Indirect estimation of building floors using aerial photogrammetry and street-level 360° imagery for seismic risk assessment
DOI:
https://doi.org/10.21754/tecnia.v35i2.2538Palabras clave:
Building floor estimation, nDSM, seismic risk, Deep LearningResumen
Building data collection is a key component of urban planning and disaster risk management. In this study, two semi-automated methods for estimating the number of floors in buildings are compared: one based on aerial images captured by drones, and another using 360° images obtained from Google Street View. For the photogrammetric approach, three-dimensional models and photogrammetric products were generated from aerial images. The results showed that accuracy in floor estimation was highest for single-story buildings (92%) and lowest for five-story buildings (66%). Regarding the analysis using 360° images, classification models alone achieved an accuracy greater than 80% for all proposed classes, although they exhibited limitations in accurately identifying vacant lots and buildings taller than five floors. Additionally, several machine learning models were implemented, among which the Random Forest model achieved the highest accuracy, with a value of 0.861.
Descargas
Citas
[1] A. Erener, G. Sarp, and M. I. Karaca, “An approach to urban building height and floor estimation by using LiDAR data,” Arabian Journal of Geosciences, vol. 13, no. 19, p. 1005, 2020, doi: 10.1007/s12517-020-06006-1.
[2] X. Ma and others, “Mapping fine-scale building heights in urban agglomeration with spaceborne lidar,” Remote Sensing of Environment, vol. 285, p. 113392, 2023, doi: 10.1016/j.rse.2022.113392.
[3] J. Lao and others, “Retrieving building height in urban areas using ICESat-2 photon-counting LiDAR data,” International Journal of Applied Earth Observation and Geoinformation, vol. 104, p. 102596, 2021, doi: 10.1016/j.jag.2021.102596.
[4] I. da Silva, W. Ibañez, and G. Poleszuk, “Experience of Using Total Station and GNSS Technologies for Tall Building Construction Monitoring,” in Facing the Challenges in Structural Engineering, H. Rodrigues, A. Elnashai, and G. M. Calvi, Eds., Cham: Springer International Publishing, 2018, pp. 471–486.
[5] G. Liasis and S. Stavrou, “Satellite images analysis for shadow detection and building height estimation,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 119, pp. 437–450, 2016, doi: 10.1016/j.isprsjprs.2016.07.006.
[6] X. Li, Y. Zhou, P. Gong, K. C. Seto, and N. Clinton, “Developing a method to estimate building height from Sentinel-1 data,” Remote Sensing of Environment, vol. 240, p. 111705, 2020, doi: 10.1016/j.rse.2020.111705.
[7] M. Liu, P. Wang, K. Hu, C. Gu, S. Jin, and L. Chen, “A Method for Extracting High-Resolution Building Height Information in Rural Areas Using GF-7 Data,” Sensors, vol. 24, no. 18, 2024, doi: 10.3390/s24186076.
[8] F. Qi, J. Z. Zhai, and G. Dang, “Building height estimation using Google Earth,” Energy and Buildings, vol. 118, pp. 123–132, 2016, doi: 10.1016/j.enbuild.2016.02.044.
[9] Y. Cao and X. Huang, “A deep learning method for building height estimation using high-resolution multi-view imagery over urban areas: A case study of 42 Chinese cities,” Remote Sensing of Environment, vol. 264, p. 112590, 2021, doi: 10.1016/j.rse.2021.112590.
[10] Y. Yan and B. Huang, “Estimation of building height using a single street view image via deep neural networks,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 192, pp. 83–98, 2022, doi: 10.1016/j.isprsjprs.2022.08.006.
[11] Z. Xu, F. Zhang, Y. Wu, Y. Yang, and Y. Wu, “Building height calculation for an urban area based on street view images and deep learning,” Computer-Aided Civil and Infrastructure Engineering, vol. 38, no. 7, pp. 892–906, 2023, doi: 10.1111/mice.12906.
[12] CISMID, “Estudio de microzonificación sísmica y evaluación de la vulnerabilidad de edificaciones en el distrito de Villa El Salvador, Lima,” Universidad Nacional de Ingeniería, Lima, Perú, Informe técnico, 2011.
[13] B. Adriano et al., “Tsunami Inundation Mapping in Lima, for Two Tsunami Source Scenarios,” Journal of Disaster Research, vol. 8, no. 2, pp. 274–284, 2013, doi: 10.20965/jdr.2013.p0274.
[14] R. Iskandar et al., “Estimating urban seismic damages and debris from building-level simulations: application to the city of Beirut, Lebanon,” Bulletin of Earthquake Engineering, vol. 21, no. 13, pp. 5949–5990, Oct. 2023, doi: 10.1007/s10518-023-01768-x.
[15] E. Berny, C. Avelar, M. A. Salgado-Gálvez, and M. Ordaz, “Estimating emergency costs for earthquakes and floods in Central Asia based on modelled losses,” Natural Hazards and Earth System Sciences, vol. 24, no. 1, pp. 53–62, 2024, doi: 10.5194/nhess-24-53-2024.
