Building Detection with Special Roofing in Hyperspectral Images using Marker-based Hierarchical Algorithm

Document Type : Original Article

Author

Assistant Professor, Remote Sensing Division, Surveying and Geomatics Engineering Department, College of Engineering, University of Zabol, Zabol, Iran

Abstract

Hyperspectral remote sensing technology has witnessed remarkable progress in the last two decades. One of the analyzes performed on the hyperspectral images is target detection. In this research, the detection of roofs with special cover has been done as a target in an urban environment. Simultaneously with the growth of urbanization and the development of urban areas, the need of managers and planners for very accurate maps of urban areas has increased significantly. Since an urban environment has complex characteristics in terms of physical, geometrical and elements used in buildings, hyperspectral data effectively help to identify, extract and produce a map of the constituent elements of an urban environment. Regarding the spectral detection of the target, continuous and numerous researches have been carried out since the last two decades. According to the studies carried out, until now, the hierarchical algorithm has achieved the best results in comparison with other algorithms for extracting spatial information in hyperspectral images, Therefore, in this research, it is tried to reveal buildings with special cover in hyperspectral images by presenting a new and accurate method.
Material and methods: The image data of the CASI sensor has been used to carry out this research. The images processed in this research include images with 32 spectral bands and a resolution of 2 meters, which were taken in May 2001 from the urban area of ​​Toulouse located in the south of France. In the proposed method, two classification algorithms of multilayer perceptron neural network (MLP) and support vector machine (SVM) are implemented on the hyperspectral image. Then, the map resulting from the combination of the two mentioned algorithms is used to select the marker for the marker-based hierarchical segmentation algorithm. Finally, with the help of the majority vote decision rule, the marker-based hierarchical segmentation map is combined with the map resulting from the integration of MLP and SVM classifications.
Results and discussion: In this research, Gaussian radial basis kernel was used to implement the SVM algorithm. The values ​​of two parameters, penalty (C) and width of Gaussian function () were determined in SVM algorithm with the help of cross validation technique. The MLP classification algorithm was implemented with 3 hidden layers that include 5, 6 and 8 neurons and its evaluation was done with 500 repetitions and to select markers, the analysis of the labeling of connected components was done based on 8 neighborhood pixels on the map resulting from the combination of MLP and SVM. Based on the obtained results, the map obtained from the proposed method includes uniform regions and has more interconnected structures to reveal buildings, which shows the importance of using spatial information along with spectral information.
Conclusion: In this research, the strategy of using spatial information along with spectral information to improve target detection in the analysis of hyperspectral images was examined. For this purpose, the spectral-spatial marker-based hierarchical algorithm, which is used in the image classification process, was used to reveal the roofs of the buildings. In the proposed method, two classification maps were used in the selection of markers and the decision rule of the majority vote in the case of the initial hierarchical segmentation algorithm. In the combination of MLP and SVM classification maps, conditional probability and selection of the highest probability of each pixel belonging to a class are used in the selection of markers and majority vote decision rule.
Material and methods: The image data of the CASI sensor has been used to carry out this research. The images processed in this research include images with 32 spectral bands and a resolution of 2 meters, which were taken in May 2001 from the urban area of ​​Toulouse located in the south of France. In the proposed method, two classification algorithms of multilayer perceptron neural network (MLP) and support vector machine (SVM) are implemented on the hyperspectral image. Then, the map resulting from the combination of the two mentioned algorithms is used to select the marker for the marker-based hierarchical segmentation algorithm. Finally, with the help of the majority vote decision rule, the marker-based hierarchical segmentation map is combined with the map resulting from the integration of MLP and SVM classifications.
Results and discussion: In this research, Gaussian radial basis kernel was used to implement the SVM algorithm. The values ​​of two parameters, penalty (C) and width of Gaussian function () were determined in SVM algorithm with the help of cross validation technique. The MLP classification algorithm was implemented with 3 hidden layers that include 5, 6 and 8 neurons and its evaluation was done with 500 repetitions and to select markers, the analysis of the labeling of connected components was done based on 8 neighborhood pixels on the map resulting from the combination of MLP and SVM. Based on the obtained results, the map obtained from the proposed method includes uniform regions and has more interconnected structures to reveal buildings, which shows the importance of using spatial information along with spectral information.
Conclusion: In this research, the strategy of using spatial information along with spectral information to improve target detection in the analysis of hyperspectral images was examined. For this purpose, the spectral-spatial marker-based hierarchical algorithm, which is used in the image classification process, was used to reveal the roofs of the buildings. In the proposed method, two classification maps were used in the selection of markers and the decision rule of the majority vote in the case of the initial hierarchical segmentation algorithm. In the combination of MLP and SVM classification maps, conditional probability and selection of the highest probability of each pixel belonging to a class are used in the selection of markers and majority vote decision rule.

