Resul ÇÖMERT, Dilek Küçük MATCI, Uğur AVDAN

DETECTION OF COLLAPSED BUILDING FROM UNMANNED AERIAL VEHICLE DATA WITH OBJECT BASED IMAGE CLASSIFICATION

Buildings are most affected the objects by earthquake disaster. Detection of collapsed buildings after an earthquake is important both for determining the current situation and quick response. Unmanned aerial vehicles that have evolved in recent years, can provide very high resolution images of the earth surface using camera systems attached to them. Information for the intended purpose can be obtained through the products produced from these images. In this study, collapsed buildings were detected in the area where high-resolution images were obtained whit unmanned aerial vehicle in 2015 and 2014. Building detection process was made based on a scenario events. In this context, 2015 images were taken before the earthquake and 2014 images were taken after the earthquake. The images of both years were processed separately to produce the digital elevation model and orthophoto image of the study area. building of the study area were obtained by applying the object-based classification process to the generated data. 11 buildings which were available in the area in 2015 and not available in the area in 2014, were detected successfully comparison of building classes of two years.

Anahtar Kelimeler:

Collapsed Building, Object Based Classification, Remote Sensing, UAV

PDF

___

[1] Sumer, E. and M. Turker, Building damage detection from post-earthquake aerial images using watershed segmentation in Golcuk, Turkey. International Society for Photogrammetry and Remote Sensing ISPRS, 2004: p. 642-647.
[2] Jiang, N., et al., Object-oriented buinding extraction by DSM and very high-resolution orthoimages. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008. 37: p. 441-446.
[3] Yano, Y., et al. Building damage detection of the 2003 Bam, Iran earthquake using QuickBird images. in Proceedings of the 25th Asian Conference on Remote Sensing. 2004. Citeseer.
[4] Safarlou, F., Change Detectıon of Buildings from High Resolution Satellite Imagery And Existing Map Data Using Object Based Classification. 2015.
[5] Teo, T.-A. and L.-C. Chen. Object-based building detection from LiDAR data and high resolution satellite imagery. in Proceedings of the 25th Asian Conference on Remote Sensing. 2004.
[6] Rutzinger, M., et al. Object-based building detection based on airborne laser scanning data within GRASS GIS environment. in Proceedings of UDMS. 2006.
[7] Miliaresis, G. and N. Kokkas, Segmentation and object-based classification for the extraction of the building class from LIDAR DEMs. Computers & Geosciences, 2007. 33(8): p. 1076-1087.
[8] Hunt, E.R., et al., Acquisition of NIR-green-blue digital photographs from unmanned aircraft for crop monitoring. Remote Sensing, 2010. 2(1): p. 290-305.
[9] Woebbecke, D.M., et al., Color indices for weed identification under various soil, residue, and lighting conditions. Transactions of the ASAE, 1995. 38(1): p. 259-269.
[10] Hunt Jr, E.R., et al., A visible band index for remote sensing leaf chlorophyll content at the canopy scale. International Journal of Applied Earth Observation and Geoinformation, 2013. 21: p. 103-112.
[11] Baatz, M., et al., eCognition user guide. Definiens Imaging GmbH, Munich, Germany, 2004.
[12] Tucker, C.J., Red and photographic infrared linear combinations for monitoring vegetation. Remote sensing of Environment, 1979. 8(2): p. 127-150.
[13] Gitelson, A.A., et al., Novel algorithms for remote estimation of vegetation fraction. Remote sensing of Environment, 2002. 80(1): p. 76-87.
[14] Mao, W., Y. Wang, and Y. Wang. Real-time detection of between-row weeds using machine vision. in 2003 ASAE Annual Meeting. 2003. American Society of Agricultural and Biological Engineers.