Nội dung được dịch bởi AI, chỉ mang tính chất tham khảo
Phân tích đặc trưng dựa trên đối tượng cho dữ liệu siêu phổ sử dụng thuật toán đom đóm
Tóm tắt
Các phương pháp phân loại dựa trên đối tượng có thể cải thiện độ chính xác của phân loại hình ảnh siêu phổ nhờ vào việc tích hợp thông tin không gian vào quy trình phân loại bằng cách gán các pixel lân cận vào cùng một lớp. Trong bài báo này, một phương pháp trích xuất đặc trưng dựa trên đối tượng mới được đề xuất, sử dụng lý thuyết thông tin để giảm sai số Bayes. Bằng cách này, phương pháp đề xuất khai thác các thống kê bậc cao cho việc trích xuất đặc trưng, điều này rất hiệu quả cho dữ liệu không Gaussian như hình ảnh siêu phổ. Tiêu chí cần tối thiểu hóa bao gồm ba thành phần thông tin tương hỗ. Hai thành phần đầu tiên xem xét tính liên quan tối đa và tính dư thừa tối thiểu, trong khi thành phần thứ ba xem xét bản đồ phân đoạn chứa các miền không giao nhau. Để có được bản đồ phân đoạn, chúng tôi áp dụng thuật toán phân cụm đom đóm, mà trong hàm thích nghi của nó đồng thời xem xét khoảng cách trong giữa các mẫu và tâm cụm của chúng, cũng như khoảng cách giữa tâm của hai cụm bất kỳ. Kết quả thực nghiệm của chúng tôi, được thực hiện trên nhiều cảnh siêu phổ khác nhau, cho thấy rằng khung phương pháp đề xuất cho kết quả phân loại tốt hơn so với một số phương pháp trích xuất đặc trưng quang phổ-không gian tiên tiến.
Từ khóa
#Phân loại dựa trên đối tượng #Trích xuất đặc trưng #Hình ảnh siêu phổ #Lý thuyết thông tin #Thuật toán đom đómTài liệu tham khảo
Cheng G, Han J, Zhou P, Guo L (2014) Multi-class geospatial object detection and geographic image classification based on collection of part detectors. ISPRS J Photogramm Remote Sens 98:119–132
Shahdoosti HR, Javaheri N (2019) A new kernel fuzzy based feature extraction method using attraction points. Multidimension Syst Signal Process 30(2):1009–1027
Shahdoosti HR, Javaheri N (2018) A fast algorithm for feature extraction of hyperspectral images using the first order statistics. Multimed Tools Appl 77(18):23633–23650
Camps-Valls G, Gomez-Chova L, Muñoz-Marí J, Vila-Francés J, Calpe-Maravilla J (2006) Composite kernels for hyperspectral image classification. IEEE Geosci Remote Sens Lett 3(1):93–97
Zhou Y, Peng J, Chen CP (2015) Extreme learning machine with composite kernels for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 8(6):2351–2360
Li J, Marpu PR, Plaza A, Bioucas-Dias JM, Benediktsson JA (2013) Generalized composite kernel framework for hyperspectral image classification. IEEE Trans Geosci Remote Sens 51(9):4816–4829
Tarabalka Y, Fauvel M, Chanussot J, Benediktsson JA (2010) SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geosci Remote Sens Lett 7(4):736–740
Li W, Prasad S, Fowler JE (2014) Hyperspectral image classification using Gaussian mixture models and Markov random fields. IEEE Geosci Remote Sens Lett 11(1):153–157
Tarabalka Y, Benediktsson JA, Chanussot J (2009) Spectral–spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans Geosci Remote Sens 47(8):2973–2987
Tarabalka Y, Chanussot J, Benediktsson JA (2010) Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognit 43(7):2367–2379
Fauvel M, Benediktsson JA, Chanussot J, Sveinsson JR (2008) Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans Geosci Remote Sens 46(11):3804–3814
Castaings T, Waske B, Atli Benediktsson J, Chanussot J (2010) On the influence of feature reduction for the classification of hyperspectral images based on the extended morphological profile. Int J Remote Sens 31(22):5921–5939
Yang XS, He X (2013) Firefly algorithm: recent advances and applications. Int J Swarm Intell 1(1):36–50
Zhang J, Cui Z, Wang Y, Wang H, Cai X, Chen J, Li W (2019) A coupling approach with GSO-BFOA for many-objective optimization. IEEE Access 7:120248–120261
Cui Z, Zhang J, Wang Y, Cao Y, Cai X, Zhang W, Chen J (2019) A pigeon-inspired optimization algorithm for many-objective optimization problems. Sci Chin Inf Sci 62(7):070212
Cui Z, Li F, Zhang W (2019) Bat algorithm with principal component analysis. Int J Mach Learn Cybern 10(3):603–622
Wang GG, Cai X, Cui Z, Min G, Chen J (2017) High performance computing for cyber physical social systems by using evolutionary multi-objective optimization algorithm. IEEE Trans Emerg Top Comput. https://doi.org/10.1109/TETC.2017.2703784
Zhang J, Xue F, Cai X, Cui Z, Chang Y, Zhang W, Li W (2019) Privacy protection based on many-objective optimization algorithm. Concurr Comput Pract Exp. https://doi.org/10.1002/cpe.5342
Van der Merwe DW, Engelbrecht AP (2003) Data clustering using particle swarm optimization. In: Evolutionary computation, 2003. CEC’03. The 2003 Congress on, vol 1, pp 215–220. IEEE
Zhang C, Ouyang D, Ning J (2010) An artificial bee colony approach for clustering. Expert Syst Appl 37(7):4761–4767
Yang XS, He X (2013) Bat algorithm: literature review and applications. Int J Bio Inspir Comput 5(3):141–149
Dhivya M, Sundarambal M (2011) Cuckoo search for data gathering in wireless sensor networks. Int J Mob Commun 9(6):642–656
