طبقه بندی مبتنی بر هدف با استفاده از قطعه بندی هرمی و الگوریتم ژنتیک وزن دار
محورهای موضوعی : کاربرد GIS&RS در برنامه ریزی
داود اکبری
1
(استادیار سنجش از دور، گروه مهندسی نقشه برداری، دانشکده مهندسی، دانشگاه زابل)
کلید واژه: تصویر فراطیفی, طبقه بندی مبتنی بر شی, الگوریتم ژنتیک وزن دار, انتخاب نشانه, قطعه بندی هرمی,
چکیده مقاله :
اخیرا، یک روش موثر برای طبقه بندی طیفی-مکانی با استفاده از قطعه بندی هرمی (HSEG) رشد یافته از نشانه های انتخاب شده ارائه شده است. هدف این مقاله بهبود این روش برای طبقه بندی تصاویر فراطیفی در مناطق شهری است. ابتدا الگوریتم ژنتیک وزن دار (WG) برای بدست آوردن باندهای بهینه داده های فراطیفی استفاده می شود. الگوریتم HSEG مبتنی بر نشانه سپس بر ویژگی های بدست آمده پیاده سازی می شوند. در ادامه، ویژگی های زمینه ای از تصاویر قطعه بندی شده استخراج می شوند. برای ویژگی های مکانی، ویژگی های مساحت، آنتروپی، شکل، مجاورت و رابطه به عنوان اجزای بالقوه در فضای ویژگی در نظر گرفته شده اند. سرانجام ، با استفاده از هر دو ویژگی طیفی و مکانی، اشیا تصویر توسط یک طبقه بندی کننده مبتنی بر قانون طبقه بندی می شوند. آزمون ها بر روی دو مجموعه داده اعمال شد: Berlin و Quebec City، که دو مجموعه داده شناخته شده و بنچ مارک در تصاویر فراطیفی هستند. ارزیابی نتایج نشان داد که روش پیشنهادی به ترتیب برای این مجموعه داده ها به ترتیب از 16٪ و 9٪ دقت کلی بهتری نسبت به الگوریتم HSEG اولیه به دست می آورد.
Hyperspectral imaging concerns measurement and interpretation of spectral imagery acquired by satellite, airborne, terrestrial, or laboratory sensors over visible, infrared and sometime thermal spectral regions of electromagnetic spectrum. There are two major approaches for classification of hyperspectral images: the spectral or pixel-based techniques, and the spectral-spatial or object-based techniques. Recently, an effective approach for spectral-spatial classification has been proposed using Hierarchical SEGmentation (HSEG) grown form automatically selected markers. This paper aims at improving this approach for classification of hyperspectral images in urban areas. The Weighted Genetic (WG) algorithm is first used to obtain the subspace of hyperspectral data. The obtained features are then fed into the marker-based HSEG algorithm. Then, the contextual features from segmented images are extracted. For spatial features, area, entropy, shape, adjacency and relation features are considered as the potential components in feature space. Finally, using both spectral and spatial features, the image objects are classified by a rule-based classifier. The experimental tests are applied to two datasets: the Berlin, and Quebec City, which are two known and benchmark datasets in hyperspectral imagery. The evaluation of results showed that the proposed approach achieves approximately 16% and 9% better overall accuracy than the Original-HSEG algorithm for these datasets respectively.
_||_
Akbari, D. (2019). “Improved neural network classification of hyperspectral imagery using weighted genetic algorithm and hierarchical segmentation”, IET Image Processing, Vol. 13(12), pp. 2169-2175.
Benz, U.C., Hofmann, P., Willhauck, G., Lingenfelder, I. & Heynen, M. (2004). “Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information”, ISPRS J. Photogramm, pp. 239–258.
Borzov, S.M. & Potaturkin, O.I. (2018). “Spectral-Spatial Methods for Hyperspectral Image Classification. Review.” Optoelectron.Instrument.Proc., Vol. 54, pp. 582–599.
Carleer, A.P. & Wolff, E. (2006). “Urban land cover multi-level region-based classification of VHR data by selecting relevant features”, Int. J. Remote Sens., Vol. 27(6), pp. 1035–1051.
Chen, Z. (2006). “Research on high resolution remote sensing image classification technology”, Beijing: Institute of Remote Sensing Applications of Chinese Academy of Science.
