Automatic change detection in remotely sensed hyperspectral imagery (Case study: wetlands and waterbodies)

Document Type: Original Article

Authors

School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran

Abstract

Wetlands are one of the important types of ecosystems that play a fundamental role in the environment and
provide significant benefits due to the resources that they contain. Therefore, it is necessary to monitor the
changes in these ecosystems. The alterations in Earth’s ecosystems caused by the natural activities, such as
drought, as well as human activities and population growth has been affecting the wetlands and waterbodies
area. Therefore, for achieving a better detection of these changes over time, it is important to generate
descriptive location maps based on the characteristics of wetlands. Hyperspectral images have shown
potential use in many applications due to their high spectral resolution, and consequently, their high
informative value. This study presents a hybrid procedure for automatic detection of changes in wetlands
using a new approach which can provide more details about the changes with high accuracy. The hybrid
proposed method is based on incorporating chronochrome, Z-score analysis, Otsu algorithm, simplex via
split augmented lagrangian (SISAL), HarsanyiFarrandChang (HFC), Pearson correlation coefficient
(PCC), and support vector machine (SVM) to detect changes using hyperspectral imagery. The proposed
method in the first step, produce a training data for tuning SVM and kernel parameters. The second step,
predicted change areas based on a chronochrome algorithm and binary change map obtained using SVM
classifier. The third step, the amplitude of changes is created by Z-Score analysis and binary change mask.
Finally, the multiple change map is produced based on the estimation of number and extraction of
endmembers and similarity measure. The proposed method evaluated and compared the performances with
other common hyperspectral change detection methods using three real-world datasets of multi-temporal
hyperspectral imagery. The empirical results reveal the superiority of the proposed hybrid method in
extracting the change map with an overall accuracy of nearly 96% and a kappa coefficient of 0.89 while
other hyperspectral change detection methods have the overall accuracy lower than 93% and kappa
coefficient 0.80. In addition, this hybrid method can provide ‘multiple changes’ as well as the magnitude of
extracted changes.

Keywords

Main Subjects


Adar, S., Notesco, G., Brook, A., Livne, I., Rojik, P., Kopackova, V., ... & Ehrler, C. (2011, October). Change detection over Sokolov open-pit mining area, Czech Republic, using multi-temporal HyMAP data (2009-2010). In Image and Signal Processing for Remote Sensing XVII (Vol. 8180, p. 81800T). International Society for Optics and Photonics.
Adar, S., Shkolnisky, Y., & Dor, E. B. (2012, July). New approach for spectral change detection assessment using multistrip airborne hyperspectral data. In Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International (pp. 4966-4969). IEEE.
Ahlqvist, O. (2008). Extending post-classification change detection using semantic similarity metrics to overcome class heterogeneity: A study of 1992 and 2001 US National Land Cover Database changes. Remote Sensing of Environment, 112(3), 1226-1241.
Barrett, E. C. (2013). Introduction to environmental remote sensing. Routledge.
Bioucas-Dias, J. M. (2009, August). A variable splitting augmented Lagrangian approach to linear spectral unmixing. In Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2009. WHISPERS'09. First Workshop on (pp. 1-4). IEEE.
Bovolo, F., & Bruzzone, L. (2015). The time variable in data fusion: A change detection perspective. IEEE Geoscience and Remote Sensing Magazine, 3(3), 8-26.
Bovolo, F., Marchesi, S., & Bruzzone, L. (2012). A framework for automatic and unsupervised detection of multiple changes in multitemporal images. IEEE Transactions on Geoscience and Remote Sensing, 50(6), 2196-2212.
Castellana, L., D’Addabbo, A., & Pasquariello, G. (2007). A composed supervised/unsupervised approach to improve change detection from remote sensing. Pattern Recognition Letters, 28(4), 405-413.
Chang, C. I., & Du, Q. (2004). Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Transactions on geoscience and remote sensing, 42(3), 608-619.
Chan, K. K. Y., & Xu, B. (2013). Perspective on remote sensing change detection of Poyang Lake wetland. Annals of GIS, 19(4), 231-243.
Cheadle, C., Cho-Chung, Y. S., Becker, K. G., & Vawter, M. P. (2003). Application of z-score transformation to Affymetrix data. Applied bioinformatics, 2(4), 209-217.
Datt, B., McVicar, T. R., Van Niel, T. G., Jupp, D. L., & Pearlman, J. S. (2003). Preprocessing EO-1 Hyperion hyperspectral data to support the application of agricultural indexes. IEEE Transactions on Geoscience and Remote Sensing, 41(6), 1246-1259.
