Çok yüksek çözünürlüklü renkli İHA görüntülerinden kentsel alanlarda araç tespiti

Abstract

Kentsel alanlarda uzaktan algılama görüntülerinden bina, ağaç, araç, vb. coğrafi nesnelerin otomatik olarak tespiti oldukça gerekli ve önemlidir. Bu çalışmada, çok yüksek konumsal çözünürlüklü renkli (Kırmızı, Yeşil, Mavi) stereo insansız hava aracı (İHA) görüntülerinden kentsel alanlarda sabit araçların tespiti yapılmıştır. Kullanılan yaklaşımın ilk adımında stereo İHA görüntülerinden sayısal yüzey modeli (SYM) oluşturulmaktadır. Sonra, SYM verisinden sayısal arazi modeli (SAM) ve SYM kullanılarak İHA görüntülerinden ortofoto oluşturulmaktadır. Ardından, yalnız yer üstü nesneleri elde etmek için SYM ve SAM verilerinin farkı alınarak normalize edilmiş sayısal yüzey modeli (nSYM) hesaplanmaktadır. Daha sonra, elde edilen nSYM verisi ek bant olarak kullanılmak suretiyle ortofotonun çoklu çözünürlük segmentasyonu ve ardından nesne-tabanlı sınıflandırması yapılmaktadır. Yaklaşım, Hacettepe Üniversitesi, Beytepe Yerleşkesi’nde farklı özelliklere sahip iki alan üzerinde uygulanmıştır. Oluşturulan referans veriyle yapılan karşılaştırma neticesinde, araç tespiti doğruluğu birinci test alanı (Alan#1) için %78.53 ve ikinci test alanı (Alan#2) için %92.15 olarak hesaplanmıştır. Elde edilen sonuçlar, önerilen yaklaşımla sabit araçların çok yüksek konumsal çözünürlüklü İHA görüntülerinden tespitinin yüksek doğrulukla yapılabildiğini göstermiştir.

Keywords

• İnsansız hava aracı (İHA),Ortofoto,Sayısal yüzey modeli (SYM),Sayısal arazi modeli (SAM),Segmentasyon,Sabit araç tespiti

Vehicle detection in urban areas from very high resolution UAV color images

Abstract

It is very essential and important in urban areas for the automatic detection of geographical objects such as buildings, trees, and vehicles by using remotely sensed images. In this study, the stationary vehicles were detected from very high spatial resolution stereo color (Red, Green, Blue) unmanned aerial vehicles (UAV) images in urban areas. In the first step of the approach used, digital surface model (DSM) is generated from the stereo images. Then, digital terrain model (DTM) is generated from the DSM, and by using the DSM orthophotos are generated from IHA images. Next, the normalized digital surface model (nDSM) is calculated by taking the difference between the DSM and DTM to obtain only the ground objects. After that, using the obtained nDSM data as an additional band, the multi-resolution segmentation and then object-based classification of the orthophoto are carried out. The approach was applied on two areas with different characteristics at Hacettepe University, Beytepe Campus. After comparing the results with the reference data, the vehicle detection accuracy was computed as 78.53% for the first test field (Field # 1) and it was computed as 92.15% for the second test field (Field # 2). The results show that the detection of stationary vehicles from very high spatial resolution UAV images can be performed with high accuracy using the proposed approach.

Keywords

• Unmanned aerial vehicle (UAV),Orthophoto,Digital surface model (DSM),Digital terrain model (DTM),Segmentation,Detection of stationary vehicle

References

1. Xiong Z, Zhang Y. “An initial study on vehicle information extraction from single-pass quickbird satellite imagery”. Photogrammetric Engineering & Remote Sensing, 74(11), 1401-1411, 2008.
2. Mancini F, Dubbini M, Gattelli M, Stecchi F, Fabbri S, Gabbianelli G. “Using unmanned aerial vehicles (uav) for high resolution reconstruction of topography: The structure from motion approach on coastal environments”. International Journal of Remote Sensing, 5(10), 6880-6898, 2013.
3. Stilla U, Michaelsen E, Soergel U, Hinz S, Ender J. “Airborne monitoring of vehicle activity in urban areas”. International Society For Photogrammetry And Remote Sensing, Commission III, Muenchen, Germany WG III/4, 2015.
4. Bulatov D, Schilling H. “Segmentation methods for detection of stationary vehicles in combined elevation and optical data”. 23rd International Conference on Pattern Recognition (ICPR), Cancun Center Mexico, 4-8 December, 2016.
5. Leithloff J, Hinz S, Stilla U. “Automatic vehicle detection in space images supported by digital map data”. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 36(3), 75-80, 2005.
6. Jin X, Davis CH. “Vehicle detection from high resolution satellite imagery using morphological shared-weight neural networks”. Science Direct Image and Vision Computing, 25(12), 1422-1431, 2006.
7. Leitloff J, Hinz S, Stilla U. “Vehicle detection in very high resolution satellite images of city areas”. The Institude of Electrical and Electronics Engineers Transactions On Geoscience And Remote Sensing, 48(7), 2795-2806, 2010.
8. Zheng Z, Wang X, Zhou G, Jiang L. “Vehicle detection based on morphology from highway aerial images”. 32nd International Geoscience And Remote Sensing Symposium, Munich, Germany, 24 July 2012.