Horng MH (2012) Vector quantization using the firefly algorithm for image compression. Expert Syst Appl 39(1):1078–1091
Banati H, Bajaj M (2011) Fire fly based feature selection approach. IJCSI Int J Comput Sci Issues 8(4):473
Basu B, Mahanti GK (2011) Fire fly and artificial bees colony algorithm for synthesis of scanned and broadside linear array antenna. Prog Electromagn Res 32:169–190
Senthilnath J, Omkar SN, Mani V (2011) Clustering using firefly algorithm: performance study. Swarm Evolut Comput 1(3):164–171
Shapiro L, Stockman G (2002) Computer vision. Prentice-Hall, Englewood Cliffs
Baudat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. Neural Comput 12(10):2385–2404
Kuo BC, Li CH, Yang JM (2009) Kernel nonparametric weighted feature extraction for hyperspectral image classification. IEEE Trans Geosci Remote Sens 47(4):1139–1155
Tuia D, Ratle F, Pozdnoukhov A, Camps-Valls G (2010) Multisource composite kernels for urban-image classification. IEEE Geosci Remote Sens Lett 7(1):88–92
Fang L, Li S, Duan W, Ren J, Benediktsson JA (2015) Classification of hyperspectral images by exploiting spectral–spatial information of superpixel via multiple kernels. IEEE Trans Geosci Remote Sens 53(12):6663–6674
Gan L, Xia J, Du P, Chanussot J (2018) Multiple feature kernel sparse representation classifier for hyperspectral imagery. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2018.2814781
Sun L, Wu Z, Liu J, Xiao L, Wei Z (2015) Supervised spectral–spatial hyperspectral image classification with weighted Markov random fields. IEEE Trans Geosci Remote Sens 53(3):1490–1503
Yu H, Gao L, Li J, Li SS, Zhang B, Benediktsson JA (2016) Spectral-spatial hyperspectral image classification using subspace-based support vector machines and adaptive Markov random fields. Remote Sens 8(4):355
Benediktsson JA, Palmason JA, Sveinsson JR (2005) Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Trans Geosci Remote Sens 43(3):480–491
Plaza A, Martinez P, Plaza J, Perez R (2005) Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations. IEEE Trans Geosci Remote Sens 43(3):466–479
Cavallaro G, Dalla Mura M, Benediktsson JA, Bruzzone L (2015) Extended self-dual attribute profiles for the classification of hyperspectral images. IEEE Geosci Remote Sens Lett 12(8):1690–1694
Kavzoglu T, Colkesen I, Yomralioglu T (2015) Object-based classification with rotation forest ensemble learning algorithm using very-high-resolution WorldView-2 image. Remote Sens Lett 6(11):834–843
Zehtabian A, Ghassemian H (2016) Automatic object-based hyperspectral image classification using complex diffusions and a new distance metric. IEEE Trans Geosci Remote Sens 54(7):4106–4114
Ma L, Li M, Gao Y, Chen T, Ma X, Qu L (2017) A novel wrapper approach for feature selection in object-based image classification using polygon-based cross-validation. IEEE Geosci Remote Sens Lett 14(3):409–413
Yang XS (2008) Nature-inspired metaheuristic algorithms. Luniver Press, UK
Omran M, Engelbrecht AP, Salman A (2005) Particle swarm optimization method for image clustering. Int J Pattern Recognit Artif Intell 19(03):297–321
Cover TM, Thomas JA (1991) Elements of information theory. Wiley, New York
Hellman M, Raviv J (1970) Probability of error, equivocation, and the Chernoff bound. IEEE Trans Inf Theory 16(4):368–372
Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238
Mandal M, Mukhopadhyay A (2013) An improved minimum redundancy maximum relevance approach for feature selection in gene expression data. Proc Technol 10:20–27
Kamandar M, Ghassemian H (2013) Linear feature extraction for hyperspectral images based on information theoretic learning. IEEE Geosci Remote Sens Lett 10(4):702–706
Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076
Sain SR, Scott DW (1996) On locally adaptive density estimation. J Am Stat Assoc 91(436):1525–1534
Hild KE, Erdogmus D, Torkkola K, Principe JC (2006) Feature extraction using information-theoretic learning. IEEE Trans Pattern Anal Mach Intell 28(9):1385–1392
Hyperspectral Remote Sensing Scenes. http://www.ehu.es/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes. Accessed 11 Sep 2017
Shahdoosti HR, Javaheri N (2018) A new hybrid feature extraction method in a dyadic scheme for classification of hyperspectral data. Int J Remote Sens 39(1):101–130
Li W, Liu J, Du Q (2016) Sparse and low-rank graph for discriminant analysis of hyperspectral imagery. IEEE Trans Geosci Remote Sens 54(7):4094–4105
Imani M, Ghassemian H (2017) High-dimensional image data feature extraction by double discriminant embedding. Pattern Anal Appl 20(2):473–484
Kianisarkaleh A, Ghassemian H (2016) Nonparametric feature extraction for classification of hyperspectral images with limited training samples. ISPRS J Photogramm Remote Sens 119:64–78
Imani M, Ghassemian H (2018) Discriminant analysis in morphological feature space for high-dimensional image spatial–spectral classification. J Appl Remote Sens 12(1):016024
Shahdoosti HR, Mirzapour F (2017) Spectral–spatial feature extraction using orthogonal linear discriminant analysis for classification of hyperspectral data. Eur J Remote Sens 50(1):111–124