Dronova, I., Gong, P., & Wang, L. (2011). Object-based analysis and change detection of major wetland cover types and their classification uncertainty during the low water period at Poyang Lake, China. Remote Sensing of Environment, 115(12), 3220-3236.
Eismann, M. T., Meola, J., & Hardie, R. C. (2008). Hyperspectral change detection in the presenceof diurnal and seasonal variations. IEEE Transactions on Geoscience and Remote Sensing, 46(1), 237-249.
Franklin, S. E., Ahmed, O. S., Wulder, M. A., White, J. C., Hermosilla, T., & Coops, N. C. (2015). Large area mapping of annual land cover dynamics using multitemporal change detection and classification of Landsat time series data. Canadian Journal of Remote Sensing, 41(4), 293-314.
Fröjse, L. (2011). Multitemporal satellite images for urban change detection.
Gaspar, P., Carbonell, J., & Oliveira, J. L. (2012). On the parameter optimization of Support Vector Machines for binary classification. Journal of integrative bioinformatics, 9(3), 33-43.
George, R., Padalia, H., & Kushwaha, S. P. S. (2014). Forest tree species discrimination in western Himalaya using EO-1 Hyperion. International Journal of Applied Earth Observation and Geoinformation, 28, 140–149.
Ghobadi, Y., Pradhan, B., Shafri, H. Z., bin Ahmad, N., & Kabiri, K. (2015). Spatio-temporal remotely sensed data for analysis of the shrinkage and shifting in the Al Hawizeh wetland. Environmental Monitoring and Assessment, 187(1), 1–17. https://doi.org/10.1007/s10661-014-4156-0
Gibbes, C., Southworth, J., & Keys, E. (2009). Wetland conservation: change and fragmentation in Trinidad’s protected areas. Geoforum, 40(1), 91–104.
Gómez, C., White, J. C., & Wulder, M. A. (2016). Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 116, 55–72.
Goodenough, D. G., Dyk, A., Niemann, K. O., Pearlman, J. S., Chen, H., Han, T., … West, C. (2003). Processing Hyperion and ALI for forest classification. IEEE Transactions on Geoscience and Remote Sensing, 41(6), 1321–1331. https://doi.org/10.1109/TGRS.2003.813214
Gu, B., Sheng, V. S., Tay, K. Y., Romano, W., & Li, S. (2017). Cross Validation Through Two-Dimensional Solution Surface for Cost-Sensitive SVM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1103–1121.
Gunawardena, A., Fernando, T., Takeuchi, W., Wickramasinghe, C. H., & Samarakoon, L. (2014). Identification, evaluation and change detection of highly sensitive wetlands in South-Eastern Sri Lanka using ALOS (AVNIR2, PALSAR) and Landsat ETM+ data. In IOP Conference Series: Earth and Environmental Science (Vol. 20, p. 012050). IOP Publishing.
Hasanlou, M., Samadzadegan, F., & Homayouni, S. (2015). SVM-based hyperspectral image classification using intrinsic dimension. Arabian Journal of Geosciences, 8(1), 477–487.
Hasanlou, M., & Seydi, S. T. (2018). Hyperspectral Change Detection: An Experimental Comparative Study. International Journal of Remote Sensing, 1-45.
Hegazy, I. R., & Kaloop, M. R. (2015). Monitoring urban growth and land use change detection with GIS and remote sensing techniques in Daqahlia governorate Egypt. International Journal of Sustainable Built Environment, 4(1), 117–124.
Huang, S., Ramirez, C., Kennedy, K., Mallory, J., Wang, J., & Chu, C. (2017). Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California. GIScience & Remote Sensing, 1–20.
Hughes, M. L., McDowell, P. F., & Marcus, W. A. (2006). Accuracy assessment of georectified aerial photographs: implications for measuring lateral channel movement in a GIS. Geomorphology, 74(1–4), 1–16.
Hussain, M., Chen, D., Cheng, A., Wei, H., & Stanley, D. (2013). Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 80, 91–106.
Jafari, R., & Lewis, M. M. (2012). Arid land characterisation with EO-1 Hyperion hyperspectral data. International Journal of Applied Earth Observation and Geoinformation, 19, 298–307.
Jiang, F., Qi, S., Liao, F., Ding, M., & Wang, Y. (2014). Vulnerability of Siberian crane habitat to water level in Poyang Lake wetland, China. GIScience & Remote Sensing, 51(6), 662–676.
