به کارگیری روش های تخمین بعد ذاتی در استخراج ویژگی های بدست آمده از تصاویر راداری، ماهواره ای و لیدار به منظورشناسایی عوارض خاص شهری

نوع مقاله: مقاله پژوهشی

نویسندگان

استادیاردانشکده مهندسی نقشه برداری و اطلاعات مکانی، پردیس دانشکده های فنی دانشگاه تهران

چکیده

امروزه ترکیب دادهها و تصاویری که از منابع مختلف سنجش از دوری به دست آمدهاند، به عنوان راهحلی بهینه به منظور استخراج اطلاعات بیشتر مطرح است، چرا که این دادهها با دید وسیع خود، رقومی بودن، تهیه بصورت دورهای، اطلاعات مختلفی را در اختیار محققین قرار میدهند. در این راستا، سنجندههای غیرفعال نوری به صورت گسترده در نگاشت ساختارهای افقی مورد استفاده قرار میگیرند. دادههای راداری نیز با توجه به این که غالباً مستقل از شرایط جوی و به صورت شبانهروزی امکان جمعآوری دارند و نیز برخی ساختارهای زمینی و اهداف مصنوعی پاسخ ویژهای در فرکانس راداری دارند، تواناییهای تصاویر نوری را تکمیل میکنند. همچنین دادههای هوابرد لیدار نیز میتوانند اندازهگیریهای نمونهای با دقت بسیار بالا از ساختارهای قائم در اختیار قرار دهند. در نتیجه، استفاده همزمان دادههای نوری، راداری و لیدار میتواند اطلاعات بیشتری در کاربردهای متنوع فراهم نماید. در این تحقیق، با بکارگیری همزمان این سه دسته داده سعی بر شناسایی عوارض خاص شهری به شکل بهینه نمودیم. در این راستا، با بکارگیری و تولید توصیفگرهای مختلف (57 توصیفگر) و با استفاده از روشهای استخراج ویژگی (شامل PCA و ICA) و تخمین ابعاد ذاتی دادهها (شاملSML و NWHFC)، فضای بهینهای برای طبقهبندی نظارت شده ایجاد شد. پس از انجام طبقهبندی (روش K-NN) با استفاده از نتایج بدست آمده، توصیفگرهای (لایههای اطلاعاتی) تولید شده برای شناسایی عوارض خاص شهری شامل ساختمانها، راهها و پوشش گیاهی براساس دقت کلاسهبندی بدست آمده و گروهبندی شدند. نتایج عددی بدست آمده حاکی از کارایی بالای رویه پیشنهادی و نیز روشهای بکارگرفته شده تخمین بعد ذاتی و استخراج ویژگی است.

کلیدواژه‌ها


عنوان مقاله [English]

Applying Intrinsic Dimension Estimation Methods in the Extraction of Features Obtained from Radar and Satellite Imagery, and LiDAR Data to Identify Urban Specific Features

نویسندگان [English]

  • Parham Pahlavani
  • Mahdi Hasanlou
Assistant Professor, Faculty of Surveying and Geospatial data Engineering, College of Engineering, University of Tehran
چکیده [English]

Abstract
Nowadays, the combination of data and images obtained from different remote sensing sources is considered as an optimal solution for extracting more information, since these data, with their own wide vision, digital format, their periodically preparation, and high temporal resolution provide researchers with a variety of information about the land surface. In this regard, the passive optical sensors are widely used in mapping horizontal structures. Given that, radar data can often be collected 24-hours a day and Independent of atmospheric conditions, and also some ground structures and artificial targets have a specific response in the radar frequency, they complete the capabilities of optical images. LiDAR airborne data can also provide sample measurements from vertical structures with very high accuracy. As a result, the simultaneous use of optical, radar and LiDAR data can provide more information in a variety of applications. In this research, by simultaneously applying these three categories of data, we tried to identify the urban specific features in an optimal way. In this regard, by utilizing and producing various descriptors (57 descriptors), and using the feature extraction methods (including PCA and ICA) and estimating the intrinsic dimensions of the data (including SML and NWHFC), an optimal space for the supervised classification was created. After classifying (K-NN method) using the obtained results, descriptors (information layers) produced to identify specific urban features including buildings, roads and vegetation were obtained and grouped according to the classification accuracy. The numerical results indicate the high efficiency of the proposed procedure as well as the applied methods of estimating intrinsic dimension and extracting the features.

