Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas
Actualmente diversas investigaciones se han enfocado en analizar a partir de videos de alta velocidad, características de las descargas eléctricas atmosféricas con el fin de adquirir mejor comprensión del fenómeno, que conlleva entre otros aspectos el desarrollo de sistemas de protección robustos. L...
- Autores:
-
Orozco Gómez, Diego Hernando
- Tipo de recurso:
- Fecha de publicación:
- 2022
- Institución:
- Universidad Nacional de Colombia
- Repositorio:
- Universidad Nacional de Colombia
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unal.edu.co:unal/81443
- Palabra clave:
- 620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería
Image processing
Redes neuronales (computadores)
Procesamiento de imágenes
Procesamiento de señales
Descarga eléctrica atmosférica
Procesamiento imágenes
Red neuronal convolucional
Segmentación
Convolutional neural network
Detection
Image processing
Lightning
Multiplicity
Segmentation
- Rights
- openAccess
- License
- Reconocimiento 4.0 Internacional
| id |
UNACIONAL2_ebe0365c3f4b8470fb68624273a85b3b |
|---|---|
| oai_identifier_str |
oai:repositorio.unal.edu.co:unal/81443 |
| network_acronym_str |
UNACIONAL2 |
| network_name_str |
Universidad Nacional de Colombia |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| dc.title.translated.eng.fl_str_mv |
Methodological proposal for the signals and video processing applied to detection and multiplicity characterization of lightning |
| title |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| spellingShingle |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas 620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería Image processing Redes neuronales (computadores) Procesamiento de imágenes Procesamiento de señales Descarga eléctrica atmosférica Procesamiento imágenes Red neuronal convolucional Segmentación Convolutional neural network Detection Image processing Lightning Multiplicity Segmentation |
| title_short |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| title_full |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| title_fullStr |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| title_full_unstemmed |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| title_sort |
Propuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricas |
| dc.creator.fl_str_mv |
Orozco Gómez, Diego Hernando |
| dc.contributor.advisor.none.fl_str_mv |
Bolaños Martínez, Freddy Herrera Murcia, Javier Gustavo |
| dc.contributor.author.none.fl_str_mv |
Orozco Gómez, Diego Hernando |
| dc.contributor.researchgroup.spa.fl_str_mv |
Grupo de Automática de la Universidad Nacional Gaunal |
| dc.subject.ddc.spa.fl_str_mv |
620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería |
| topic |
620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería Image processing Redes neuronales (computadores) Procesamiento de imágenes Procesamiento de señales Descarga eléctrica atmosférica Procesamiento imágenes Red neuronal convolucional Segmentación Convolutional neural network Detection Image processing Lightning Multiplicity Segmentation |
| dc.subject.armarc.none.fl_str_mv |
Image processing Redes neuronales (computadores) |
| dc.subject.lemb.spa.fl_str_mv |
Procesamiento de imágenes Procesamiento de señales |
| dc.subject.proposal.spa.fl_str_mv |
Descarga eléctrica atmosférica Procesamiento imágenes Red neuronal convolucional Segmentación |
| dc.subject.proposal.eng.fl_str_mv |
Convolutional neural network Detection Image processing Lightning Multiplicity Segmentation |
| description |
Actualmente diversas investigaciones se han enfocado en analizar a partir de videos de alta velocidad, características de las descargas eléctricas atmosféricas con el fin de adquirir mejor comprensión del fenómeno, que conlleva entre otros aspectos el desarrollo de sistemas de protección robustos. La mayoría de las investigaciones han requerido de un observador que ante el suceso del evento provea un disparo manual a la cámara permitiendo almacenar la información visual del fenómeno. Por tanto, este trabajo se orientó en proponer una metodología para la detección de las descargas utilizando dos implementaciones basadas en procesamiento de señales y visión computacional, con el propósito que el sistema autónomamente sea el que suministre el disparo, apartando al observador de la realización de esta tarea. El sistema de detección basado en técnicas de procesamiento de imágenes requirió la adecuación de métodos de segmentación, representación, descripción y clasificación. El algoritmo de reconocimiento con visión computacional se implementó mediante la red neuronal convolucional EfficientNetB4. Fuera de línea, las técnicas basadas en procesamiento de imágenes suministraron una precisión del 81.81%, mientras que haciendo uso de visión computacional la precisión fue de 71.63%. Con el objeto de evaluar el desempeño en tiempo real, las técnicas de procesamiento se adaptaron en un ordenador de placa reducida correspondiente a la Raspberry Pi 3 modelo B+ obteniéndose una precisión de 86.95%. Adicionalmente, se evaluó la característica de multiplicidad la cual corresponde al número de descargas subsecuentes presentes en el canal de la descarga logrando una precisión de 66.66%. (Texto tomado de la fuente) |