Keywords


Akbari, D., 2019, Improved Neural Network Classification of Hyperspectral Imagery using Weighted Genetic Algorithm and Hierarchical Segmentation, IET image processing, 13, pp. 2169-2175. https://doi.org/10.1049/iet-ipr.2018.5693
Bhattacharya, B.K., Green, R.O., Rao, S., Saxena, M., Sharma, S., Kumar, K.A., Srinivasulu, P., Sharma, S., Dhar, D. and Bandyopadhyay, S., 2019, An Overview of AVIRIS-NG Airborne Hyperspectral Science Campaign over India, Curr. Sci., 116, pp. 1082–1088. https://www.jstor.org/stable/27138000
Bradley, A.P., 1997, The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms, Pattern Recognit., 30, pp. 1145-1159. https://doi.org/10.1016/S0031-3203(96)00142-2
Carvalho, O.A. and Meneses, P.R., 2002, Spectral Correlation Mapper (SCM): An Improvement on the Spectral Angle Mapper (SAM), Asa Norte, 70910-900, Brasília, DF, Brasil.
Chang, C.I., 2003, Hyperspectral Imaging: Techniques for spectral Detection and Classification, Orlando, FL: Kluwer Academic. https://doi.org/10.1007/978-1-4419-9170-6
Chang, C.I. and Chiang, S.S., 2002, Anomaly Detection and Classification for Hyperspectral Imagery, IEEE Trans. Geosci. Remote Sens., 40, pp. 1314-1325. https://doi.org/10.1109/TGRS.2002.800280
Chang, C.I., Heinz, D.C., 2000, Constrained Subpixel Target Detection for Remotely Sensed Imagery, IEEE Trans. Geosci. Remote Sens., 38, pp. 1144-1059. https://doi.org/10.1109/36.843007
Cheng, G. and Han, J., 2016, A Survey on Object Detection in Optical Remote Sensing Images, ISPRS J. Photogramm. Remote Sens., 117, pp. 11–28. https://doi.org/10.1016/j.isprsjprs.2016.03.014
Cristianini, N. and Shawe-Taylor, J., 2000, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press. https://doi.org/10.1017/CBO9780511801389
Dos Reis Salles, R., Souza Filho, C.R., Cudahy, T., Vicente, L.E. and Monteiro, L.V.S., 2017, Hyperspectral Remote Sensing Applied to Uranium Exploration: A Case Study at the Mary Kathleen Metamorphic-Hydrothermal U-REE Deposit, NW, Queensland, Australia, J. Geochem. Explor., 179, pp. 36–50. https://doi.org/10.1016/j.gexplo.2016.07.002
Du, Y., Chang, C.I. and Ren, H., Chang, C.C., Jensen, J.O. and D'Amico, F., 2004, New Hyperspectral Discrimination Measure for Spectral Characterization, Optical Engineering, 43, pp. 1777-1786. https://doi.org/10.1117/1.1766301
Emami, H. and Afary, A., 2007, Subpixel Classification on the Hyperspectral Images for Accuracy Improvement of Classification Results, Dep. of Geodesy and Geomatic Eng, K.N. Toosi University of Technology, Tehran, Iran. https://civilica.com/doc/4132/
Freitas, S., Silva, H. and Almeida, J., 2018, Hyperspectral Imaging for Real-time Unmanned Aerial Vehicle Maritime Target Detection, J. Intell. Robot Syst., 90, pp. 551–570. https://doi.org/10.1007/s10846-017-0689-0
Freitas, S., Silva, H., Almeida J.M. and Silva, E., 2019, Convolutional Neural Network Target Detection in Hyperspectral Imaging for Maritime Surveillance, Int. J. Adv. Robot. Syst., pp. 1-13. https://doi.org/10.1177/1729881419842991
