Propuesta del método de similitud diferencial ponderada para la detección de asbesto en imágenes hiperespectrales

Autores/as

DOI:

https://doi.org/10.61799/2216-0388.2328

Palabras clave:

Asbesto-cemento, imágenes hiperespectrales, similitud diferencial espectral, sensado remoto

Resumen

Según la OMS, más de 100 mil personas mueren al año por cánceres relacionados con el asbesto, de los cuales varios son atribuidos a la exposición a este material en el hogar. Asimismo, considerando los desafíos computacionales asociados a la detección de materiales en imágenes hiperespectrales y la necesidad de mejorar la precisión de los métodos basados en distancia espectral, este trabajo tiene por objetivo proponer como contribución un nuevo método denominado Similitud Diferencial Ponderada (WDS, por sus siglas en inglés), el cual se basa en la ponderación porcentual de la diferencia absoluta entre la firma espectral de asbesto-cemento y la firma a clasificar. Para el desarrollo del presente trabajo se realizó una adaptación de la metodología CRISP-DM a cuatro fases: F1. Entendimiento del negocio y de los datos, F2. Preparación de los datos, F3. Modelado y evaluación y F4. Despliegue del modelo. Como resultados, la capacidad de diferenciación del asbesto-cemento por parte del método propuesto fue evaluada con 1500 firmas espectrales pertenecientes a seis materiales, penalizando los pesos de las bandas 50 a 170 de las 380 consideradas. Adicionalmente, las firmas fueron divididas en conjuntos de entrenamiento y prueba mediante una proporción 80/20, obteniendo para WDS una exactitud de 99.7 %, precisión de 98.0 %, recall de 100 % y F1-score de 99.0 %, frente a 97.7 %, 87.5 %, 100 % y 93.3 % obtenidos por SDS, respectivamente. Como conclusión, los resultados obtenidos, particularmente la menor cantidad de falsos positivos, evidencian una mejor capacidad de generalización del método WDS frente a SDS al ser aplicado sobre firmas espectrales no utilizadas durante el ajuste.

Descargas

Los datos de descarga aún no están disponibles.

Biografía del autor/a

  • Gabriel Elias Chanchi, Universidad de Cartagena, Cartagena, Colombia.

    Profesor de la Facultad de Ingeniería de la Universidad de Cartagena

  • Manuel Alejandro Ospina-Alarcón, Universidad de Cartagena, Cartagena de Indias, Colombia

    Profesor de la Facultad de Ingeniería de la Universidad de Cartagena

  • Manuel Saba, Universidad de Cartagena, Cartagena de Indias, Colombia

    Profesor de la Facultad de Ingeniería de la Universidad de Cartagena

Referencias

[1] W. G. Rees, Physical principles of remote sensing, 3rd ed. Cambridge University Press, 2012. doi: 10.1017/CBO9781139017411.

[2] N. L. Vásconez and H. C. Sevilla, “Uso de los sensores remotos en mediciones forestales,” ESJ, vol. 14, no. 15, p. 58, May 2018, doi: 10.19044/esj.2018.v14n15p58.

[3] S. J. Hart and T. T. Veblen, “Detection of spruce beetle-induced tree mortality using high- and medium-resolution remotely sensed imagery,” Remote Sensing of Environment, vol. 168, pp. 134–145, Oct. 2015, doi: 10.1016/j.rse.2015.06.015.

[4] J. A. Sobrino, M. Gómez, J. C. Jiménez-Muñoz, and A. Olioso, “Application of a simple algorithm to estimate daily evapotranspiration from NOAA–AVHRR images for the Iberian Peninsula,” Remote Sensing of Environment, vol. 110, no. 2, pp. 139–148, Sep. 2007, doi: 10.1016/j.rse.2007.02.017.

[5] M. I. Abdulraheem, W. Zhang, S. Li, A. J. Moshayedi, A. A. Farooque, and J. Hu, “Advancement of Remote Sensing for Soil Measurements and Applications: A Comprehensive Review,” Sustainability, vol. 15, no. 21, p. 15444, Oct. 2023, doi: 10.3390/su152115444.

