The impact of geometric features on the detection of water body from point clouds

Year 2024, Volume: 14 Issue: 1, 29 - 44, 15.03.2024

Samed Özdemir , Fevzi Karslı

https://doi.org/10.17714/gumusfenbil.1361716

Abstract

High-resolution remote sensing imagery plays a strategic role in critical applications such as water resource management, water quality monitoring, and emergency responses to natural disasters for the quick and accurate identification and extraction of water bodies. However, traditional water body extraction methods present various challenges, particularly in the selection of image texture and characteristic features. In this study, a methodology is proposed that combines geometric features extracted from point cloud data with spectral information obtained from aerial photographs to more effectively define and extract the boundaries of water bodies. The geometric features generated from three-dimensional (3D) structure tensors are merged with the spectral information produced by the sensor system, and the well-known Random Forest (RF) classifier suitable for high-dimensional data, speed, and resistance to overfitting is used for training in water body detection. The effectiveness of the methodology developed in Matlab has been tested over four different locations in Turkey with varying topographic and vegetative characteristics. When the accuracy analysis of the detected water body boundaries is evaluated through the F-Score, the following were obtained: 85.7% for Study Area-1, 76.6% for Study Area-1 River, 93.7% for Study Area-2, 94.9% for Study Area-3, and 73.6% for Study Area-4. The study demonstrates that the presented methodology is applicable across different spatial scales and sensor types and carries potential for comprehensive uses in environmental and hydrological research.

Keywords

Point cloud, Random forest, Digital elevation model, Classification, Water body extraction

Nokta bulutu verisi ile su kütlesi tespitinde geometrik özniteliklerin etkisi

Abstract

Yüksek çözünürlüklü uzaktan algılama görüntülerinden su kütlelerinin hızlı ve doğru bir şekilde tespit edilmesi ve çıkarılması, su kaynakları yönetimi, su kalitesi izleme, doğal afet acil müdahaleleri gibi kritik uygulama alanlarında stratejik bir öneme sahiptir. Bununla birlikte, geleneksel su kütle çıkarma yöntemleri, özellikle görüntü dokusu ve karakteristik özelliklerin seçilmesi konusunda çeşitli zorluklar sunmaktadır. Bu çalışmada, nokta bulutu verilerinden çıkarılan geometrik öznitelikler ve hava fotoğraflarından alınan spektral bilgileri bir araya getirerek, su kütlelerinin sınırlarının daha etkin bir şekilde tanımlanmasını ve çıkarılmasını sağlayan bir metodoloji önerilmektedir. Üç boyutlu (3B) yapı tensöründen yararlanılarak nokta bulutlarından üretilen geometrik öznitelikler algılayıcı sistemin ürettiği spektral bilgiler ile birleştirilerek, yüksek boyutlu verilere uygunluğu, hızı ve aşırı uyuma direnci ile bilinen Rastgele Orman (RO) sınıflandırıcısı su kütlelerinin tespiti için eğitimde kullanılmıştır. Matlab ortamında geliştirilen metodolojinin etkinliği, Türkiye’de topografik ve bitkisel özellikleri farklı dört farklı lokasyon üzerinde test edilmiştir. Sınıflandırma işlemi ile tespit edilen su kütlesi sınırlarının doğruluk analizi F-Skoru üzerinden değerlendirildiğinde, Çalışma Alanı-1 için: %85.7, Çalışma Alanı-1 Akarsu için %76.6, Çalışma Alanı-2 için %93.7, Çalışma Alanı-3 için %94.9, ve Çalışma Alanı-4 için %73.6, olarak elde edilmiştir. Çalışma, sunulan metodolojinin farklı mekânsal ölçekler ve sensör türleri için uygulanabilir olduğunu ve çevresel ve hidrolojik araştırmalarda geniş kapsamlı kullanımlar için potansiyel taşıdığını ortaya koymaktadır.

Keywords

Nokta bulutu, Rastgele orman, Sayısal yükseklik modeli, Sınıflandırma, Su kütlesi çıkarımı