[16] Peter Drenan and Shandi Treloar, “Debris Estimation and Forecasting Tools and Approaches,” in A Debris Management Handbook for State and Local DOTs and Departments of Public Works, National Academies of Sciences, Engineering, and Medicine, Ed., Washington, DC: The National Academies Press, 2014, pp. 14–20. doi: 10.17226/22239.
[17] J. Li, X. Huang, L. Tu, T. Zhang, and L. Wang, “A review of building detection from very high resolution optical remote sensing images,” GIScience and Remote Sensing, vol. 59, no. 1. Taylor and Francis Ltd., pp. 1199–1225, 2022. doi: 10.1080/15481603.2022.2101727.
[18] M. Buyukdemircioglu, R. Can, S. Kocaman, and M. Kada, “DEEP LEARNING BASED BUILDING FOOTPRINT EXTRACTION FROM VERY HIGH RESOLUTION TRUE ORTHOPHOTOS AND NDSM,” in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, May 2022, pp. 211–218. doi: 10.5194/isprs-annals-V-2-2022-211-2022.
[19] J. Salinas, M. Diaz, C. Zavala, M. Matsuoka, I. Inocente, and F. Garcia, “Automated Building Structural Parameters Extraction for Seismic Risk Assessment in Villa El Salvador Area,” JDR, vol. 20, no. 6, pp. 959–974, Dec. 2025, doi: 10.20965/jdr.2025.p0959.
[20] CENEPRED, “Escenario de riesgo por sismo y tsunami para Lima y Callao.” Dec. 2020. [Online]. Available: https://sigrid.cenepred.gob.pe/sigridv3/storage/biblioteca//10354_escenario-de-riesgo-por-sismo-y-tsunami-para-lima-y-callao.pdf
[21] A. Quesquen, M. Estrada, F. Garcia, C. Davila, B. Puchoc, and S. Koshimura, “Systematization of geospatial information of urban occupation in Metropolitan Lima-Callao for the evaluation of the tsunami threat by different seismic scenarios,” 2025.
[22] C. Jimenez et al., “Seismic Source of 1746 Callao Earthquake from Tsunami Numerical Modeling,” Journal of Disaster Research, vol. 8, no. 2, pp. 266–273, 2013, doi: 10.20965/jdr.2013.p0266.
[23] M. Diaz, C. Zavala, M. Estrada, and M. Matsuoka, “Characterization of the Structural Typologies of Buildings in the Lima Metropolitan Area,” Journal of Disaster Research, vol. 18, no. 4, pp. 329–337, June 2023, doi: 10.20965/jdr.2023.p0329.
[24] SENCICO, “Technical Standard of Buildings E.030: Earthquake-resistant Design.” 2018.
[25] C. Zavala, Z. Aguilar, and M. Estrada, “Evaluation of SRSND simulator against fragility curves for Pisco Quake,” in 8th Center for Urban Earthquake Engineering Conference, Tokyo, Japan, Mar. 2011.
[26] CISMID, “ESTUDIOS DE MICROZONIFICACIÓN GEOTÉCNICA SÍSMICA Y EVALUACIÓN DEL RIESGO EN ZONAS UBICADAS EN LOS DISTRITOS DE CARABAYLLO Y EL AGUSTINO (PROVINCIA Y DEPARTAMENTO DE LIMA); DISTRITO DEL CUSCO (PROVINCIA Y DEPARTAMENTO DEL CUSCO); Y DISTRITO DE ALTO SELVA ALEGRE (PROVINCIA Y DEPARTAMENTO DE AREQUIPA),” Universidad Nacional de Ingeniería, Lima, Perú, Informe técnico, 2013.
[27] CISMID, “CONVENIO DE COLABORACIÓN INTERINSTITUCIONAL ENTRE EL MINISTERIO DE VIVIENDA, CONSTRUCCIÓN Y SANEAMIENTO Y LA UNIVERSIDAD NACIONAL DE INGENIERÍA PARA LA ELABORACIÓN DE LOS ESTUDIOS DE MICROZONIFICACIÓN SÍSMICA Y ANÁLISIS DE RIESGO EN ZONAS DE ESTUDIOS UBICADAS EN LAS ÁREAS URBANAS DE LAS MUNICIPALIDADES DISTRITALES DE PUEBLO LIBRE (LIMA), LA VICTORIA (LIMA), TRUJILLO (LA LIBERTAD) Y VÍCTOR LARCO HERRERA (LA LIBERTAD).,” Universidad Nacional de Ingeniería, Lima, Perú, Informe técnico, 2018.
[28] CISMID, “ANÁLISIS DE RIESGO EN ZONAS URBANAS DEL DISTRITO DE SAN ISIDRO,” Universidad Nacional de Ingeniería, Lima, Perú, Informe técnico, 2019.
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 TECNIA
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Los artículos publicados por TECNIA pueden ser compartidos a través de la licencia pública internacional Creative Commons: CC BY 4.0. Permisos lejos de este alcance pueden ser consultados a través del correo tecnia@uni.edu.pe
