335.
[3]勒文戟,刘政凯.多类别遥感图像的复合分类方法[M].环境遥感,1995,10(4)：288-301.
[4]Jie Yu.etc. Multispectral Remote Sensing Image Classification Based on PSO-BP Considering Texture[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation,2008(6):25-27.
[5]Mauro Barni, Andrea Garzelli, etc. Robust Fuzzy Clustering Algorithm for the Classification of Remote Sensing Images [J]. Geosciences and Remote Sensing Symposium, IGARSS 2000(5):2143-2145.
[6]Sanghoon Lee, Melba M.Crawford. Unsupervised Multistage Image Classification Using Hierarchical Clustering with a Bayesian Similarity Measure [J]. IEEE Transactions on Image Processing,2005,14(3):312-320.
[7]Sanghoon Lee, Melba M.Crawford. Hierarchical Clustering Aprroach for Unsupervised Image Classification of Hyperspectral Data [J]. Geoscience and Remote Sensing Symposium, IEEE International IGARSS 2009:178-181.
[8]Andrea Paoli, Farid Melgani. Clustering of Hyperspectral Images Based on Multiobjective Particle Swarm Optimization[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(12):4175-4188.
[9]Cedric Wemmert, Anne Puissant. Multiresolution Remote Sensing Image Clustering [J]. IEEE Geosciences and Remote Sensing Letters,2009, 6(3):533-537.
[10]杜培军.遥感原理与应用[M].中国矿业大学出版社,2006：157-158.
[11]费圆圆,孙劲光,陶志勇.基于小波分解和灰度共生矩阵的纹理图像检索[M].现代计算机,2007(10)：269.
[12]S.Mallat.. A theory of multiiesolution signal decomposition:The wavelet representation [J]. IEEE Transaction and Pattern Analysis, Machine Intel, PAMI-11,1989(7):674-693.
[13]钱乐祥等.遥感数字影像处理与地理特征提取[M].科学出版社2004：159-160.
[14]阎国倩,赵云升等.混合像元光谱特征影响因子分析[M].光谱学与光谱分析,2009,12(29)：3358-3361.
[15]Charles Ichoku, Arnon Karnilei. A review of mixture modeling techniques for sub-pixel land cover estimation [J]. Remote Sensing Reviews, 2001(13):161-186.
[16]Chen, X.X. and Vierling L. Spectral mixture analyses of hyperspectral data acquired using a tethered balloon[J]. Remote Sensing of Environment,2006, 103(3):338-350.
[17]Somers B, Cools K.etc. Nonlinear hyperspectral mixture analysis for tree cover estimates in orchards [J]. Remote Sensing of Environment,2009, 113(6):1183-1193.
[18]Ichoku C, Karnieli A. A review of mixture modeling techniques for sub-pixel land cover estimation[J]. Remote Sensing Reviews,1996(13):161-186.
[19]R.H.Yuhas, A.F.H.Goetz and J. W. Boardman. Discrimination among semi-arid landscape endmembers using the spectral angle mapper (sam) algorithm[C]. Proc. Summaries 3rd Annu. JPL Airborne Geosciences Workshop,1992(1):147-149.
[20]A. M. Cross, J. J. Settle, and N. A. D. R. T. M. Paivinen. Subpixel measurement of tropical forest cover using avhrr data[J].Remote Sensing,1991(12):1119-1129.
[21]J.J.Settle. On the relationship between spectral unmixing and sub-space projection [J]. IEEE Transaction Geosciences Remote Sensing, 1996(34):1045-1046.
[22]G. M. Foody. Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data[J]. Int. J. Remote Sensing,1996(17): 1317-1340.
[23]G. M. Foody, Thematic mapping from remotely sensed data with neural networks: MLP, RBF, and PNN based approaches[J]. J.Geo-graph System,2001(3): 217-232.
[24]F. van der Meer. Iterative spectral unmixing [J]. Int. J. Remote Sensing,1999(20): 3431-3436.
[25]C.-I. Chang and D. C. Heinz. Constrained subpixel target detection for remotely sensed imagery[J]. IEEE Transaction Geosciences Remote Sensing,2000,38(3): 1144-1159.
[26]D. C. Heinz and C.-I. Chang. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyper-spectral imagery[J]. IEEE Transaction Geosciences Remote Sensing,2001,39(3):529-545.
[27]J. Bayliss, J. A. Gualtieri, and R. Cromp. Analyzing hyperspectral data with independent component analysis [J]. Proc. SPIE,1997(3240):133-143.
[28]C.Y. Liou and K.O.Yang. Unsupervised classification of remote sensing imagery with non-negative matrix factorization[C]. Int. Conf. ONIP,2005:377-382.
[29]M. S. Gebbinck and T. E. Schoulen, J. Desachy, Ed. Decomposition of mixed pixels[J]. Proc. Image and Signal Processing Remote Sensing Ⅱ,1995(2579): 104-115.