[6] S. A. Jaywant and K. M. Arif, “Remote Sensing Techniques for Water Quality Monitoring: A Review,” Sensors, vol. 24, no. 24, p. 8041, Dec. 2024, doi: 10.3390/s24248041.

[7] K. Jindo et al., “Potential utilization of satellite remote sensing for field-based agricultural studies,” Chem. Biol. Technol. Agric., vol. 8, no. 1, p. 58, Dec. 2021, doi: 10.1186/s40538-021-00253-4.

[8] Q. Li, “Application of Unmanned Aerial Vehicle Remote Sensing in Engineering Measurement,” Rem Sens, vol. 9, no. 2, p. 42, Oct. 2020, doi: 10.18282/rs.v9i2.1372.

[9] S. K. Phang, T. H. A. Chiang, A. Happonen, and M. M. L. Chang, “From Satellite to UAV-Based Remote Sensing: A Review on Precision Agriculture,” IEEE Access, vol. 11, pp. 127057–127076, 2023, doi: 10.1109/ACCESS.2023.3330886.

[10] Riefda Novikarany, “Benefits of Remote Sensing for Environmental Monitoring,” IJIS, vol. 4, no. 2, pp. 445–454, Feb. 2025, doi: 10.55927/ijis.v4i2.19.

[11] L. Gao and R. T. Smith, “Optical hyperspectral imaging in microscopy and spectroscopy – a review of data acquisition,” J. Biophoton., vol. 8, no. 6, pp. 441–456, Jun. 2015, doi: 10.1002/jbio.201400051.

[12] M. E. Klein, B. J. Aalderink, R. Padoan, G. De Bruin, and T. A. G. Steemers, “Quantitative Hyperspectral Reflectance Imaging,” Sensors, vol. 8, no. 9, pp. 5576–5618, Sep. 2008, doi: 10.3390/s8095576.

[13] G. Lu and B. Fei, “Medical hyperspectral imaging: a review,” J. Biomed. Opt., vol. 19, no. 1, p. 010901, Jan. 2014, doi: 10.1117/1.JBO.19.1.010901.

[14] B. Rasti et al., “Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox,” IEEE Geosci. Remote Sens. Mag., vol. 8, no. 4, pp. 60–88, Dec. 2020, doi: 10.1109/MGRS.2020.2979764.

[15] R. M. Willett, M. F. Duarte, M. A. Davenport, and R. G. Baraniuk, “Sparsity and Structure in Hyperspectral Imaging: Sensing, Reconstruction, and Target Detection,” IEEE Signal Process. Mag., vol. 31, no. 1, pp. 116–126, Jan. 2014, doi: 10.1109/MSP.2013.2279507.

[16] J. Lalwani, D. Linnet, M. Vetrivelan, K. H. Venkat, R. Shaik, and B. Jajodia, “Hybrid quantum-classical solution for automated labeling and validation,” in Quantum Information Science, Sensing, and Computation XVII, Proc. SPIE, vol. 13451, Art. no. 1345107, May 2025, doi: 10.1117/12.3053743.

[17] S. A. Rodriguez Gonzalez, M. Shimoni, J. Plaza, A. Plaza, I. Renhorn, and J. Ahlberg, “The detection of concealed targets in woodland areas using hyperspectral imagery,” ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., vol. IV-3/W2-2020, pp. 29–33, Oct. 2020, doi: 10.5194/isprs-annals-IV-3-W2-2020-29-2020.

[18] Y. Sun et al., “Hyperspectral Classification of Hazardous Materials Based on Deep Learning,” Sustainability, vol. 15, no. 9, p. 7653, May 2023, doi: 10.3390/su15097653.

[19] S. Thongrom et al., “A Comprehensive Framework for the Development of a Compact, Cost-Effective, and Robust Hyperspectral Camera Using COTS Components and a VPH Grism,” Sensors, vol. 25, no. 12, p. 3631, Jun. 2025, doi: 10.3390/s25123631.