| publishDate |
2022 |
| dc.date.accessioned.none.fl_str_mv |
2022-04-06T18:51:41Z |
| dc.date.available.none.fl_str_mv |
2022-04-06T18:51:41Z |
| dc.date.issued.none.fl_str_mv |
2022-04-06 |
| dc.type.spa.fl_str_mv |
Trabajo de grado - Maestría |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/masterThesis |
| dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/TM |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://repositorio.unal.edu.co/handle/unal/81443 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Nacional de Colombia |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Institucional Universidad Nacional de Colombia |
| dc.identifier.repourl.spa.fl_str_mv |
https://repositorio.unal.edu.co/ |
| url |
https://repositorio.unal.edu.co/handle/unal/81443 https://repositorio.unal.edu.co/ |
| identifier_str_mv |
Universidad Nacional de Colombia Repositorio Institucional Universidad Nacional de Colombia |
| dc.language.iso.spa.fl_str_mv |
spa |
| language |
spa |
| dc.relation.references.spa.fl_str_mv |
[1] M. A. Uman, The lightning discharge, vol. 39. 1987. [2] H. H. Goh et al., “A review of lightning protection system - Risk assessment and application,” Indones. J. Electr. Eng. Comput. Sci., vol. 8, no. 1, pp. 221–229, 2017, doi: 10.11591/ijeecs.v8.i1.pp221-229. [3] E. Krausmann, E. Renni, M. Campedel, and V. Cozzani, “Industrial accidents triggered by earthquakes, floods and lightning: Lessons learned from a database analysis,” Nat. Hazards, vol. 59, no. 1, pp. 285–300, 2011, doi: 10.1007/s11069-011-9754-3. [4] E. Renni, E. Krausmann, and V. Cozzani, “Industrial accidents triggered by lightning,” J. Hazard. Mater., vol. 184, no. 1–3, pp. 42–48, 2010, doi: 10.1016/j.jhazmat.2010.07.118. [5] D. M. Elsom, “Factors contributing to a long-term decrease in national lightning fatality rates: case study of the United Kingdom with wider implications,” Int. J. Disaster Risk Reduct., vol. 31, pp. 341–353, 2018, doi: 10.1016/j.ijdrr.2018.06.001. [6] R. L. Holle, “A summary of recent national-Scale lightning fatality studies,” Weather. Clim. Soc., vol. 8, no. 1, pp. 35–42, 2016, doi: 10.1175/WCAS-D-15-0032.1. [7] A. E. Ritenour, M. J. Morton, J. G. McManus, D. J. Barillo, and L. C. Cancio, “Lightning injury: A review,” Burns, vol. 34, no. 5, pp. 585–594, 2008, doi: 10.1016/j.burns.2007.11.006. [8] A. Necci, G. Antonioni, V. Cozzani, E. Krausmann, A. Borghetti, and C. Alberto Nucci, “A model for process equipment damage probability assessment due to lightning,” Reliab. Eng. Syst. Saf., vol. 115, pp. 91–99, 2013, doi: 10.1016/j.ress.2013.02.018. [9] Y. Yasuda, S. Yokoyama, M. Minowa, and T. Satoh, “Classification of lightning damage to wind turbine blades,” IEEJ Trans. Electr. Electron. Eng., vol. 7, no. 6, pp. 559–566, 2012, doi: 10.1002/tee.21773. [10] M. Gagné and D. Therriault, “Lightning strike protection of composites,” Prog. Aerosp. Sci., vol. 64, pp. 1–16, 2014, doi: 10.1016/j.paerosci.2013.07.002. [11] J. E. Jerauld, M. A. Uman, V. A. Rakov, K. J. Rambo, D. M. Jordan, and G. H. Schnetzer, “Measured electric and magnetic fields from an unusual cloud-to-ground lightning flash containing two positive strokes followed by four negative strokes,” J. Geophys. Res. Atmos., vol. 114, no. D19, 2009, doi: 10.1029/2008jd011660. [12] M. M. F. Saba, C. Schumann, T. A. Warner, J. H. Helsdon Jr., W. Schulz, and R. E. Orville, “Bipolar cloud-to-ground lightning flash observations,” J. Geophys. Res. Atmos., vol. 118, no. 19, pp. 11,098-11,106, 2013, doi: 10.1002/jgrd.50804. [13] Y. Tian et al., “Characteristics of a bipolar cloud-to-ground lightning flash containing a positive stroke followed by three negative strokes,” Atmos. Res., vol. 176–177, pp. 222–230, 2016, doi: 10.1016/j.atmosres.2016.02.023. [14] M. D. Tran and V. A. Rakov, “Initiation and propagation of cloud-to-ground lightning observed with a high-speed video camera,” Sci. Rep., vol. 6, no. 39521, 2016, doi: 10.1038/srep39521. [15] M. M. F. Saba et al., “Upward lightning flashes