[30]S. Chettri and N. Netanyahu. Spectral unmixing of remotely sensed imagery using maximum entropy[J]. Proc. SPIE,1997(2962):55-62.
[31]Eberhart, R. C., J. Kennedy. A new optimizer using particle swarm theory[C]. Proceeding of the Sixth International Symposium on Micro Machine and Human Science, Piscataway Japan,1995:39-43.
[32]Kennedy, J., R. C. Eberhart. Particle swarm optimization[C]. Proceeding of IEEE International Conference on Neural Networks. Perth, WA:IEEE 1995:1942-1948.
[33]Omran, M. G., A. P. Engelbrecht, etc. Particle Swarm Optimization Method for Image Clustering [J]. International Journal on Pattern Recognition and Artificial Intelligence,2005,19(3):297-321.
[34]SHI Y H, EBERHART R C.A modified particle swarm optimizer[C]. Proceedings of the IEEE World Congress on Computational Intelligence, 1998:69-73.
[35]LOVBJERG M, RASMUSSEN T K, KRINK T. Hybrid particle swarm optimizer with breeding and subpopulations[C]. Proceedings of the 3 rd Genetic and Evolution Computation Conference, Sanfrancisco,2001:469-476.
[36]LU Z S, HOU Z R. Particle swarm optimization with adaptive mutation [J]. Acta Electronica Sinica,2004,32(3):416-420.
[37]高海兵,周驰,高亮.广义粒子群优化算法[J].计算机学报2005,28(12)：1980-1987.
[38]CHEN B R, FENG X T. Particle swarm optimization with contracted ranges of both search space and velocity [J]. Journal of Northeastern University,2005, 26(5):488-491.
[39]易文晟.图像语义检索和分类研究[D].博士论文,浙江大学,2007：33.
[40]Zadeh, LA.. Fuzzy sets[J]. Information and Control,1965(8):338-353.
[41]Pawlak, Z.. Rough sets[J]. International Journal of Computer and Information Science,1982:341-356.
[42]Ho,T.B, Funakoshi K. Information retrieval using rough sets[J]. Journal of Japanese Society for Artificial Intelligence,1998,13(3):424-433.
[43]Dubois, D., H. Prade. Rough fuzzy sets and fuzzy rough sets[J]. International Journal of General Systems,1990(17):191-208.
[44]李士勇,李盼池.量子计算与量子优化算法[M].哈尔滨工业大学出版社,2009：13-14.
[2]Jonathan Lee, Ronald C. Aneural network Approach to Cloud Classification[C]. IEEE Transactions on Geosciences and Remote Sensing,1990(05):331-335.
[3]勒文戟,刘政凯.多类别遥感图像的复合分类方法[M].环境遥感,1995,10(4)：288-301.
[4]Jie Yu.etc. Multispectral Remote Sensing Image Classification Based on PSO-BP Considering Texture[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation,2008(6):25-27.
[5]Mauro Barni, Andrea Garzelli, etc. Robust Fuzzy Clustering Algorithm for the Classification of Remote Sensing Images [J]. Geosciences and Remote Sensing Symposium, IGARSS 2000(5):2143-2145.
[6]Sanghoon Lee, Melba M.Crawford. Unsupervised Multistage Image Classification Using Hierarchical Clustering with a Bayesian Similarity Measure [J]. IEEE Transactions on Image Processing,2005,14(3):312-320.
[7]Sanghoon Lee, Melba M.Crawford. Hierarchical Clustering Aprroach for Unsupervised Image Classification of Hyperspectral Data [J]. Geoscience and Remote Sensing Symposium, IEEE International IGARSS 2009:178-181.
[8]Andrea Paoli, Farid Melgani. Clustering of Hyperspectral Images Based on Multiobjective Particle Swarm Optimization[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(12):4175-4188.
[9]Cedric Wemmert, Anne Puissant. Multiresolution Remote Sensing Image Clustering [J]. IEEE Geosciences and Remote Sensing Letters,2009, 6(3):533-537.
[10]杜培军.遥感原理与应用[M].中国矿业大学出版社,2006：157-158.
[11]费圆圆,孙劲光,陶志勇.基于小波分解和灰度共生矩阵的纹理图像检索[M].现代计算机,2007(10)：269.
[12]S.Mallat.. A theory of multiiesolution signal decomposition:The wavelet representation [J]. IEEE Transaction and Pattern Analysis, Machine Intel, PAMI-11,1989(7):674-693.
[13]钱乐祥等.遥感数字影像处理与地理特征提取[M].科学出版社2004：159-160.
[14]阎国倩,赵云升等.混合像元光谱特征影响因子分析[M].光谱学与光谱分析,2009,12(29)：3358-3361.
[15]Charles Ichoku, Arnon Karnilei. A review of mixture modeling techniques for sub-pixel land cover estimation [J]. Remote Sensing Reviews, 2001(13):161-186.
[16]Chen, X.X. and Vierling L. Spectral mixture analyses of hyperspectral data acquired using a tethered balloon[J]. Remote Sensing of Environment,2006, 103(3):338-350.