Kayastha, N., Thomas, V., Galbraith, J., & Banskota, A. (2012). Monitoring wetland change using inter-annual landsat time-series data. Wetlands, 32(6), 1149–1162.
Keramitsoglou, I., Stratoulias, D., Fitoka, E., Kontoes, C., & Sifakis, N. (2015). A transferability study of the kernel-based reclassification algorithm for habitat delineation. International Journal of Applied Earth Observation and Geoinformation, 37, 38–47.
Keshava, N. (2003). A survey of spectral unmixing algorithms. Lincoln laboratory journal, 14(1), 55–78.
Khurshid, K. S., Staenz, K., Sun, L., Neville, R., White, H. P., Bannari, A., Champagne, C. M., et al. (2006). Preprocessing of EO-1 Hyperion data. Canadian Journal of Remote Sensing, 32(2), 84–97.
Kumar, L., & Sinha, P. (2014). Mapping salt-marsh land-cover vegetation using high-spatial and hyperspectral satellite data to assist wetland inventory. GIScience & Remote Sensing, 51(5), 483–497.
Lee, S. (2011). Detecting Wetland Change through Supervised Classification of Landsat Satellite Imagery within the Tunkwa Watershed of British Columbia, Canada. Retrieved January 10, 2017, from http://www.diva-portal.org/smash/record.jsf?pid= diva2:681571
Li, H., Zhang, D., Zhang, Y., & Xu, Y. (2008). Research of image preprocessing methods for EO-1 Hyperion hyperspectral data in tidal flat area. Geoinformatics, 71471G–71471G.
Liu, S. (2015). Advanced Techniques for Automatic Change Detection in Multitemporal Hyperspectral Images. University of Trento. Retrieved January 10, 2017, from http://eprints-phd.biblio.unitn.it/1393/
Liu, Y., & Parhi, K. K. (2016). Computing RBF kernel for SVM classification using stochastic logic. Signal Processing Systems (SiPS), 2016 IEEE International Workshop on (pp. 327–332). IEEE.
Lu, D., Moran, E., Hetrick, S., & Li, G. (2011). Land-use and land-cover change detection. Advances in Environmental Remote Sensing Sensors, Algorithms, and Applications. CRC Press Taylor & Francis Group, New York, 273–290.
Mabwoga, S. O., & Thukral, A. K. (2014). Characterization of change in the Harike wetland, a Ramsar site in India, using landsat satellite data. SpringerPlus, 3(1), 576.
McCarthy, M. J., Merton, E. J., & Muller-Karger, F. E. (2015). Improved coastal wetland mapping using very-high 2-meter spatial resolution imagery. International Journal of Applied Earth Observation and Geoinformation, 40, 11–18.
Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on geoscience and remote sensing, 42(8), 1778–1790.
Mereta, S. T., Boets, P., Bayih, A. A., Malu, A., Ephrem, Z., Sisay, A., Endale, H., et al. (2012). Analysis of environmental factors determining the abundance and diversity of macroinvertebrate taxa in natural wetlands of Southwest Ethiopia. Ecological Informatics, 7(1), 52–61.
Mousazadeh, R., Ghaffarzadeh, H., Nouri, J., Gharagozlou, A., & Farahpour, M. (2015). Land use change detection and impact assessment in Anzali international coastal wetland using multi-temporal satellite images. Environmental monitoring and assessment, 187(12), 1–11.
Ng, H.-F. (2006). Automatic thresholding for defect detection. Pattern recognition letters, 27(14), 1644–1649.
Nielsen, A. A. (2007). The regularized iteratively reweighted MAD method for change detection in multi-and hyperspectral data. IEEE Transactions on Image processing, 16(2), 463–478.
Nielsena, A. A., & Müllerb, A. (2003). Change detection by the MAD method in hyperspectral image data. Retrieved May 9, 2017, from http://citeseerx.ist.psu.edu/viewdoc/summary? doi=10.1.1.608.8367
Omo-Irabor, O. O. (2016). A Comparative Study of Image Classification Algorithms for Landscape Assessment of the Niger Delta Region. Journal of Geographic Information System, 8(02), 163.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1), 62–66.
Pacifici, F. (2007). Change detection algorithms: State of the art. URL: http://www. disp. uniroma2. it/earth_observatio n/pdf/CD-Algorithms. pdf (Accessed on 4 November, 2011).