characteristics from high-speed videos,” J. Geophys. Res. Atmos., vol. 121, no. 14, pp. 8493–8505, 2016, doi: 10.1002/2016JD025137. [16] J. Herrera, C. Younes, and L. Porras, “Cloud-to-ground lightning activity in Colombia: A 14-year study using lightning location system data,” Atmos. Res., vol. 203, pp. 164–174, 2018, doi: 10.1016/j.atmosres.2017.12.009. [17] G. Diendorfer et al., “Review of CIGRE Report ‘Cloud-to-Ground Lightning Parameters Derived from Lightning Location Systems – The Effects of System Performance,’” Cigre, no. 376, 2009. [18] M. M. F. Saba et al., “High-speed video observations of positive lightning flashes to ground,” J. Geophys. Res. Atmos., vol. 115, no. D24, 2010, doi: 10.1029/2010JD014330. [19] A. M. Hussein, S. Kazazi, M. Anwar, M. Yusouf, and P. Liatos, “Characteristics of the most intense lightning storm ever recorded at the CN Tower,” J. Atmos. Solar-Terrestrial Phys., vol. 154, pp. 195–206, 2017, doi: 10.1016/j.jastp.2016.05.002. [20] A. C. V. Saraiva, M. M. F. Saba, O. Pinto Jr., K. L. Cummins, E. P. Krider, and L. Z. S. Campos, “A comparative study of negative cloud-to-ground lightning characteristics in São Paulo (Brazil) and Arizona (United States) based on high-speed video observations,” J. Geophys. Res. Atmos., vol. 115, no. D11, 2010, doi: 10.1029/2009JD012604. [21] L. S. Antunes et al., “Day-to-day differences in the characterization of lightning observed by multiple high-speed cameras,” Electr. Power Syst. Res., vol. 118, pp. 93–100, 2015, doi: 10.1016/j.epsr.2014.07.030. [22] Y. Zhang, W. Lu, J. Li, W. Dong, D. Zheng, and S. Chen, “Luminosity characteristics of leaders in natural cloud-to-ground lightning flashes,” Atmos. Res., vol. 91, no. 2–4, pp. 326–332, 2009, doi: 10.1016/j.atmosres.2008.01.013. [23] M. M. F. Saba, C. Schumann, T. A. Warner, J. H. Helsdon, and R. E. Orville, “High-speed video and electric field observation of a negative upward leader connecting a downward positive leader in a positive cloud-to-ground flash,” Electr. Power Syst. Res., vol. 118, pp. 89–92, 2015, doi: 10.1016/j.epsr.2014.06.002. [24] L. Z. S. Campos, M. M. F. Saba, O. Pinto Jr., and M. G. Ballarotti, “Waveshapes of continuing currents and properties of M-components in natural negative cloud-to-ground lightning from high-speed video observations,” Atmos. Res., vol. 84, no. 4, pp. 302–310, 2007, doi: 10.1016/j.atmosres.2006.09.002. [25] C. J. Biagi, K. L. Cummins, K. E. Kehoe, and E. P. Krider, “National Lightning Detection Network (NLDN) performance in southern Arizona, Texas, and Oklahoma in 2003-2004,” J. Geophys. Res. Atmos., vol. 112, no. 5, pp. 1–17, 2007, doi: 10.1029/2006JD007341. [26] O. Pinto, I. R. C. A. Pinto, and K. P. Naccarato, “Geographical variations of negative cloud-to-ground lightning parameters: A review,” 2012 31st Int. Conf. Light. Prot. ICLP 2012, 2012, doi: 10.1109/ICLP.2012.6344292. [27] D. De Jesus Perez-Perez, J. G. Herrera-Murcia, and E. Perez-Gonzalez, “Experimental detection efficiency evaluation for a lightning location system on a mountainous region,” 2013 Int. Symp. Light. Prot. SIPDA 2013, pp. 73–78, 2013, doi: 10.1109/SIPDA.2013.6729235. [28] N. Shimoji, S. Kuninaka, and K. Izumi, “Evaluation of the brightness of lightning channels and branches using the magnitude system: Application of astronomical photometry,” Results Phys., vol. 7, pp. 2085–2095, 2017, doi: 10.1016/j.rinp.2017.06.013. [29] K. Berger, “Blitzstrom-Parameter von Aufwartsblitzen,” Bull. Schweiz. Elektrotech, vol. 69, pp. 353–360, 1978. [30] S. P. A. Vayanganie, M. Fernando, U. Sonnadara, V. Cooray, and C. Perera, “Optical observations of electrical activity in cloud discharges,” J. Atmos. Solar-Terrestrial Phys., vol. 172, pp. 24–32, 2018, doi: 10.1016/j.jastp.2018.03.007. [31] M. Boecker, G. Corpuz, G. Hargrave, S. Das, N. Fischer, and V. Skendzic, “Line current differential relay response to a direct lightning strike on a phase conductor,” 71st Annu. Conf. Prot. Relay Eng. CPRE 2018, vol. 2018-Janua, pp. 1–12, 2018, doi: 10.1109/CPRE.2018.8349805. [32] Nasa, “Where Lightning Strikes,” 2001. https://science.nasa.gov/science-news/science-at-nasa/2001/ast05dec_1. [33] Lightning Protection Devices SA, “Características principales del proceso de descarga de un rayo.” https://www.lpdargentina.com.ar/caracteristicas-principales-del-proceso-de-descarga-de-un-rayo/. [34] J. L. Bermudez Arboleda, “Lightning Currents and Electromagnetic Fields Associated With Return Strokes To Elevated Strike Objects,” vol. 2741, p. 178, 2003. [35] A. C. V. Saraiva et al., “High-speed video and electromagnetic analysis of two natural bipolar cloud-to-ground lightning