[17]Somers B, Cools K.etc. Nonlinear hyperspectral mixture analysis for tree cover estimates in orchards [J]. Remote Sensing of Environment,2009, 113(6):1183-1193.
[18]Ichoku C, Karnieli A. A review of mixture modeling techniques for sub-pixel land cover estimation[J]. Remote Sensing Reviews,1996(13):161-186.
[19]R.H.Yuhas, A.F.H.Goetz and J. W. Boardman. Discrimination among semi-arid landscape endmembers using the spectral angle mapper (sam) algorithm[C]. Proc. Summaries 3rd Annu. JPL Airborne Geosciences Workshop,1992(1):147-149.
[20]A. M. Cross, J. J. Settle, and N. A. D. R. T. M. Paivinen. Subpixel measurement of tropical forest cover using avhrr data[J].Remote Sensing,1991(12):1119-1129.
[21]J.J.Settle. On the relationship between spectral unmixing and sub-space projection [J]. IEEE Transaction Geosciences Remote Sensing, 1996(34):1045-1046.
[22]G. M. Foody. Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data[J]. Int. J. Remote Sensing,1996(17): 1317-1340.
[23]G. M. Foody, Thematic mapping from remotely sensed data with neural networks: MLP, RBF, and PNN based approaches[J]. J.Geo-graph System,2001(3): 217-232.
[24]F. van der Meer. Iterative spectral unmixing [J]. Int. J. Remote Sensing,1999(20): 3431-3436.
[25]C.-I. Chang and D. C. Heinz. Constrained subpixel target detection for remotely sensed imagery[J]. IEEE Transaction Geosciences Remote Sensing,2000,38(3): 1144-1159.
[26]D. C. Heinz and C.-I. Chang. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyper-spectral imagery[J]. IEEE Transaction Geosciences Remote Sensing,2001,39(3):529-545.
[27]J. Bayliss, J. A. Gualtieri, and R. Cromp. Analyzing hyperspectral data with independent component analysis [J]. Proc. SPIE,1997(3240):133-143.
[28]C.Y. Liou and K.O.Yang. Unsupervised classification of remote sensing imagery with non-negative matrix factorization[C]. Int. Conf. ONIP,2005:377-382.
[29]M. S. Gebbinck and T. E. Schoulen, J. Desachy, Ed. Decomposition of mixed pixels[J]. Proc. Image and Signal Processing Remote Sensing Ⅱ,1995(2579): 104-115.
[30]S. Chettri and N. Netanyahu. Spectral unmixing of remotely sensed imagery using maximum entropy[J]. Proc. SPIE,1997(2962):55-62.
[31]Eberhart, R. C., J. Kennedy. A new optimizer using particle swarm theory[C]. Proceeding of the Sixth International Symposium on Micro Machine and Human Science, Piscataway Japan,1995:39-43.
[32]Kennedy, J., R. C. Eberhart. Particle swarm optimization[C]. Proceeding of IEEE International Conference on Neural Networks. Perth, WA:IEEE 1995:1942-1948.
[33]Omran, M. G., A. P. Engelbrecht, etc. Particle Swarm Optimization Method for Image Clustering [J]. International Journal on Pattern Recognition and Artificial Intelligence,2005,19(3):297-321.
[34]SHI Y H, EBERHART R C.A modified particle swarm optimizer[C]. Proceedings of the IEEE World Congress on Computational Intelligence, 1998:69-73.
[35]LOVBJERG M, RASMUSSEN T K, KRINK T. Hybrid particle swarm optimizer with breeding and subpopulations[C]. Proceedings of the 3 rd Genetic and Evolution Computation Conference, Sanfrancisco,2001:469-476.
[36]LU Z S, HOU Z R. Particle swarm optimization with adaptive mutation [J]. Acta Electronica Sinica,2004,32(3):416-420.
[37]高海兵,周驰,高亮.广义粒子群优化算法[J].计算机学报2005,28(12)：1980-1987.
[38]CHEN B R, FENG X T. Particle swarm optimization with contracted ranges of both search space and velocity [J]. Journal of Northeastern University,2005, 26(5):488-491.
[39]易文晟.图像语义检索和分类研究[D].博士论文,浙江大学,2007：33.
[40]Zadeh, LA.. Fuzzy sets[J]. Information and Control,1965(8):338-353.
[41]Pawlak, Z.. Rough sets[J]. International Journal of Computer and Information Science,1982:341-356.
[42]Ho,T.B, Funakoshi K. Information retrieval using rough sets[J]. Journal of Japanese Society for Artificial Intelligence,1998,13(3):424-433.
[43]Dubois, D., H. Prade. Rough fuzzy sets and fuzzy rough sets[J]. International Journal of General Systems,1990(17):191-208.
[44]李士勇,李盼池.量子计算与量子优化算法[M].哈尔滨工业大学出版社,2009：13-14.