9. Kaynarca M, Demir N. “Nesne tabanlı sınıflandırma ile karayolunda bulunan araçların tespiti”. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 17(Özel Sayı), 12-17, 2017.
10. Zhao T, Nevatia R. “Car detection in low resolution aerial image”. 8th Institude of Electrical and Electronics Engineers Conference, Vancouver, Canada, 7-14 July 2001.
11. Schlosser C, Reitberger J. “Automatic car detection in high resolution urban scenes based on an adaptive 3D model”. 5th Institude of Electrical and Electronics Engineers Conference, Alushta, Ukreine, 5-11 June 2003.
12. Gerhardinger A, Ehrlich D, Pesaresi M. “Vehicles detection from very high resolution satellite imagery”. The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences, 36(3), 83-88, 2005.
13. Zheng H, Li L, “An artificial immune approach for vehicle detection from high resolution space imagery”. International Journal of Computer Science and Network Security, 7(2), 170-179, 2007.
14. Sharma G, Merry C J, Poel P, McCord M. “Vehicle detection in 1 m resolution satellite and airborne imagery, International Journal of Remote Sensing, 27(4), 779-797, 2007.
15. Nguyen TT, Grabner H, Gruber B, Bischof H. “On-line boosting for car detection from aerial images”. International IEEE Conference on Computer Science, Paris, France, 22-28 April 2007.
16. Tsai L W, Hsieh J W, Fan K C. “Vehicle detection using normalized color and edge map”. IEEE Transactions on Image Processing, 16(3), 850-853, 2007.
17. Holt A C, Seto E Y W, Rivard T, Gong P. “Object based detection and classification of vehicles from high resolution aerial photography”. Photogrammetric Engineering & Remote Sensing, 75(7), 871-880, 2009.
18. Liı W, Yamazaki F, Thuy VT. “Automated vehicle extraction and speed determination from quickbird satellite images”. The Institute of Electrical and Electronics Engineers Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 4(1), 75-82, 2011.
19. Kembhavi A, Harwood D, Davis LS. “Vehicle detection using partial least squares”. The Institude of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence, 33(6), 1250-1265, 2011.
20. Salehi B, Zhang Y, Zhong M. “Automatic moving vehicles information extraction from single-pass worldview-2 imagery”. The Institude of Electrical and Electrical Engineers Jornal of Selected Topics in Applied Earth Observations And Remote Sensing, 5(1), 135-145, 2012.
21. Zhang Y, Xiong Z. “Moving vehicle detection using a single set of qickbird imagery-an initial study”. International Society for Photogrammetry and Remote Sensing, Commission VII, İstanbul, Turkey, 29 September-2 October, 2014.
22. Sejpal R, Charadva M, Sarwade N. “Review on moving vehicle detection in aerial surveliance”. International Journal of Research in Engineering and Technology, 3(6), 281-284, 2014.
23. Sincha D, Chervonenkis M, Skribtsov P, “Vehicle detection and classification in aerial images”. Indian Journal of Science and Technology, 9(48), 295-303, 2016.
24. Qu S, Wang Y, Meng G, Pan C. “Vehicle detection in satellite images by incorporating objectness and convolutional neural network”. Journal of Industrial and Intelligent Information, 4(2), 158-162, 2016.
25. Ludwig Boltzmann Institute Archaeological Prospection and Virtual Archaeology. “ALS filtering”. http://lbiarchpro.org/alsfiltering/lbiproject/results/lastools/filtering algorithm-2 (16.11. 2017).
26. Axelsson P. “DEM generation from laser scanner data using adaptive tin models”. International Society For Photogrammetry And Remote Sensing, 33(1), 110-117, 2000.
27. Axelsson P. “Processing of laser scanner data algorithms and applications”. International Journal of Photogrammetry & Remote Sensing, 54 (1999), 138-147, 1999.
28. Ludwig Boltzmann Institute Archaeological Prospection and Virtual Archaeology. “ALS filtering”. http://lbiarchpro.org/alsfiltering/lbiproject/results/lastools/guidelines-2 (16.11.2017).
29. University of North Carolina at Chapel Hill. “Fast Tools to Catch Reality”. https://www.cs.unc.edu/~isenburg/lastools/download/ lasground_README.txt (16.11.2017).
30. University of North Carolina at Chapel Hill. “Fast Tools to Catch Reality”. https://www.cs.unc.edu/~isenburg/lastools/download/lasclassify_README.txt (16.11.2017).
31. Sithole G, Vosselman G. “Experimental comparison of filter algorithms for bare earth extraction from airborne laser scanning point clouds”. ISPRS Journal of Photogrammetry & Remote Sensing, 59(1-2), 85-101, 2004.