flashes,” J. Geophys. Res. Atmos., vol. 119, no. 10, pp. 6105–6127, 2014, doi: 10.1002/2013JD020974. [36] M. Azadifar, F. Rachidi, M. Rubinstein, V. A. Rakov, M. Paolone, and D. Pavanello, “Bipolar lightning flashes observed at the säntis tower: Do we need to modify the traditional classification?,” J. Geophys. Res., vol. 121, no. 23, pp. 14,117-14,126, 2016, doi: 10.1002/2016JD025461. [37] Y. Zhu, V. A. Rakov, and M. D. Tran, “Optical and electric field signatures of lightning interaction with a 257-m tall tower in Florida,” Electr. Power Syst. Res., vol. 153, pp. 128–137, 2017, doi: 10.1016/j.epsr.2016.08.036. [38] B. Wu et al., “Synchronized Two-Station Optical and Electric Field Observations of Multiple Upward Lightning Flashes Triggered by a 310-kA +CG Flash,” J. Geophys. Res. Atmos., vol. 124, no. 2, pp. 1050–1063, 2019, doi: 10.1029/2018JD029378. [39] X. Kong, Y. Zhao, T. Zhang, and H. Wang, “Optical and electrical characteristics of in-cloud discharge activity and downward leaders in positive cloud-to-ground lightning flashes,” Atmos. Res., vol. 160, pp. 28–38, 2015, doi: 10.1016/j.atmosres.2015.02.014. [40] A. F. R. Leal, G. A. V. S. Ferreira, A. M. Morais, and A. R. A. Manito, “Automated low-cost setup for optical and E-field records of lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 214, no. January, p. 105552, 2021, doi: 10.1016/j.jastp.2021.105552. [41] M. Arcanjo, M. Guimarães, and S. Visacro, “On the interpeak interval of unipolar pulses of current preceding the return stroke in negative CG lightning,” Electr. Power Syst. Res., vol. 173, pp. 13–17, 2019, doi: 10.1016/j.epsr.2019.03.028. [42] B. Fan, P. Yuan, X. Wang, Y. Zhao, J. Cen, and Y. Su, “Development characteristics of cloud-to-ground lightning with multiple grounding points,” Sci. China Earth Sci., vol. 61, no. 8, pp. 1127–1135, 2018, doi: 10.1007/s11430-017-9204-4. [43] C. Wang, Z. Sun, R. Jiang, Y. Tian, and X. Qie, “Characteristics of downward leaders in a cloud-to-ground lightning strike on a lightning rod,” Atmos. Res., vol. 203, pp. 246–253, 2018, doi: 10.1016/j.atmosres.2017.12.014. [44] Y. Li, S. Qiu, L. Shi, Z. Huang, T. Wang, and Y. Duan, “Three-Dimensional Reconstruction of Cloud-to-Ground Lightning Using High-Speed Video and VHF Broadband Interferometer,” J. Geophys. Res. Atmos., vol. 122, no. 24, pp. 13,420-13,435, 2017, doi: 10.1002/2017JD027214. [45] S. Visacro, M. Guimaraes, and M. H. Murta Vale, “Striking Distance Determined From High-Speed Videos and Measured Currents in Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 122, no. 24, pp. 13,356-13,369, 2017, doi: 10.1002/2017JD027354. [46] M. M. F. Saba et al., “Lightning attachment process to common buildings,” Geophys. Res. Lett., vol. 44, no. 9, pp. 4368–4375, 2017, doi: 10.1002/2017GL072796. [47] M. D. Tran and V. A. Rakov, “When does the lightning attachment process actually begin?,” J. Geophys. Res. Atmos., vol. 120, no. 14, pp. 6922–6936, 2015, doi: 10.1002/2015JD023155. [48] Q. Qi, W. Lu, Y. Ma, L. Chen, Y. Zhang, and V. A. Rakov, “High-speed video observations of the fine structure of a natural negative stepped leader at close distance,” Atmos. Res., vol. 178–179, pp. 260–267, 2016, doi: 10.1016/j.atmosres.2016.03.027. [49] W. Lu et al., “Three-dimensional propagation characteristics of the leaders in the attachment process of a downward negative lightning flash,” J. Atmos. Solar-Terrestrial Phys., vol. 136, pp. 23–30, 2015, doi: 10.1016/j.jastp.2015.07.011. [50] H. Zhang et al., “Single-Station-Based Lightning Mapping System with Electromagnetic and Thunder Signals,” IEEE Trans. Plasma Sci., vol. 47, no. 2, pp. 1421–1428, 2019, doi: 10.1109/TPS.2019.2891087. [51] C. Schumann et al., “On the Triggering Mechanisms of Upward Lightning,” Sci. Rep., vol. 9, no. 9576, 2019, doi: 10.1038/s41598-019-46122-x. [52] H. Huang, D. Wang, T. Wu, and N. Takagi, “Formation Features of Steps and Branches of an Upward Negative Leader,” J. Geophys. Res. Atmos., vol. 123, no. 22, pp. 12,597-12,605, 2018, doi: 10.1029/2018JD028979. [53] S. Visacro, M. Guimaraes, and M. H. Murta Vale, “Features of upward positive leaders initiated from towers in natural cloud-to-ground lightning based on simultaneous high-speed videos, measured currents, and electric fields,” J. Geophys. Res. Atmos., vol. 122, no. 23, pp. 12,786-12,800, 2017, doi: 10.1002/2017JD027016. [54] S. Yuan, R. Jiang, X. Qie, D. Wang, Z. Sun, and M. Liu, “Characteristics of Upward Lightning on the Beijing 325 m Meteorology Tower and Corresponding Thunderstorm Conditions,” J. Geophys. Res. Atmos., vol. 122, no. 22, pp. 12,093-12,105, 2017, doi: 10.1002/2017JD027198. [55] D. R. Poelman et al., “Global