Frolov, D. and Smith, R.B., 1999, Locally Adaptive Constrained Energy Minimization for AVIRIS Image, Eighth JPL Airborne Earth Science (AVIRS), 1. http://www.microimages.com/papers
Homayouni, S. and Roux, M., 2005, Hyperspectral Image Analysis for Material Mapping using Spectral Matching, ISPRS04-Istanbul, GET, Telecom Paris, UMR 5141 LTCI, Department TSI, 46 rue Barrault, France.
Hou, Y., Zhang, Y., Yao, L., Liu, X. and Wang, F., 2016, Mineral Target Detection based on MSCPE_BSE in Hyperspectral Image, In Proceedings of the 2016 IEEE Int. Geosci. Remote Sens. Symposium (IGARSS), Beijing, China, pp. 1614–1617. https://doi.org/10.1109/IGARSS.2016.7729412
Jang, J.S.R., 1993, ANFIS: Adaptive-Network-based Fuzzy Inference Systems, IEEE Trans. Syst. Man Cybern., 23, pp. 665-685. https://doi.org/10.1109/21.256541
Jha, S.S. and Nidamanuri, R.R., 2020, Gudalur Spectral Target Detection (GST-D): A New Benchmark Dataset and Engineered Material Target Detection in Multi-Platform Remote Sensing Data, Remote Sens., 12, pp. 2145. https://doi.org/10.3390/rs12132145
Kanjir, U., Greidanus, H. and Oštir, K., 2018, Vessel Detection and Classification from Space borne Optical Images: A Literature Survey, Remote Sens. Environ., 207, pp. 1–26. https://doi.org/10.1016/j.rse.2017.12.033
Landgrebe, D., 1999, Some Fundamentals and Methods for Hyperspectral Image Data Analysis, SPIE Int. Symp. On Biomedical Optics (Photonics West), San Jose CA, Proc. SPIE, 3603, pp. 104-113. https://doi.org/10.1117/12.346731
Ren, S., He, K. and Girshick, R., 2017, Faster R-cnn: Towards Real Time Object Detection with Region Proposal Networks, IEEE Trans. Pattern Anal., 39, pp. 1137–1149. https://doi.org/10.48550/arXiv.1506.01497
Rosenfield, G.H., Fitzpatric-Lins, K., 1986, A Coefficient of Agreement as a Measure of Thematic Classification Accuracy, Photogrammetric Eng. Remote Sensing., 52, pp. 223-227.
Tarabalka, Y., Tilton, J.C., Benediktsson, J.A. and Chanussot, J.A., 2011, Marker-Based Approach for the Automated Selection of a Single Segmentation from a Hierarchical Set of Image Segmentations, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens, 5, pp. 262-272. https://doi.org/10.1109/JSTARS.2011.2173466
Tilton, J., 2003, Analysis of hierarchically related image segmentations, in Proc. IEEE Workshop Adv. Tech. Anal. Remotely Sensed Data, pp. 60–69.  https://doi.org/10.1109/WARSD.2003.1295173
Tilton, J., 2009, RHSEG User’s Manual: Including the Core RHSEG Open Source Release, HSEGExtract, HSEGReader and HSEGViewer.
Van der Meer, F., 2006, The Effectiveness of Spectral Similarity Measures for the Analysis of Hyperspectral Imagery, Int. J. Appl. Earth Observation Geoinformation., 8, pp. 3–17. https://doi.org/10.1016/j.jag.2005.06.001
Yadav, D., Arora, M.K., Tiwari, K.C. and Ghosh, J.K., 2018, Parameters A_ecting Target Detection in VNIR and SWIR Range, Egypt. J. Remote Sens. Space Sci., 21, pp. 325–333. https://doi.org/10.1016/j.ejrs.2017.08.004
Zhang, X., Nansen, C. and Aryamanesh, N., 2015, Importance of Spatial and Spectral Data Reduction in the Detection of Internal Defects in Food Products, Appl Spectrosc., 69, pp. 473–480. https://doi.org/10.1366/14-07672