Chen, Y., Huang, L., Zhu, L., Yokoya, N. & Jia, X. (2019). “Fine-Grained Classification of Hyperspectral Imagery Based on Deep Learning”, Remote Sensing, Vol. 11.
Congalton, R. (1991). “A review of assessing the accuracy of classifications of remotely sensed data”, Remote Sensing of Environment, Vol. 37, pp. 35–46.
Fauvel, M., Chanussot, J., Benediktsson, J.A. & Sveinsson, J.R. (2008). “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles”, IEEE Trans. Geosci. Remote Sens., Vol. 46, pp. 3804–3814.
Gonzalez, R. & Woods, R. (2002). Digital Image Processing. 2nd ed. Englewood Cliffs, NJ: Prentice-Hall.
Huang, C.L. & Wang, C.J. (2006). “A GA-based feature selection and parameter optimization for support vector machines”, Expert Systems with Application, pp. 231-240.
Li, Y., Zhang, H. & Shen, Q. (2017). “Spectral–Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network”, Remote Sensing, Vol. 9(67).
Li, X., Zhao, S., Rui, Y. & Tang, W. (2007). “An object-based classification approach for high-spatial resolution Imagery”, Geoinformatics 2007: Remotely Sensed Data and Information, pp. 6752 -6753.
Liu, B., Yu, X., Yu, A., Zhang, P. & Wan, G. (2018). “Spectral-spatial classification of hyperspectral imagery based on recurrent neural networks”, Remote Sensing Letters, Vol. 9 (12), pp. 1118-1127.
Lu, D., Hetrick, S. & Moran, E. (2010). “Land cover classification in a complex urban-rural landscape with Quickbird imagery”, Photogrammetric Engineering and Remote Sensing, Vol. 76, pp. 1159–1168.
Nghi, D.H. & Mai, L.C. (2008). “An object-oriented classification techniques for high resolution satellite imagery”, International Symposium on Geoinformatics for Spatial Infrastructure Development in Earth and Allied Sciences.
Shackelford, A.K. & Davis, C.H. (2003). “A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas”, IEEE Trans. Geosci. Remote Sens., Vol. 41(10), pp. 2354–2363.
Shippert, P. (2004). “Why Use Hyperspectral Imagery?”, Photogrammetric Engineering and Remote Sensing, pp. 377–380.
Soille, P. (2003). Morphological Image Analysis. 2nd ed. Berlin, Germany: Springer-Verlag.
Story, M. & Congalton, R. (1986). “Accuracy assessment: A user's perspective”, Photogrammetric Engineering and Remote Sensing, Vol. 52, pp. 397–399.
Tarabalka, Y., Tilton, J.C., Benediktsson, J.A. & Chanussot, J. (2012). “A Marker-Based Approach for the Automated Selection of a Single Segmentation From a Hierarchical Set of Image Segmentations”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 5(1), pp. 262-272.
Tilton, J. (2003). “Analysis of hierarchically related image segmentations”, in Proc. IEEE Workshop Adv. Tech. Anal. Remotely Sensed Data, pp. 60–69.
Tilton, J. (2008). “HSEG/RHSEG, HSEGViewer and HSEGReader User’s Manual (Version 1.40)”, Provided With the Evaluation Version of RHSEG.
Walker, J.S. & Blaschke, T. (2008). “Object-based land cover classification for the Phoenix metropolitan area: optimization vs. transportability”, Int. J. Remote Sens., pp. 2021–2040.
Watanachaturaporn, P., Arora, M.K. & Varshney, P.K. (2008). “Multisource classification using support vector machines: an empirical comparison with decision tree and neural network classifiers”, Photogrammetric Engineering and Remote Sensing, Vol. 74, pp. 239–246.
Zhang, C. & Qiu, F. (2012). “Mapping Individual Tree Species in an Urban Forest Using Airborne Lidar Data and Hyperspectral Imagery”, Photogrammetric Engineering and Remote Sensing, Vol. 78, pp. 1079–1087.
Zhuo, L. & Zheng, J. (2008). “A Genetic Algorithm Based Wrapper Feature Selection Method for Classification of Hyperspectral Image Using Support Vector Machine”, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 37, pp. 397-402.