32. Montealegre AL, Lamelas MT, de la Riva J. “A comparison of open source lidar filtering algorithms in a mediterranean forest environment”. The Institute of Electrical and Electronics Engineers Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(8), 4072-4085, 2015.
33. Yılmaz V, Konakoğlu B, Şerifoğlu Ç, Güngör O, Gökalp E. “Image classification based ground filtering of point clouds extracted from uav based aerial photos”. Geocarto International, 33(3), 310-320, 2018.
34. Baatz M, Arno S. Multiresolution Segmentation-An Optimization Approach for High Quality Multi-Scale Image Segmentation. Editor: Sttrobl J. Angewandte Geographische Informationsverarbeitung, 12-23, Salzburg, Germany, Herbert Wichmann Verlag Publisher, 2000.
35. Jähne B. Digital Image Processing. 6th ed. Berlin, Germany, Springer Heidelberg Press, 2005.
36. Marangoz AM. Fotogrametri I Geometrik ve Matematik Temeller. Birinci baskı, Zonguldak, Türkiye, Bülent Ecevit Üniversitesi Yayınları, 2012.
37. Zhang Y, Maxwell T, Tong H, Dey V. “Development of supervised software tool for automated determination of optimal segmentation parameters for e-cognition”. International Society for Photogrammetry And Remote Sensing Technical Commission VII. Vienna, Austria, 5-7 July 2010.
38. Dass R, Priyanka P, Devi S. “Image segmentation techniques”. International Journal Of Electronics & Communication Technology, 3(1), 66-70, 2012.
39. Strobl J, Blaschke T, Griesebner G. Angewandte Geographische Informations Verarbeitung. 12th ed. Heidelberg, Germany, Wichmann-Verlag, 2003.
40. Kavzoğlu T, Yıldız M. “Parameter based performance analysis of objects based image analysis using aerial and quickbird-2 images”. International Society For Photogrammetry and Remote Sensing and Spatial İnformation Sciences, 2(7), 31-37, 2014.
41. Dragut L, Tiede D, Levick SR. “ESP is a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data”. International Journal of Geographical İnformation Science, 24(6), 859-871, 2010.
42. Dragut L, Csillik O, Eisank C, Tiede D. ESP 2 (Estimation of Scale Parameters 2)-User Guide. 2nd ed. Salzburg, Austria, Elsevier, 2014.
43. Dey V. “A Supervised Approach for the Estimation of Parameters of Multiresolution Segmentation and Its Application in Building Feature Extration from VHR Imagery”. Department of Geodesy and Geomatics Engineering, University of New Brunswick, Fredericton, Canada, Technical Report, 278, 2011.
44. Meyer GE, Neto JC. “Verification of color vegetation indices for automated crop mapping applications”. Computers and Electronics In Agriculture, 6(3), 282-293, 2008.
45. Benz UC, Hofmann P, Willhauch G, Lingenfelder I, Heynen M. “Multiresolution object oriented fuzzy analysis of remote sensing data for gis ready information”. International Society For Photogrammetry and Remote Sensing, 58(3-4), 239-258, 2004.
46. Brodsky L, Boruvka L. “Object oriented fuzzy analysis of remote sensing data for bare soil brightness mapping”. Department of Soil Science and Geology, Faculty of Agrobiology, Czech University of Agriculture in Prague, 1(3), 79-84, 2006.
47. MATLAB Software Documentation Home. “Image Processing Toolbox”. http://mathworks.com/help/images/arcpy/gray-level co-occurence-matrix-glcm.html (16.11.2017).
48. Collins MJ, Dymond C, Johnson EA. “Mapping Subalpine Forest Types Using Networks of Nearest Neighbour Classifiers”. International Journal of Remote Sensing, 9(25), 1701-1721, 2004.
49. Yu Q, Gong P, Clinton N, Biging G, Kelly M, Schlrokauer D. “Object based detailed vegetation classification with airborne high spatial resolution remote sensing imagery”. Photogrammetric Engineering & Remote Sensing, 72(7), 799-811, 2006.
50. ArcGIS Software 10.3 Documentation Library. “Calculating Field Values” http://desktop.arcgis.com/en/arcmap/10.3/managedata /tables/calculating-area-length-and-other-geometric properties.html (16.11.2017).
51. Oruç M. Uydu Görüntülerinin Sınıflandırılması ve Doğruluk Değerlendirmesi, Birinci baskı, Zonguldak, Türkiye, Bülent Ecevit Üniversitesi Yayınları, 2010.
52. Mather PM, Koch M. Computer Processing of Remotely Sensed Images. 4th ed. Nottingham, United Kingdom, Wiley, 2011.
53. Hermosilla T,Ruiz AR, Recio A, Estornell J. “Evaluation of automatic building detection approaches combining high resolution images and lidar data”. Remote Sensing, 3(1), 1188-1210, 2011.
54. Rishikeshan CA, Ramesh H. “An ann supported mathematical morphology based algorithm for lakes extraction from satellite images”. ISH Journal of Hydraulic Engineering, 20(4), 222-229, 2017.