ground strike point characteristics in negative downward lightning flashes-Part 1: Observations,” Nat. Hazards Earth Syst. Sci., vol. 21, no. 6, pp. 1909–1919, 2021, doi: 10.5194/nhess-21-1909-2021. [56] F. H. Heidler and C. Paul, “High-Speed Video Observation, Currents, and EM-Fields From Four Negative Upward Lightning to the Peissenberg Tower, Germany,” IEEE Trans. Electromagn. Compat., pp. 18–25, 2020, doi: 10.1109/TEMC.2020.3032781. [57] L. Schwalt, S. Pack, and W. Schulz, “Ground truth data of atmospheric discharges in correlation with LLS detections,” Electr. Power Syst. Res., vol. 180, no. March 2019, 2020, doi: 10.1016/j.epsr.2019.106065. [58] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “Leader observations during the initial breakdown stage of a lightning flash,” J. Geophys. Res. Atmos., vol. 119, no. 21, pp. 12,198-12,221, Feb. 2014, doi: 10.1002/2014JD021994. [59] S. Karunarathne, T. C. Marshall, M. Stolzenburg, N. Karunarathna, and R. E. Orville, “Modeling stepped leaders using a time-dependent multidipole model and high-speed video data,” J. Geophys. Res. Atmos., vol. 120, no. 6, pp. 2419–2436, 2015, doi: 10.1002/2014JD022679. [60] M. D. Tran and V. A. Rakov, “A study of the ground-attachment process in natural lightning with emphasis on its breakthrough phase,” Sci. Rep., vol. 7, no. 15761, 2017, doi: 10.1038/s41598-017-14842-7. [61] R. Jiang, Z. Wu, X. Qie, D. Wang, and M. Liu, “High-speed video evidence of a dart leader with bidirectional development,” Geophys. Res. Lett., vol. 41, no. 14, pp. 5246–5250, 2014, doi: 10.1002/2014GL060585. [62] W. R. Gamerota, V. P. Idone, M. A. Uman, T. Ngin, J. T. Pilkey, and D. M. Jordan, “Dart-stepped-leader step formation in triggered lightning,” Geophys. Res. Lett., vol. 41, no. 6, pp. 2204–2211, 2014, doi: 10.1002/2014GL059627. [63] L. Z. S. Campos and M. M. F. Saba, “Visible channel development during the initial breakdown of a natural negative cloud-to-ground flash,” Geophys. Res. Lett., vol. 40, no. 17, pp. 4756–4761, 2013, doi: 10.1002/grl.50904. [64] X. Wang et al., “Comparisons of optical characteristics of two upward lightning flashes triggered by a nearby positive cloud-to-ground lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 198, no. October 2019, 2020, doi: 10.1016/j.jastp.2020.105193. [65] A. Srivastava et al., “Intermittent Propagation of Upward Positive Leader Connecting a Downward Negative Leader in a Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 124, no. 24, pp. 13763–13776, 2019, doi: 10.1029/2019JD031148. [66] Q. Qi et al., “High-Speed Video Observations of Natural Lightning Attachment Process With Framing Rates up to Half a Million Frames per Second,” Geophys. Res. Lett., vol. 46, no. 21, pp. 12580–12587, 2019, doi: 10.1029/2019GL085072. [67] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, T. A. Warner, and R. E. Orville, “Stepped-to-dart leaders preceding lightning return strokes,” J. Geophys. Res. Atmos., vol. 118, no. 17, pp. 9845–9869, 2013, doi: 10.1002/jgrd.50706. [68] M. Stolzenburg, T. C. Marshall, and S. Karunarathne, “On the Transition From Initial Leader to Stepped Leader in Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 125, no. 4, pp. 0–2, 2020, doi: 10.1029/2019JD031765. [69] X. Wang, X. Zhao, H. Cai, G. Liu, M. Liao, and L. Qu, “Optical characteristics of branched downward positive leader associated with recoil leader activity,” J. Atmos. Solar-Terrestrial Phys., vol. 196, 2019, doi: 10.1016/j.jastp.2019.105158. [70] J. D. Hill et al., “The attachment process of rocket-triggered lightning dart-stepped leaders,” J. Geophys. Res. Atmos., vol. 121, no. 2, pp. 853–871, 2016, doi: 10.1002/2015JD024269. [71] M. Stolzenburg, T. C. Marshall, S. Bandara, B. Hurley, and R. Siedlecki, “Ultra-high speed video observations of intracloud lightning flash initiation,” Meteorol. Atmos. Phys., no. 2013, 2021, doi: 10.1007/s00703-021-00803-3. [72] Y. Zhang, Y. Zhang, C. Li, W. Lu, and D. Zheng, “Simultaneous optical and electrical observations of ‘chaotic’ leaders preceding subsequent return strokes,” Atmos. Res., vol. 170, pp. 131–139, 2016, doi: 10.1016/j.atmosres.2015.11.012. [73] R. Jiang et al., “Characteristics of lightning leader propagation and ground attachment,” J. Geophys. Res. Atmos., vol. 120, no. 23, pp. 11,988-12,002, 2015, doi: 10.1002/2015JD023519. [74] L. Schwalt, S. Pack, W. Schulz, and G. Pistotnik, “Percentage of single-stroke flashes related to different thunderstorm types,” Electr. Power Syst. Res., vol. 194, no. January, p. 107109, 2021, doi: 10.1016/j.epsr.2021.107109. [75] W. Schulz, G. Diendorfer, S. Pedeboy, and D. Roel Poelman, “The European lightning