Hava Lidar verilerinin denetimsiz yapay sinir ağları kullanılarak filtrelenmesi

Yıl 2021, Cilt: 8 Sayı: 1, 18 - 29, 01.05.2021

Alper Şen , Burcu Bayaslı

https://doi.org/10.9733/JGG.2021R0002.T

Öz

Hava Lidar (Light Detection and Ranging) sistemleri ile üretilen mekânsal veriler, yüksek doğruluklu, hızlı ve az maliyetli olarak elde edilmektedir. Ancak verilerin nesne çıkarımı amacıyla elle işlenmesi, zaman alan ve emek yoğun bir işlemdir. Bu süreci otomatik bir hale dönüştürmek amacıyla, denetimli/denetimsiz sınıflandırma yöntemleri kullanılabilmektedir. Lidar verilerinin, zemine ait ve zemine ait olmayan veriler olarak ayrılmasına filtreleme denir. Lidar verileri kullanılarak Sayısal Yükseklik Modeli oluşturulmasında filtreleme işlemi büyük önem arz etmektedir. Bu çalışmada, Harita Genel Müdürlüğü’nün başkanlığında 2014 yılında üretilen, Riegl LMS-Q1560 Lidar sistemiyle Bergama ilçesinde 1200 metre yükseklikte gerçekleştirilen uçuş verilerinden elde edilen ayrık-dönüşlü Lidar test verisi kullanılmıştır. Lidar nokta bulutu, denetimsiz bir yapay sinir ağı yöntemi olan Kendini Düzenleyen Haritalar (KDH) yöntemi ile analiz edilerek kümelere ayrılmıştır. Kümeler, uydu görüntüleri ile karşılaştırılarak nesne sınıfları belirlenmiştir. Bu yöntem ile elde edilen nesne sınıflarının doğruluğu, görsel olarak sınıfları belirlenen tüm noktalar incelenerek hesaplanmıştır. Sinir ağına ait en az nöron sayısı, denetimli olarak hata değerlerine göre belirlenmiştir. Lidar nokta bulutunun KDH yöntemiyle filtrelenmesi sonucu, Tip-1 hatası %11.54, Tip-2 hatası %19.43 ve toplam hata %16.41 olarak bulunmuştur. Elde edilen sonuçlara göre, hava Lidar verilerinin filtrelenmesinde KDH sinir ağlarının belirlenen nöron sayısı ile etkin olarak kullanılabildiği görülmüştür.

Anahtar Kelimeler

Lidar, Yapay sinir ağları, Kendini düzenleyen haritalar, Filtreleme

Teşekkür

Bergama ilçesine ait Lidar test uçuş verilerini sağlayan Harita Genel Müdürlüğü’ne teşekkürü bir borç biliriz.

Filtering of airborne Lidar data by using unsupervised artificial neural networks

Öz

Spatial data produced with airborne Lidar(Light Detection and Ranging) systems are obtained with high accuracy, fast and low cost. However, manual processing of the data for object extraction is time consuming and labor intensive. Supervised/unsupervised classification methods can be used to make this process automatic. Classification of Lidar data as ground and non-ground data is called filtering. Filtering is very important in creating a Digital Elevation Model using Lidar data. In this study, the discrete-return Lidar test data obtained from the flight at 1200 meters altitude in Bergama district with the Riegl LMS-Q1560 Lidar system produced in 2014 under the chairmanship of the General Directorate of Mapping was used. The Lidar point cloud was grouped into clusters by analyzing it with the Self Organizing Maps (SOM), which is an unsupervised artificial neural network method. Feature classes were determined by comparing clusters with satellite images. The accuracy of the feature classes obtained by this method was calculated by examining all points of the classes which were visually determined. The minimum number of neurons of neural network was determined according to the error values. As a result of filtering the Lidar point cloud with SOM method, Type-1 error was found as 11.54%, Type-2 error was 19.43% and total error was 16.41%. In accordance with the results obtained, it was seen that SOM neural networks with the number of neurons determined could be used effectively in filtering the airborne Lidar data.