کلیدواژه‌ها [English]

  • Intrinsic Dimension
  • Image Classification
  • RADAR
  • LiDAR
  • Optic
  • Feature Detection
1- A. Agarwal, T. El-Ghazawi, H. El-Askary, and J. Le-Moigne, “Efficient Hierarchical-PCA Dimension Reduction for Hyperspectral Imagery,” in 2007 IEEE International Symposium on Signal Processing and Information Technology, 2007, pp. 353–356.

2- A. J. Richardson and J. H. Everitt, “Using spectral vegetation indices to estimate rangeland productivity,” Geocarto Int., vol. 7, no. 1, pp. 63–69, 1992.

3- A. Moussa and N. El-Sheimy, “A new object based method for automated extraction of urban objects from airborne sensors data,” in Proceedings of: XXII ISPRS Congress, Melbourne, Australia, 2012.

4- B. Sirmacek and C. Unsalan, “Building detection from aerial images using invariant color features and shadow information,” in Computer and Information Sciences, 2008. ISCIS’08. 23rd International Symposium on, 2008, pp. 1–5.

5- C. F. Jordan, “Derivation of leaf-area index from quality of light on the forest floor,” Ecology, pp. 663– 666, 1969.

6- C. Fuchs, “Extraktion polymorpher Bildstrukturen und ihre topologische und geometrische Gruppierung,” Bayerischen Akademie der Wissenschaften, Munchen, 1998.

7- C. Lin and R. Nevatia, “Building detection and description from a single intensity image,” Comput. Vis. Image Underst., vol. 72, no. 2, pp. 101–121, 1998.

8- C.-I. Chang and Q. Du, “Estimation of number of spectrally distinct signal sources in hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens., vol. 42, no. 3, pp. 608–619, 2004.

9- D. Grigillo and U. Kanjir, “Urban object extraction from digital surface model and digital aerial images,” in Proceedings of XXII ISPRS Congress, Melbourne, Australia, 2012.

10- F. J. Kriegler, W. A. Malila, R. F. Nalepka, and W. Richardson, “Preprocessing transformations and their

effects on multispectral recognition,” in Remote Sensing of Environment, VI, 1969, vol. 1, p. 97.

11- F. Rottensteiner and C. Briese, “A new method for building extraction in urban areas from high-resolution LIDAR data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 34, no. 3/A, pp. 295–301, 2002.

12- G. Sohn and I. J. Dowman, “Extraction of buildings from high resolution satellite data,” Autom. Extr. Man- Made Objects Aer. Space Images III Balkema Publ. Lisse, pp. 345–355, 2001.

13- G. Vosselman, B. G. H. Gorte, and G. Sithole, “Change detection for updating medium scale maps using laser altimetry,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 34, pp. 1–6, 2004.

14- G. Vozikis, Application of High Resolution Remote Sensing Data – Part III URBAN DATA COLLECTION: AN AUTOMATED APPROACH IN REMOTE SENSING. .

15- H. Arefi and M. Hahn, “A morphological reconstruction algorithm for separating off-terrain points from terrain

points in laser scanning data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 36, no. 3/W19, 2005.

16- H.-G. Maas and G. Vosselman, “Two algorithms for extracting building models from raw laser altimetry data,” ISPRS J. Photogramm. Remote Sens., vol. 54, no. 2, pp. 153–163, 1999.

17- J. A. Benediktsson, M. Pesaresi, and K. Amason, “Classification and feature extraction for remote sensing images from urban areas based on morphological transformations,” Geosci. Remote Sens. IEEE Trans. On, vol. 41, no. 9, pp. 1940–1949, 2003.

18- J. Niemeyer, F. Rottensteiner, and U. Soergel, “Classification of urban LiDAR data using conditional random field and random forests,” in Urban Remote Sensing Event (JURSE), 2013 Joint, 2013, pp. 139–142.

19- J. Niemeyer, F. Rottensteiner, and U. Soergel, “Conditional random fields for lidar point cloud classification in complex urban areas,” ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 1, no. 3, pp. 263–268, 2012.