location system EUCLID - Part 1: Performance analysis and validation,” Nat. Hazards Earth Syst. Sci., vol. 16, no. 2, pp. 595–605, 2016, doi: 10.5194/nhess-16-595-2016. [76] M. D. Tran and V. A. Rakov, “Attachment process in subsequent strokes and residual channel luminosity between strokes of natural lightning,” J. Geophys. Res., vol. 120, no. 23, pp. 12,248-12,258, 2015, doi: 10.1002/2015JD024032. [77] M. Guimaraes, M. Arcanjo, M. H. Murta Vale, and S. Visacro, “Unusual features of negative leaders’ development in natural lightning, according to simultaneous records of current, electric field, luminosity, and high-speed video,” J. Geophys. Res. Atmos., vol. 122, no. 4, pp. 2325–2333, 2017, doi: 10.1002/2016JD025891. [78] M. Stolzenburg, T. C. Marshall, S. Karunarathne, and R. E. Orville, “Length estimations of presumed upward connecting leaders in lightning flashes to flat water and flat ground,” Atmos. Res., vol. 211, pp. 85–94, 2018, doi: 10.1016/j.atmosres.2018.04.020. [79] X. Wang et al., “High-speed video observations of branching behaviors in downward stepped leaders and upward connecting leaders in negative natural lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 183, pp. 61–66, 2019, doi: 10.1016/j.jastp.2018.12.010. [80] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “Branched dart leaders preceding lightning return strokes,” J. Geophys. Res. Atmos., vol. 119, no. 7, pp. 4228–4252, 2014, doi: 10.1002/2013JD021254. [81] L. Huang et al., “Correlation of Charge Distribution among Different Branches in a Natural Lightning Flash,” IEEE Access, vol. 6, pp. 42829–42836, 2018, doi: 10.1109/ACCESS.2018.2859399. [82] D. A. Kotovsky, M. A. Uman, R. A. Wilkes, and D. M. Jordan, “High-Speed Video and Lightning Mapping Array Observations of In-Cloud Lightning Leaders and an M Component to Ground,” J. Geophys. Res. Atmos., vol. 124, no. 3, pp. 1496–1513, 2019, doi: 10.1029/2018JD029506. [83] Y. Zhang, Y. Zhang, D. Zheng, and W. Lu, “Characteristics and Discharge Processes of M Events with Large Current in Triggered Lightning,” Radio Sci., vol. 53, no. 8, pp. 974–985, 2018, doi: 10.1029/2018RS006552. [84] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “An M component with a concurrent dart leader traveling along different paths during a lightning flash,” J. Geophys. Res. Atmos., vol. 120, no. 19, pp. 10,267-10,284, 2015, doi: 10.1002/2015JD023417. [85] J. Montanyà, O. van der Velde, and E. R. Williams, “The start of lightning: Evidence of bidirectional lightning initiation,” Sci. Rep., vol. 5, no. 15180, 2015, doi: 10.1038/srep15180. [86] N. Shimoji and Y. Uehara, “Color analysis of lightning leaders: Application of astronomical photometry,” AIP Conf. Proc., vol. 1906, 2017, doi: 10.1063/1.5012310. [87] A. Sasithradevi, S. Mohamed Mansoor Roomi, and M. Mareeswari, “A vision based method for detecting lightning in surveillance videos,” Proc. IEEE Int. Conf. Emerg. Technol. Trends Comput. Commun. Electr. Eng. ICETT 2016, pp. 0–4, 2017, doi: 10.1109/ICETT.2016.7873685. [88] S. H. Mun et al., “Performance Analysis of Real Time Image Processing for Lightning Event Using Cython and Python Programming Languages,” IOP Conf. Ser. Earth Environ. Sci., vol. 228, no. 1, 2019, doi: 10.1088/1755-1315/228/1/012009. [89] Y. C. J. Liu, K. J. Nixon, and I. R. Jandrell, “A method to determine the lightning termination points using digital images,” 2011 7th Asia-Pacific Int. Conf. Light. APL2011, pp. 828–832, 2011, doi: 10.1109/APL.2011.6110242. [90] R. Gin, R. Bianchi, and B. Pilon, “A computer vision system to analyse images of lightning flashes,” in Seventh Conference on Artificial Intelligence and its Applications to the Environmental Sciences, 2009, pp. 1–4. [91] J. R. Smit, H. G. P. Huntt, T. Cross, C. Schumann, and T. A. Warner, “Generation of metrics by semantic segmentation of high speed lightning footage using machine learning,” 2020 Int. SAUPEC/RobMech/PRASA Conf. SAUPEC/RobMech/PRASA 2020, 2020, doi: 10.1109/SAUPEC/RobMech/PRASA48453.2020.9041123. [92] MathWorks, “Image Processing Toolbox,” 2021. https://la.mathworks.com/products/image.html. [93] MathWorks, “Matlab,” 2021. https://la.mathworks.com/. [94] J. B., “Close Lightning Strike Compilation,” 2021. https://www.youtube.com/watch?v=YJubbxyhvtY. [95] Pexels, “Las mejores fotos y vídeos de stock compartidos por talentosos creadores,” 2021. https://www.pexels.com/es-es/. [96] Pixabay, “Increíbles imágenes gratis para descargar,” 2021. https://pixabay.com/es/. [97] Videvo, “Free Stock Video Footage,” 2021. https://www.videvo.net/. [98] Python, “Python 3.8.0,” 2019. https://www.python.org/downloads/release/python-380/. [99] OpenCV, “OpenCV 