Parente, M., & Plaza, A. (2010). Survey of geometric and statistical unmixing algorithms for hyperspectral images. Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2010 2nd Workshop on (pp. 1–4). IEEE.
Pieper, M., Manolakis, D., Cooley, T., Brueggeman, M., Weisner, A., & Jacobson, J. (2015). New insights and practical considerations in hyperspectral change detection. 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 4161–4164). IEEE.
Rapinel, S., Hubert-Moy, L., & Clément, B. (2015). Combined use of LiDAR data and multispectral earth observation imagery for wetland habitat mapping. International journal of applied earth observation and geoinformation, 37, 56–64.
Ring, M., & Eskofier, B. M. (2016). An approximation of the Gaussian RBF kernel for efficient classification with SVMs. Pattern Recognition Letters, 84, 107–113.
Romshoo, S. A., & Rashid, I. (2014). Assessing the impacts of changing land cover and climate on Hokersar wetland in Indian Himalayas. Arabian Journal of Geosciences, 7(1), 143–160.
Sakthivel, N. R., Saravanamurugan, S., Nair, B. B., Elangovan, M., & Sugumaran, V. (2016). Effect of kernel function in support vector machine for the fault diagnosis of pump. Journal of Engineering Science and Technology, 11(6), 826–838.
Samadzadegan, F., Hasani, H., & Schenk, T. (2012). Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using ant colony optimization. Canadian Journal of Remote Sensing, 38(2), 139–156.
Schaum, A., & Stocker, A. (1998). Long-interval chronochrome target detection. Proc. 1997 International Symposium on Spectral Sensing Research (pp. 1760–1770).
Scheffler, D., & Karrasch, P. (2013). Preprocessing of hyperspectral images: a comparative study of destriping algorithms for EO1-hyperion. Image and Signal Processing for Remote Sensing XIX (Vol. 8892, p. 88920H). International Society for Optics and Photonics.
Seydi, S. T., & Hasanlou, M. (2017). A new land-cover match-based change detection for hyperspectral imagery. European Journal of Remote Sensing, 50(1), 517–533.
Seydi, S. T., & Hasanlou, M. (2018). Sensitivity analysis of pansharpening in hyperspectral change detection. Applied Geomatics, 1–11.
Seydi, S. teymoor, & Hasanlou, M. (2016). Novel Wetland and Water Body Change Detction using Multitemporal Hyperspectral Imagery. Presented at the International Water Conference 2016 on Water Resources in Arid Areas, Oman,Muscat: Springer.
Shah-Hosseini, R., Homayouni, S., & Safari, A. (2015). A hybrid kernel-based change detection method for remotely sensed data in a similarity space. Remote Sensing, 7(10), 12829–12858.
Sica, Y. V., Quintana, R. D., Radeloff, V. C., & Gavier-Pizarro, G. I. (2016). Wetland loss due to land use change in the Lower Paraná River Delta, Argentina. Science of the Total Environment, 568, 967–978.
Singh, A. (1989). Review article digital change detection techniques using remotely-sensed data. International journal of remote sensing, 10(6), 989–1003.
Smith, R. (2012). Introduction to Hyperspectral Imaging, MicroImages Inc. Mentor, OH. Retrieved from http://www.microimages.com/documentation/Tutorials/hyprspec.pdf
Storey, E. A., Stow, D. A., Coulter, L. L., & Chen, C. (2017). Detecting shadows in multi-temporal aerial imagery to support near-real-time change detection. GIScience & Remote Sensing, 1–18.
Taminskasa, J., Petroliusa, R., Limanauskienėa, R., Satkūnasb, J., & Linkevičienėa, R. (2013). Prediction of change in wetland habitats by groundwater: case study in Northeast Lithuania. Estonian Journal of Earth Sciences, 62(2), 57ø e72.
Thonfeld, F., Feilhauer, H., Braun, M., & Menz, G. (2016). Robust Change Vector Analysis (RCVA) for multi-sensor very high resolution optical satellite data. International Journal of Applied Earth Observation and Geoinformation, 50, 131–140.
Varma, S., & Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC bioinformatics, 7(1), 91.
Vladimir, V. N., & Vapnik, V. (1995). The nature of statistical learning theory. Springer Heidelberg.