[20] Q. Fang, Z. Wang, J. Wang, and L. Zhang, “ARM-Net: A Tri-Phase Integrated Network for Hyperspectral Image Compression,” Sensors, vol. 25, no. 6, p. 1843, Mar. 2025, doi: 10.3390/s25061843.

[21] X.-H. Han, J. Wang, and H. Jiang, “Recent Advancements in Hyperspectral Image Reconstruction from a Compressive Measurement,” Sensors, vol. 25, no. 11, p. 3286, May 2025, doi: 10.3390/s25113286.

[22] O. Lim, S. Mancini, and M. Dalla Mura, “Feasibility of a Real-Time Embedded Hyperspectral Compressive Sensing Imaging System,” Sensors, vol. 22, no. 24, p. 9793, Dec. 2022, doi: 10.3390/s22249793.

[23] J. Transon, R. D’Andrimont, A. Maugnard, and P. Defourny, “Survey of Hyperspectral Earth Observation Applications from Space in the Sentinel-2 Context,” Remote Sensing, vol. 10, no. 2, p. 157, Jan. 2018, doi: 10.3390/rs10020157.

[24] M. Díaz, R. Guerra, P. Horstrand, S. López, J. F. López, and R. Sarmiento, “Towards the Concurrent Execution of Multiple Hyperspectral Imaging Applications by Means of Computationally Simple Operations,” Remote Sensing, vol. 12, no. 8, p. 1343, Apr. 2020, doi: 10.3390/rs12081343.

[25] Z. Khan, S.-C. Yoon, and S. M. Bhandarkar, “Deep Learning Model Compression and Hardware Acceleration for High-Performance Foreign Material Detection on Poultry Meat Using NIR Hyperspectral Imaging,” Sensors, vol. 25, no. 3, p. 970, Feb. 2025, doi: 10.3390/s25030970.

[26] M. E. Paoletti, J. M. Haut, N. S. Pereira, J. Plaza, and A. Plaza, “Ghostnet for Hyperspectral Image Classification,” IEEE Trans. Geosci. Remote Sensing, vol. 59, no. 12, pp. 10378–10393, Dec. 2021, doi: 10.1109/TGRS.2021.3050257.

[27] D. W. Kamp, “Asbestos-induced lung diseases: an update,” Translational Research, vol. 153, no. 4, pp. 143–152, Apr. 2009, doi: 10.1016/j.trsl.2009.01.004.

[28] W. A. Y. Mir et al., “Asbestos-Related Diseases and Its Impact on Health: An Updated Review Article,” Curr Pulmonol Rep, vol. 12, no. 4, pp. 244–255, Oct. 2023, doi: 10.1007/s13665-023-00324-x.

[29] G. Bonifazi, G. Capobianco, S. Serranti, S. Malinconico, and F. Paglietti, “Asbestos detection in construction and demolition waste adopting different classification approaches based on short wave infrared hyperspectral imaging,” Detritus, no. 20, pp. 90–99, Aug. 2022, doi: 10.31025/2611-4135/2022.15211.

[30] G. Bonifazi et al., “Asbestos detection in construction and demolition waste by different classification methods applied to short-wave infrared hyperspectral images,” Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 307, p. 123672, Feb. 2024, doi: 10.1016/j.saa.2023.123672.

[31] M. Krówczyńska and E. Wilk, “Hazardous waste in the Anthropocene: The comparative methods for asbestos roofs detection to assess the environmental risk,” The Anthropocene Review, vol. 11, no. 2, pp. 367–383, Aug. 2024, doi: 10.1177/20530196231207981.

[32] M. Hikuwai, N. Patorniti, A. Vieira, G. Frangioudakis Khatib, and R. Stewart, “Artificial Intelligence for the Detection of Asbestos Cement Roofing: An Investigation of Multi-Spectral Satellite Imagery and High-Resolution Aerial Imagery,” Sustainability, vol. 15, no. 5, p. 4276, Feb. 2023, doi: 10.3390/su15054276.

[33] F. Frassy et al., “Mapping Asbestos-Cement Roofing with Hyperspectral Remote Sensing over a Large Mountain Region of the Italian Western Alps,” Sensors, vol. 14, no. 9, pp. 15900–15913, Aug. 2014, doi: 10.3390/s140915900.

