Classification of hyperspectral remote sensing images using frequency spectrum similarity
Source abstract
Abstract
An algorithm of hyperspectral remote sensing images classification is proposed based on the frequency spectrum of spectral signature. The spectral signature of each pixel in the hyperspectral image is taken as a discrete signal, and the frequency spectrum is obtained using discrete Fourier transform. The discrepancy of frequency spectrum between ground objects’ spectral signatures is visible, thus the difference between frequency spectra of reference and target spectral signature is used to measure the spectral similarity. Canberra distance is introduced to increase the contribution from higher frequency components. Then, the number of harmonics involved in the proposed algorithm is determined after analyzing the frequency spectrum energy cumulative distribution function of ground object. In order to evaluate the performance of the proposed algorithm, two hyperspectral remote sensing images are adopted as experimental data. The proposed algorithm is compared with spectral angle mapper (SAM), spectral information divergence (SID) and Euclidean distance (ED) using the product accuracy, user accuracy, overall accuracy, average accuracy and Kappa coefficient. The results show that the proposed algorithm can be applied to hyperspectral image classification effectively.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Remote-Sensing Image Classification · Remote Sensing and Land Use · Geochemistry and Geologic Mapping
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Kaarna A, Zemcik P, Kalviainen H, et al. Compression of multispectral remote sensing images using clustering and spectral reduction. IEEE T Geosci Remote Sens, 2000, 38(2): 1588–159210.1109/36.841986 ↗
2. Du Q, Fowler J E. Low-complexity principal component analysis for hyperspectral image compression. Int J High Perform Comput Appl, 2008, 22: 438–44810.1177/1094342007088380 ↗
3. Tu T M. Unsupervised signature extraction and separation in hyperspectral images: a noise-adjusted fast independent component analysis approach. Opt Eng, 2000, 39(4): 897–90610.1117/1.602461 ↗
4. Wang J, Chang C I. Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis. IEEE T Geosci Remote Sens, 2006, 44(6): 1586–160010.1109/TGRS.2005.863297 ↗
5. Feng Y, He M Y, Song J H, et al. ICA-based dimensionality reduction and compression of hyperspectral images (in Chinese). J Electron & Inf Technol, 2007, 29(12): 2871–2875
6. Guo B, Gunn S R, Damper R I. Band selection for hyperspectral image classification using mutual information. IEEE Geosci Remote Sens Lett, 2006, 3(4): 522–52610.1109/LGRS.2006.878240 ↗
7. Sotoca J, Pla F. Hyperspectral data selection from mutual information between image bands. LNCS, 2006, 4109: 853–861
8. Marin J A, Brockhaus J, Rolf J, et al. Assessing band selection and image classification techniques on HYDICE hyperspectral data. Systems, Man, and Cybernetics In: IEEE SMC 99 Conference Proceedings, Tokyo, 1999. 1067–107
9. Jimenez L O, Landgrebe D A. Hyperspectral data analysis and supervised feature reduction via projection pursuit. IEEE T Geosci. Remote Sens, 1999, 37(6): 2653–266710.1109/36.803413 ↗
10. Jimenez L O, Morales-Morell A, Creus A. Classification of hyperdimensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks. IEEE T Geosci Remote Sensing, 1999, 37(3): 1360–136610.1109/36.763300 ↗
11. Cawse K A, Damelin S, Plessis L, et al. An investigation of data compression techniques for hyperspectral core imager data. In: Proceedings of the Mathemathics in Industry Study Group, South Africa, 2008. 1–25
12. Banskota A, Wynne R H. Kayastha N. Improving within-genus tree species discrimination using the discrete wavelet transform applied to airborne hyperspectral data. Int J Remote Sens, 2011, 32(13): 3551–356310.1080/01431161003698302 ↗
13. Lee J, Woodyatt A, Berman M. Enhancement of high spectralresolution remote-sensing data by a noise-adjusted principal components transform. IEEE T Geosci Remote Sens, 1990, 28(3): 295–30410.1109/36.54356 ↗
14. Amato U, Cavalli R M, Palombo A, et al. Experimental approach to the selection of the components in the minimum noise fraction. IEEE T Geosci Remote Sens, 2009, 47(1): 153–16010.1109/TGRS.2008.2002953 ↗
15. Frate F D, Licciardi G A, Duca R. Autoassociative neural networks for features reduction of hyperspectral data. In: Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Grenoble, 2009. 1–4
16. Licciardi G A, Frate F D. A comparison of feature extraction methodologies applied on hyperspectral data. In: Proceedings of ESA Hyperspectral Workshop, Frascati, 2010