References

• Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2281. https://doi.org/10.1109/TPAMI.2012.120
• Axelsson, P. (2000). DEM generation from laser scanner data using adaptive TIN models. International Archives of Photogrammetry and Remote Sensing, 33, 110–117.
• Bandini, F., Sunding, T. P., Linde, J., Smith, O., Jensen, I. K., Köppl, C. J., Butts, M., & Bauer-Gottwein, P. (2020). Unmanned Aerial System (UAS) observations of water surface elevation in a small stream: Comparison of radar altimetry, LIDAR and photogrammetry techniques. Remote Sensing of Environment, 237, 111487. https://doi.org/10.1016/j.rse.2019.111487
• Belgiu, M., & Drăgut, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
• Bentley, J. L. (1975). Multidimensional binary search trees used for associative searching, Communications of the ACM, 18(9) 509-517.
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
• Canaz, S., Karsli, F., Guneroglu, A., & Dihkan, M. (2015). Automatic boundary extraction of inland water bodies using LiDAR data. Ocean and Coastal Management, 118, 158–166. https://doi.org/10.1016/j.ocecoaman.2015.07.024
• Guo, B., Huang, X., Zhang, F., & Sohn, G. (2015). Classification of airborne laser scanning data using JointBoost. ISPRS Journal of Photogrammetry and Remote Sensing, 100, 71–83. https://doi.org/10.1016/j.isprsjprs.2014.04.015
• Hartley, R. & Zisserman, A. (2004). Multiple view geometry in computer vision (2nd Ed.). Cambridge University Press.
• Kavzoglu, T., & Tonbul, H. (2018). An experimental comparison of multi-resolution segmentation, slic and k-means clustering for object-based classification of vhr imagery. International Journal of Remote Sensing, 39(18), 6020–6036. https://doi.org/10.1080/01431161.2018.1506592
• Legleiter, C. J. (2012). Remote measurement of river morphology via fusion of LIDAR topography and spectrally based bathymetry, Earth Surface Processes and Landforms, 37(5), 499-518.
• Mazzoleni, M., Paron, P., Reali, A., Juizo, D., Manane, J., & Brandimarte, L. (2020). Testing UAV-derived topography for hydraulic modelling in a tropical environment. Natural Hazards, May. https://doi.org/10.1007/s11069-020-03963-4
• Pauly, M., Keiser, R., & Gross, M. (2003). Multi-scale feature extraction on point-sampled surfaces. EUROGRAPHICS 2003, 22(3).
• Pech-May, F., Aquino-Santos, R., & Delgadillo-Partida, J. (2023). Sentinel-1 SAR images and deep learning for water body mapping. Remote Sensing, 15(12), 3009.
• Roelens, J., Höfle, B., Dondeyne, S., Van Orshoven, J., & Diels, J. (2018). Drainage ditch extraction from airborne LiDAR point clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 146(May), 409–420. https://doi.org/10.1016/j.isprsjprs.2018.10.014
• Rutzinger, M., Rutzinger, M., Rottensteiner, F., Rottensteiner, F., & Pfeifer, N. (2009). A comparison of evaluation techniques for building extraction from airborne laser scanning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2(1), 11–20. https://doi.org/10.1109/JSTARS.2009.2012488
• Shaker, A., Yan, W. Y., & LaRocque, P. E. (2019). Automatic land-water classification using multispectral airborne LiDAR data for near-shore and river environments. ISPRS Journal of Photogrammetry and Remote Sensing, 152(July 2018), 94–108. https://doi.org/10.1016/j.isprsjprs.2019.04.005
• Smeeckaert, J., Mallet, C., David, N., Chehata, N., & Ferraz, A. (2013). Large-scale classification of water areas using airborne topographic LiDAR data. Remote Sensing of Environment, 138, 134–148. https://doi.org/10.1016/j.rse.2013.07.004
• Song, S., Liu, J., Liu, Y., Feng, G., Han, H., Yao, Y., & Du, M. (2020). Intelligent object recognition of urban water bodies based on deep learning for multi-source and multi-temporal high spatial resolution remote sensing ımagery. Sensors, 20(2), 397. https://doi.org/10.3390/s20020397
• Toscano, G. J., Gopalam, U. K., & Devarajan, V. (2014). Auto hydro break line generation using lidar elevation and intensity data. ASPRS 2014 Annual Conference: Geospatial Power in Our Pockets, Co-Located with Joint Agency Commercial Imagery Evaluation Workshop, JACIE 2014, 2009.
• Tymków, P., Jóźków, G., Walicka, A., Karpina, M., & Borkowski, A. (2019). Identification of water body extent based on remote sensing data collected with unmanned aerial vehicle. Water (Switzerland), 11(2). https://doi.org/10.3390/w11020338
• Vetter, M., Hofle, B., & Rutzinger, M. (2009). Water classification using 3D airborne laser scanning point clouds. Vermessung & Geoinformation, 2, 227–238.
• Wang, Y., Li, S., Lin, Y., & Wang, M. (2021). Lightweight deep neural network method for water body extraction from high-resolution remote sensing ımages with multisensors. Sensors, 21(21), 7397.
• Weinmann, M., Urban, S., Hinz, S., Jutzi, B., & Mallet, C. (2015). Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas. Computers and Graphics (Pergamon), 49, 47–57. https://doi.org/10.1016/j.cag.2015.01.006
• Westoby, M. J., Brasington, J., Glasser, N. F., Hambrey, M. J., & Reynolds, J. M. (2012). ‘Structure-from-Motion’photogrammetry: A low-cost, effective tool for geoscience applications. Geomorphology, 179, 300-314.
• Zheng, X., Godbout, L., Zheng, J., McCormick, C., & Passalacqua, P. (2019). An automatic and objective approach to hydro-flatten high resolution topographic data. Environmental Modelling and Software, 116(February), 72–86. https://doi.org/10.1016/j.envsoft.2019.02.007