Anahtar Kelimeler

Lidar, Artificial neural networks, Self organizing maps, Filtering

Kaynakça

• Briese, C. (2010). Extraction of digital terrain models. Vosselman, G., & Maas, H.-G.(ed) Airborne and terrestrial laser scanning (s.135–167). Dunbeath, UK: Whittles Publishing.
• Chen, Q., Wang, H., Zhang, H., Sun, M., & Liu, X. (2016). A point cloud filtering approach to generating DTMs for steep mountainous areas and adjacent residential areas. Remote sensing, 8(1), 71.
• Chen, Z., Gao, B., & Devereux, B. (2017). State-of-the-art: DTM generation using airborne LIDAR data. Sensors, 17(1), 150.
• Giampouras, P., Charou, E., & Kesidis, A. (2013). Artificial Neural Network Approach for Land Cover Classification of Fused Hyperspectral and Lidar Data. Papadopoulos, H.,
• Andreou, A.S., Iliadis, L., & Maglogiannis, I.(ed) IFIP International Conference on Artificial Intelligence Applications and Innovations (s. 255-261). Berlin, Heidelberg: Springer.
• Grebby, S., Naden, J., Cunningham, D., & Tansey, K. (2011). Integrating airborne multispectral imagery and airborne LiDAR data for enhanced lithological mapping in vegetated terrain. Remote Sensing of Environment, 115(1), 214-226.
• Kang, X., Liu, J., & Lin, X. (2014). Streaming progressive TIN densification filter for airborne LiDAR point clouds using multi-core architectures. Remote sensing, 6(8), 7212-7232.
• Kayı, A., Erdoğan, M., & Eker, O. (2015). OPTECH HA-500 ve RIEGL LMS-Q1560 ile gerçekleştirilen LİDAR test sonuçları. Harita Dergisi, 153(2), 42-46.
• Kohonen, T. (1990). The Self-Organizing Map. Proceedings of the IEEE, 78, 1464-1480.
• Kohonen, T. (2001). Self-organizing maps. Berlin, Almanya: Springer.
• Kwon, S. K., Jung, H. S., Baek, W. K., & Kim, D. (2017). Classification of forest vertical structure in south Korea from aerial orthophoto and lidar data using an artificial neural network. Applied Sciences, 7(10), 1046.
• Mongus, D., & Žalik, B. (2014). Computationally efficient method for the generation of a digital terrain model from airborne LiDAR data using connected operators. IEEE journal of selected topics in applied earth observations and remote sensing, 7(1), 340-351.
• Morris, J. T., Porter, D., Neet, M., Noble, P. A., Schmidt, L., Lapine, L. A., & Jensen, J. R. (2005). Integrating LIDAR elevation data, multi‐spectral imagery and neural network modelling for marsh characterization. International Journal of Remote Sensing, 26(23), 5221-5234.
• Salah, M., Trinder, J., & Shaker, A. (2009). Evaluation of the self‐organizing map classifier for building detection from lidar data and multispectral aerial images. Journal of Spatial Science, 54(2), 15-34.
• Şen, A., Süleymanoğlu, B., & Soycan, M. (2020). Unsupervised extraction of urban features from airborne lidar data by using self-organizing maps. Survey Review, 52(371), 150-158.
• Sithole, G., & Vosselman, G. (2003). Report: ISPRS Comparison of Filters. Commission III, Working Group 3. https://www.itc.nl/isprs/wgIII-3/filtertest/report05082003.pdf.
• Sithole, G., & Vosselman, G. (2004). Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds. ISPRS journal of photogrammetry and remote sensing, 59(1-2), 85-101.
• Skupin, A., & Agarwal, P. (2008). Introduction: What is a Self-Organizing Map? Agarwal, P., & Skupin, A.(ed) Self-organising maps: Applications in geographic information science (s. 1-20). Chichester, UK: John Wiley & Sons.
• Yan, J., & Thill, J.-C. (2008). Visual exploration of spatial interaction data with self-organizing maps. Agarwal, P., & Skupin, A.(ed) Self-organising maps: Applications in geographic information science (s. 67-85). Chichester, UK: John Wiley & Sons.
• Zaletnyik, P., Laky, S., & Toth, C. (2010). LiDAR waveform classification using self-organizing map. ASPRS, 28-30.
• Zhang, J., Lin, X., & Ning, X. (2013). SVM-based classification of segmented airborne LiDAR point clouds in urban areas. Remote Sensing, 5(8), 3749-3775.