17. Ding S, Yuan X X, Chen L. Automatic band selection of hyperspectral remote sensing image classification using particle swarm optimization (in Chinese). Acta Geodaetica et Cartographica Sinica, 2010, 39(3): 257–263
18. Du P J, Wang X M, Tan K, et al. Dimensionality reduction and feature extraction from hyperspectral remote sensing imagery based on manifold learning (in Chinese). Geom Inf Sci Wuhan Univ, 2011, 36(2): 148–152
19. Hoffbeck J P, Landgrebe D A. Classification of remote sensing images having high spectral resolution. Remote Sens Environ, 1996, 57(3):119–12610.1016/0034-4257(95)00138-7 ↗
20. Jia X, Riehards J A. Segmented prineipal components transformation for efficient hyperspectral remote sensing image display and classification. IEEE T Geosci Remote Sens, 1999, 37(1): 538–5410.1109/36.739109 ↗
21. Maghsoudi Y, Zoej M J V, Collins M. Using class-based feature selection for the classification of hyperspectral data. Int J Remote Sens, 2011, 32(15): 4311–432610.1080/01431161.2010.486416 ↗
22. Xu W D, Yin Q, Kuang D B. Decision tree classification of hyperspectral image based on discrete wavelet transform (in Chinese). J Remote Sens, 2006, 10(2): 204–210
23. Zhang L P, Li D R. Artificial neural network application in spectral recognition (in Chinese). Spectro Spectral Anal, 1999, 19(2): 158–160
24. Goel P K, Prasher S O, Patel R M, et al. Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn. Comput Electron Agric, 2003, 39(2): 67–9310.1016/S0168-1699(03)00020-6 ↗
25. Camps-Valls G, Gomez-Chova L, Munoz-Mari J. Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection. IEEE T Geosci Remote Sens, 2008, 46(6): 1822–183510.1109/TGRS.2008.916201 ↗
26. Tarabalka Y, Fauvel M, Chanussot J, et al. SVM- and MRF-based method for accurate classification of hyperspectral images. IEEE Geosci Remote Sens Lett, 2010, 7(4): 736–74010.1109/LGRS.2010.2047711 ↗
27. Shang K, Li P J, Cheng T. Land cover classification of hyperspectral data using composite kernel support vector machines (in Chinese). Acta Scientiarum Naturalium Universitatis Pekinensis, 2011, 47 (1): 109–114
28. Tan K, Du P J. Wavelet support vector machines based on reproducing kernel Hilbert Space for hyperspectral remote sensing image classification (in Chinese). J Remote Sens, 2011, 40(2): 142–147
29. Mika S, Rätsch G, Schölkopf B. Invariant feature extraction and classification in kernel spaces. In: Advances in Neural Information Processing Systems, vol 12. Cambridge, MA: MIT Press, 1999
30. Dundar M M, Landgrebe D A. A cost-effective semisupervised classifier approach with kernels. IEEE T Geosci Remote Sens, 2004, 42(1): 264–27010.1109/TGRS.2003.817815 ↗
31. Wang J N, Zheng L F, Tong Q X. The spectral absorption identification model and mineral mapping by imaging spectrometer data (in Chinese). J Remote Sens, 1996, 11(1): 20–3110.3390/rs11010020 ↗
32. Kruse F A, Lefkoff A B, Boardman J W, et al. The spectral image processing system (SIPS)-Interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ, 1993, 44(3): 145–16310.1016/0034-4257(93)90013-N ↗
33. De Carvalho O A, Meneses P R. Spectral correlation mapper (SCM): an improvement on the spectral angle mapper (SAM). In: Proc 9th Airborne Earth Sci Workshop, 2000, JPL Pub. 00-18
34. Pluim J P W, Maintz J B A, Viergever M. Mutual information based registration of medical images: A survey. IEEE T Med Imaging, 2003, 22(8): 986–100410.1109/TMI.2003.815867 ↗
35. Angelopoulou E, Lee S W, Bajcsy R. Spectral gradients: A material descriptor invariant to geometry and incident illumination. In: Proc IEEE Int Confon-Comp Vision. Los Alamitos: IEEE Computer Society Press, 1999. 861–86710.1109/ICCV.1999.790312 ↗
36. Chang C I. An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis. IEEE Trans Inf Theory, 2000, 46(5): 1927–193210.1109/18.857802 ↗
37. Du P J, Fang T, Tang H. Spectral similarity measure based on set theory and its application to hyperspectral RS image retrieval (in Chinese). J Shanghai Jiaotong Univ, 2004, 38(10):182–185
38. Li D R, Zhang J X. The status and analysis methods of image texture (in Chinese). WTUSM Bull Sci Technol, 1993, 3: 30–37
39. Chen S P. Research on Geo-Information Tupu. Beijing: The Commercial Press, 2001
40. Tong Q X, Tang C, Li H G. A creative action:the second experiment of Tengchong aerial remote sensing (in Chinese). Geo-inf Sci, 1999, 1(1): 67–75
41. Xiao P F, Feng X Z, An R, et al. Segmentation of multispectral high-resolution satellite imagery using log Gabor filters. Int J Remote Sens, 2010, 31(2): 1427–143910.1080/01431160903475324 ↗