Yüksek Çözünürlüklü Multispektral Uydu Görüntülerinde Kuvvetlendirilmiş Sınıflandırıcılar Kullanılarak Otomatik Yol Çıkarımı

Öz

Bu çalışmada yüksek çözünürlüklü multispektral uydu görüntülerinden karayolu çıkarımı için yeni bir yöntem önerilmiştir. Önerilen yöntem, literatürde genellikle su ve bitki örtüsünün sınıflandırılması için kullanılan ve spektral bantların oranlanmasıyla elde edilen indisler ile birlikte bölütleme sonuçları üzerinden elde edilen bölütlere ait yapısal özellikleri öznitelik olarak kullanmakta ve ADABOOST gözetimli bir öğrenme algoritmasını bu öznitelikler ile eğitmektedir. Algoritma çeşitli uydu görüntülerinde denenmiş, yol çıkarımında başarılı olduğu gözlemlenmiştir.

Anahtar Kelimeler

• Örüntü Tanıma
• Uzaktan Algılama
• Uydu Görüntüleri
• Yol Çıkarımı

Road Extraction from Multispectral Satellite Images Using Boosted Classifiers

Öz

In this study, a new method for extracting road mask from high resolution multispectral satellite images is proposed. Proposed method uses indices which are generally utilized for water or vegetation detection in the literature with the structural properties of segments generated by segmentation procedure as features and trains ADABOOST supervised learning algorithm with them. The proposed method is tried on different satellite images and it is observed that the proposed method which is developed using Adaboost learning algorithm is succesful at extracting road networks from satellite images.

Anahtar Kelimeler

• Pattern Recognition
• Remote Sensing
• Satellite Images
• Road Extraction

Kaynakça

1. H. Zhao, J. Kumagai, M. Nakagawa, R. Shibasaki, "Semi-automatic Road Extraction from High- resolution Satellite Image," Proc. Photogrammetric Computer Vision ISPRS Commission III, Symposium , 406-411, (2002).
2. L. Wang, Q. Qin, S. Du, D. Chen, and J. Tao, "Road extraction from remote sensing image based on multi-resolution analysis," International Symposium on Remote Sensing of Environment, ( 2005.)
3. V.Shukla, R. Chandrakant, R. Ramachandran, "Semi-Automatic Road Extraction Algorithm For High Resolution Images Using Path Following Approach," ICVGIP02, 201-207, (2002)
4. C. Zhang, M. Shunji, B. Emmanuel, “Road Network Detection by Mathematical Morphology”, ISPRS Workshop "3D Geospatial Data Production: Meeting Application Requirements", 185-200, (1999).
5. T. Géraud, J.B Mouret, “Fast road network extraction in satellite images using mathematical morphology and Markov random fields”. EURASIP Journal of Applied Signal Processing, 2503-2514, (2004).
6. B. Sirmacek, C. Unsalan, "Road Network Extraction Using Edge Detection and Spatial Voting," ICPR,3113-3116,(2010).
7. H. Y. Lee, W. Park, H.K. Lee, “Automatic Road Extraction from 1M-Resolution Satellite Images.” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 55, (2000).
8. J. Amini, C. Lucas, M.R. Saradjian, A. Azizi, S. Sadeghian, “Fuzzy Logic System For Road Identification Using Ikonos Images”, Photogrammetric Record, (2002).

9. U. Bacher, H. Mayer , “Automatic Road Extraction from Multispectral High Resolution Satellite Images”, ISPRS Object Extraction for 3D City Models, Road Databases and Traffic Monitoring - Concepts, Algorithms and Evaluation, (2005).
10. D. Comanicu, P. Meer: "Mean shift: A robust approach toward feature space analysis." IEEE Trans. Pattern Anal. Machine Intell., 603-619, (2002).
11. C.M. Christoudias, B. Georgescu, P. Meer, "Synergism in low level vision,", Proceedings: 16th International Conference on Pattern Recognition , 150- 155 ,(2002).
12. A.R. Huete, “A Soil-Adjusted Vegetation Index (SAVI)”. Remote Sensing of Environment, vol. 25:295-309, (1988).
13. J.Weier, D. Herring. “Measuring Vegetation (NDVI & EVI). Internet: http://earthobservatory.nasa.gov/Features/MeasuringVegetation/, (2012).
14. B. Gao, “NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space”, Remote Sensing of Environment, vol. 58:257-266,(1996).
15. M.D. Nellis, J.M. Briggs, “Transformed Vegetation Index for Measuring Spatial Variation in Drought Impacted Biomass on Konza Prairie, Kansas”, Transactions of the Kansas Academy of Science, vol. 95: 93-99, (1992).
16. Y. J. Kaufman, D. Tanre, “Strategy for Direct and Indirect Methods for Correcting the Aerosol Effect on Remote Sensing: from AVHRR to EOS-MODIS”, Remote Sensing of Environment, vol 55:65-79, (1996).
17. R.E. Schapire , Y. Singer “Improved boosting algorithms using confidence-rated predictions”. Machine Learning, vol 37:297-336, (1999).