4.4.0,” 2020. https://opencv.org/opencv-4-4-0/. [100] OpenCV, “Color conversions,” 2021. https://docs.opencv.org/4.4.0/de/d25/imgproc_color_conversions.html. [101] OpenCV, “Sobel Derivatives,” 2021. https://docs.opencv.org/4.4.0/d2/d2c/tutorial_sobel_derivatives.html. [102] OpenCV, “Laplace Operator,” 2021. https://docs.opencv.org/4.4.0/d5/db5/tutorial_laplace_operator.html. [103] OpenCV, “Canny Edge Detector,” 2021. https://docs.opencv.org/4.4.0/da/d5c/tutorial_canny_detector.html. [104] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Third Edit. Pearson Prentice Hall, 2008. [105] OpenCV, “Basic Thresholding Operations,” 2021. https://docs.opencv.org/4.4.0/db/d8e/tutorial_threshold.html. [106] Y. Benezeth, P. M. Jodoin, B. Emile, H. Laurent, and C. Rosenberger, “Review and evaluation of commonly-implemented background subtraction algorithms,” in 19th International Conference on Pattern Recognition, 2008, pp. 2–5, doi: 10.1109/icpr.2008.4760998. [107] OpenCV, “How to Use Background Subtraction Methods,” 2021. https://docs.opencv.org/4.4.0/d1/dc5/tutorial_background_subtraction.html. [108] A. Fernández Villán, Mastering OpenCV 4 with Python: A Practical Guide Covering Topics from Image Processing, Augmented Reality to Deep Learning with OpenCV 4 and Python 3.7, vol. 1. Birmingham: Packt Publishing Ltd., 2019. [109] OpenCV, “Finding contours in your image,” 2021. https://docs.opencv.org/4.4.0/df/d0d/tutorial_find_contours.html. [110] A. Kowalczyk, Support Vector Machines Succinctly. Syncfusion, 2017. [111] Python, “CSV File Reading and Writing,” 2021. https://docs.python.org/3/library/csv.html. [112] Scikit-learn, “C-Support Vector Classification,” 2021. https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html. [113] Scikit-learn, “sklearn.metrics.precision_recall_fscore_support,” 2021. https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html. [114] Joblib, “Joblib: running Python functions as pipeline jobs,” 2021. https://joblib.readthedocs.io/en/latest/. [115] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol. 2016-Decem, pp. 770–778, doi: 10.1109/CVPR.2016.90. [116] M. Tan and Q. V Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in 36th International Conference on Machine Learning, ICML 2019, 2019, vol. 2019-June, pp. 10691–10700. [117] TensorFlow, “Una plataforma de extremo a extremo de código abierto para el aprendizaje automático,” 2021. https://www.tensorflow.org/. [118] Python, “Python - Download the latest version,” 2021. https://www.python.org/downloads/. [119] R. P. Foundation, “Raspberry Pi,” 2021. https://www.raspberrypi.org/. [120] “Jetson Nano Developer Kit,” 2021. https://developer.nvidia.com/embedded/jetson-nano-developer-kit. [121] Coral, “Build beneficial and privacy preserving AI,” 2021. https://coral.ai/. [122] O. Pi, “What’s Orange Pi Pc Plus?,” 2021. http://www.orangepi.org/. [123] R. P. Foundation, “Raspberry Pi 3 Model B+.” p. 5, [Online]. Available: https://static.raspberrypi.org/files/product-briefs/200206+Raspberry+Pi+3+Model+B+plus+Product+Brief+PRINT&DIGITAL.pdf. [124] CNET, “Genius FaceCam 310 - web camera Specs,” 2021. https://www.cnet.com/products/genius-facecam-310-web-camera/. [125] R. P. Foundation, “Camera Module V2.” https://www.raspberrypi.org/products/camera-module-v2/. [126] K. Technologies, “Chronos High-Speed Cameras User Manual Chronos 1.4 & Chronos 2.1-HD Software Version 0.5.1.” [Online]. Available: https://www.krontech.ca/wp-content/uploads/2020/10/Chronos-1.4-2.1-HD-User-Manual-Full-version-Software-Version-0.5.1.pdf. |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.license.spa.fl_str_mv |
Reconocimiento 4.0 Internacional |
| dc.rights.uri.spa.fl_str_mv |
http://creativecommons.org/licenses/by/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
Reconocimiento 4.0 Internacional http://creativecommons.org/licenses/by/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
xii, 130 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
Universidad Nacional de Colombia |
| dc.publisher.program.spa.fl_str_mv |
Medellín - Minas - Maestría en Ingeniería - Automatización Industrial |
| dc.publisher.department.spa.fl_str_mv |
Departamento de Ingeniería Eléctrica y Automática |
| dc.publisher.faculty.spa.fl_str_mv |
Facultad de Minas |
| dc.publisher.place.spa.fl_str_mv |
Medellín, Colombia |
| dc.publisher.branch.spa.fl_str_mv |
Universidad Nacional de Colombia - Sede Medellín |
| institution |
Universidad Nacional de Colombia |
| bitstream.url.fl_str_mv |
https://repositorio.unal.edu.co/bitstream/unal/81443/1/98670607.2022.pdf https://repositorio.unal.edu.co/bitstream/unal/81443/2/license.txt https://repositorio.unal.edu.co/bitstream/unal/81443/3/98670607.2022.pdf.jpg |