Vongsy, K. M. (2007). Change detection methods for hyperspectral imagery. Wright State University. Retrieved January 10, 2017, from https://etd.ohiolink.edu/!etd.send_file?accession=wright1184010751&disposition=attachment
Vongsy, K., Mendenhall, M. J., Hanna, P. M., & Kaufman, J. (2009). Change detection using synthetic hyperspectral imagery. Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2009. WHISPERS’09. First Workshop on (pp. 1–4). IEEE. Retrieved May 21, 2017, from http://ieeexplore.ieee.org/abstract/document/5289016/
Wang, J. (2013). Pearson correlation coefficient. Encyclopedia of Systems Biology (pp. 1671–1671). Springer. Retrieved January 28, 2017, from http://link.springer.com/content/pdf/10.1007/978-1-4419-9863-7_372.pdf
White, L., Brisco, B., Dabboor, M., Schmitt, A., & Pratt, A. (2015). A collection of SAR methodologies for monitoring wetlands. Remote sensing, 7(6), 7615–7645.
Whiteside, T. G., & Bartolo, R. E. (2015). Use of WorldView-2 time series to establish a wetland monitoring program for potential offsite impacts of mine site rehabilitation. International Journal of Applied Earth Observation and Geoinformation, 42, 24–37.
Wu, C., Du, B., & Zhang, L. (2013). A subspace-based change detection method for hyperspectral images. IEEE Journal of selected topics in applied earth observations and remote sensing, 6(2), 815–830.
Wu, C., Zhang, L., & Du, B. (2012). Targeted change detection for stacked multi-temporal hyperspectral image. Hyperspectral Image and Signal Processing (WHISPERS), 2012 4th Workshop on (pp. 1–4). IEEE. Retrieved July 31, 2017, from http://ieeexplore.ieee.org/abstract/document/6874282/
Yang, Y., & Yan, Z. (2016). Monitoring and Analyzing of Poyang Lake Wetland Land Use Change Based on RS and GIS. Geo-Informatics in Resource Management and Sustainable Ecosystem (pp. 213–221). Springer.
Yuan, F., Sawaya, K. E., Loeffelholz, B. C., & Bauer, M. E. (2005). Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensing. Remote sensing of Environment, 98(2), 317–328.
Yuen, P. W., & Richardson, M. (2010). An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition. The Imaging Science Journal, 58(5), 241–253.
Zanotta, D. C., Zani, H., & Shimabukuro, Y. E. (2013). Automatic detection of burned areas in wetlands by remote sensing multitemporal images. Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International (pp. 1959–1962). IEEE.
Zhao, H., Cui, B., Zhang, H., Fan, X., Zhang, Z., & Lei, X. (2010). A landscape approach for wetland change detection (1979-2009) in the Pearl River Estuary. Procedia Environmental Sciences, 2, 1265–1278.
chmitt, A., & Pratt, A. (2015). A collection of SAR methodologies for monitoring wetlands. Remote sensing, 7(6), 7615–7645.
Whiteside, T. G., & Bartolo, R. E. (2015). Use of WorldView-2 time series to establish a wetland monitoring program for potential offsite impacts of mine site rehabilitation. International Journal of Applied Earth Observation and Geoinformation, 42, 24–37.
Wu, C., Du, B., & Zhang, L. (2013). A subspace-based change detection method for hyperspectral images. IEEE Journal of selected topics in applied earth observations and remote sensing, 6(2), 815–830.
Wu, C., Zhang, L., & Du, B. (2012). Targeted change detection for stacked multi-temporal hyperspectral image. Hyperspectral Image and Signal Processing (WHISPERS), 2012 4th Workshop on (pp. 1–4). IEEE. Retrieved July 31, 2017, from http://ieeexplore.ieee.org/abstract/document/6874282/
Yang, Y., & Yan, Z. (2016). Monitoring and Analyzing of Poyang Lake Wetland Land Use Change Based on RS and GIS. Geo-Informatics in Resource Management and Sustainable Ecosystem (pp. 213–221). Springer.
Yuan, F., Sawaya, K. E., Loeffelholz, B. C., & Bauer, M. E. (2005). Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensing. Remote sensing of Environment, 98(2), 317–328.
Yuen, P. W., & Richardson, M. (2010). An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition. The Imaging Science Journal, 58(5), 241–253.
Zanotta, D. C., Zani, H., & Shimabukuro, Y. E. (2013). Automatic detection of burned areas in wetlands by remote sensing multitemporal images. Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International (pp. 1959–1962). IEEE.
Zhao, H., Cui, B., Zhang, H., Fan, X., Zhang, Z., & Lei, X. (2010). A landscape approach for wetland change detection (1979-2009) in the Pearl River Estuary. Procedia Environmental Sciences, 2, 1265–1278.