[34] G. E. Chanchí-Golondrino, M. A. Ospina-Alarcón, and M. Saba, “Proposal of a computational method for asbestos detection in hyperspectral images based on the identification of prominent peaks in the spectral signature,” rev. investig. desarro. innov, vol. 15, no. 1, pp. 119–138, Mar. 2025, doi: 10.19053/uptc.20278306.v15.n1.2025.19183.

[35] G. E. Chanchí Golondrino, M. Saba, and M. A. Ospina Alarcón, “Method for asbestos detection in hyperspectral images based on the approximate components of the wavelet transform and spectral differential similarity,” RCTA, vol. 2, no. 46, pp. 68–77, Jul. 2025, doi: 10.24054/rcta.v2i46.3521.

[36] G. E. Chanchí-Golondrino, M. A. Ospina-Alarcón, and M. Saba, “Detection of water bodies in hyperspectral images using spectral differential similarity and neural networks,” Entramado, vol. 21, no. 2, pp. 1–16, e-12876, 2025, doi: 10.18041/1900-3803/entramado.2.12876.

[37] J. Abasova, P. Tanuska, and S. Rydzi, “Big Data—Knowledge Discovery in Production Industry Data Storages—Implementation of Best Practices,” Applied Sciences, vol. 11, no. 16, p. 7648, Aug. 2021, doi: 10.3390/app11167648.

[38] H. A. Acuña-Cid, E. Ahumada-Tello, Ó. O. Ovalle-Osuna, R. Evans, J. E. Hernández-Ríos, and M. A. Zambrano-Soto, “CRISP-NET: Integration of the CRISP-DM Model with Network Analysis,” Mach. Learn. Knowl. Extr., vol. 7, no. 3, Art. no. 101, Sep. 2025, doi: 10.3390/make7030101.

[39] Z. Ma, B. N. Jørgensen, and Z. G. Ma, “DataPro – A Standardized Data Understanding and Processing Procedure: A Case Study of an Eco-Driving Project,” in Energy Informatics, vol. 15271, B. N. Jørgensen, Z. G. Ma, F. D. Wijaya, R. Irnawan, and S. Sarjiya, Eds. Cham: Springer Nature Switzerland, 2025, pp. 136–154, doi: 10.1007/978-3-031-74738-0_10.

[40] F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 8, pp. 3048–3061, Aug. 2021, doi: 10.1109/TKDE.2019.2962680.

[41] C. Schröer, F. Kruse, and J. M. Gómez, “A Systematic Literature Review on Applying CRISP-DM Process Model,” Procedia Computer Science, vol. 181, pp. 526–534, 2021, doi: 10.1016/j.procs.2021.01.199.

[42] S. A. El_Rahman, “Big Data Analysis: Hyperspectral Image Processing for Agriculture Applications,” Int. J. Comput. Digit. Syst., vol. 5, no. 4, pp. 315–323, Jul. 2016, doi: 10.12785/ijcds/050403.

[43] Z. F. Merzah and H. S. Jaber, “Assessment of Atmospheric Correction Methods for Hyperspectral Remote Sensing Imagery Using Geospatial Techniques,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 745, no. 1, p. 012123, Mar. 2020, doi: 10.1088/1757-899X/745/1/012123.

[44] Y. Xing and R. B. Gomez, “Hyperspectral image analysis using ENVI (environment for visualizing images),” in Geo-Spatial Image and Data Exploitation II, W. E. Roper, Ed., Proc. SPIE, vol. 4383, pp. 79–86, Jun. 2001, doi: 10.1117/12.428244.

Publicado

2026-09-01

Número

Sección

Artículo Originales

Cómo citar

[1]
Chanchi, G.E. et al. 2026. Propuesta del método de similitud diferencial ponderada para la detección de asbesto en imágenes hiperespectrales. Mundo FESC. 16, 36 (Sep. 2026). DOI:https://doi.org/10.61799/2216-0388.2328.