20- J. Qi, A. Chehbouni, A. R. Huete, Y. H. Kerr, and S. Sorooshian, “A modified soil adjusted vegetation index,” Remote Sens. Environ., vol. 48, no. 2, pp. 119–126, 1994.

21- J. Zhao and S. You, “Road network extraction from airborne LiDAR data using scene context,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on, 2012, pp. 9–16.

22- K. Kraus and N. Pfeifer, “Determination of terrain models in wooded areas with airborne laser scanner data,” ISPRS J. Photogramm. Remote Sens., vol. 53, no. 4, pp. 193–203, 1998.

23- L. J. P. V. D. Maaten, “An introduction to dimensionality reduction using matlab,” 2002.

 24- M. Hasanlou and F. Samadzadegan, “Comparative Study of Intrinsic Dimensionality Estimation and Dimension Reduction Techniques on Hyperspectral Images Using K-NN Classifier,” IEEE Geosci. Remote Sens. Lett. vol. 9, no. 6, pp. 1046–1050, 2012.

25- M. Hebel and U. Stilla, “Pre-classification of points and segmentation of urban objects by scan line analysis of airborne LiDAR data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 37, no. B3a, pp. 105–110, 2008. 

26- M. Persson, M. Sandvall, and T. Duckett, “Automatic building detection from aerial images for mobile robot mapping,” in Computational Intelligence in Robotics and Automation, 2005. CIRA 2005. Proceedings. 2005 IEEE International Symposium on, 2005, pp. 273–278.

27- P. Bajorski, “Second Moment Linear Dimensionality as an Alternative to Virtual Dimensionality,” IEEE Trans. Geosci. Remote Sens., vol. 49, no. 2, pp. 672–678, 2011.

28- Q. Zhan, M. Molenaar, and K. Tempfli, “Building extraction from laser data by reasoning on image segments in elevation slices,” Int. Arch. Photogramm. REMOTE Sens. Spat. Inf. Sci., vol. 34, no. 3/B, pp. 305–308, 2002.

29- R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3 edition. Upper Saddle River, N.J: Prentice

Hall, 2007.

30- R. Weibel and M. Heller, Digital terrain modelling. Oxford University Press, 1993.

31- S. A. Mumtaz and K. Mooney, “Fusion of high resolution lidar and aerial images for object extraction,” in Advances in Space Technologies, 2008. ICAST 2008. 2nd International Conference on, 2008, pp. 137–142.

32- S. Lefèvre and J. Weber, “Automatic building extraction in VHR images using advanced morphological operators,”

in Urban Remote Sensing Joint Event, 2007, 2007, pp. 1–5.

33- S. Müller and D. W. Zaum, “Robust building detection in aerial images,” Int. Arch. Photogramm. Remote Sens.,

vol. 36, no. B2/W24, pp. 143–148, 2005.

34- T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1,

pp. 21–27, Jan. 1967.

35- T. Gevers and A. W. Smeulders, “Pictoseek: Combining color and shape invariant features for image retrieval,” Image Process. IEEE Trans. On, vol. 9, no. 1, pp. 102–119, 2000.

36- T. Vögtle and E. Steinle, “On the quality of object classification and automated building modelling based on laserscanning data,” Int. Arch. Photogramm. Remote  Sens. Spat. Inf. Sci., vol. 34, no. Part 3, p. W13, 2003.

37- U. Weidner and W. Förstner, “Towards automatic building extraction from high-resolution digital elevation models,” ISPRS J. Photogramm. Remote Sens., vol. 50, no. 4, pp. 38–49, 1995.

38- "WorldView-2," Wikipedia, the free encyclopedia. 30-Nov-2014.

39- W. Rieger, M. Kerschner, T. Reiter, and F. Rottensteiner, “Roads and buildings from laser scanner data within a forest enterprise,” Int. Arch. Photogramm. Remote Sens., vol. 32, no. Part 3, p. W14, 1999.

40- Y. Wei, W. Yao, J. Wu, M. Schmitt, and U. Stilla, “Adaboost-based feature relevance assessment in fusing lidar and image data for classification of trees and vehicles in urban scenes,” ISPRS Ann.