| bitstream.checksum.fl_str_mv |
54499482caec88619543d552d38658d6 8153f7789df02f0a4c9e079953658ab2 935cd08550072392783a5434437df659 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional Universidad Nacional de Colombia |
| repository.mail.fl_str_mv |
repositorio_nal@unal.edu.co |
| _version_ |
1814089814929047552 |
| spelling |
Reconocimiento 4.0 Internacionalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Bolaños Martínez, Freddybbb8602f0b5a36926e8031d8001ea92e600Herrera Murcia, Javier Gustavo2e2b4d1daf54f4d768d83802ef0dcfc4600Orozco Gómez, Diego Hernando574a094cf414dadc3f20e39a40e89d33Grupo de Automática de la Universidad Nacional Gaunal2022-04-06T18:51:41Z2022-04-06T18:51:41Z2022-04-06https://repositorio.unal.edu.co/handle/unal/81443Universidad Nacional de ColombiaRepositorio Institucional Universidad Nacional de Colombiahttps://repositorio.unal.edu.co/Actualmente diversas investigaciones se han enfocado en analizar a partir de videos de alta velocidad, características de las descargas eléctricas atmosféricas con el fin de adquirir mejor comprensión del fenómeno, que conlleva entre otros aspectos el desarrollo de sistemas de protección robustos. La mayoría de las investigaciones han requerido de un observador que ante el suceso del evento provea un disparo manual a la cámara permitiendo almacenar la información visual del fenómeno. Por tanto, este trabajo se orientó en proponer una metodología para la detección de las descargas utilizando dos implementaciones basadas en procesamiento de señales y visión computacional, con el propósito que el sistema autónomamente sea el que suministre el disparo, apartando al observador de la realización de esta tarea. El sistema de detección basado en técnicas de procesamiento de imágenes requirió la adecuación de métodos de segmentación, representación, descripción y clasificación. El algoritmo de reconocimiento con visión computacional se implementó mediante la red neuronal convolucional EfficientNetB4. Fuera de línea, las técnicas basadas en procesamiento de imágenes suministraron una precisión del 81.81%, mientras que haciendo uso de visión computacional la precisión fue de 71.63%. Con el objeto de evaluar el desempeño en tiempo real, las técnicas de procesamiento se adaptaron en un ordenador de placa reducida correspondiente a la Raspberry Pi 3 modelo B+ obteniéndose una precisión de 86.95%. Adicionalmente, se evaluó la característica de multiplicidad la cual corresponde al número de descargas subsecuentes presentes en el canal de la descarga logrando una precisión de 66.66%. (Texto tomado de la fuente)Currently, several researches have conducted in processing high speed videos, in order to analyze lightning features and acquire a better phenomenon comprehension, which might lead to development of more robust protection systems. Most of the investigations have required a human observer, who, in the occurrence of the event, provides a manual trigger to the camera allowing the visual information of the phenomenon to be stored. Therefore, this work was aimed at proposing a methodology for the lightning detection using two implementations based on signal processing and computer vision, with the purpose that the system autonomously provides the trigger, avoiding the need of a human observer for performing this task. The detection system based on image processing techniques required the adaptation of segmentation, representation, description and classification methods. The computer vision recognition algorithm was implemented using the EfficientNetB4 convolutional neural network. Off-line, the techniques based on image processing provided an accuracy of 81.81%, using computer vision the accuracy was 71.63%. In order to evaluate the performance in real time, the processing techniques were adapted in a single-board computer corresponding to the Raspberry Pi 3 model B+, obtaining an accuracy of 86.95%. Additionally, the lightning multiplicity that refers to the number of strokes in a flash was evaluated, achieving an accuracy of 66.66%.MaestríaMagister en Ingeniería – Automatización IndustrialProcesamiento de Señales Visión ArtificialÁrea Curricular de Ingeniería Eléctrica e Ingeniería de Controlxii, 130 páginasapplication/pdfspaUniversidad Nacional de ColombiaMedellín - Minas - Maestría en Ingeniería - Automatización IndustrialDepartamento de Ingeniería Eléctrica y AutomáticaFacultad de MinasMedellín, ColombiaUniversidad Nacional de Colombia - Sede Medellín620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaImage processingRedes neuronales (computadores)Procesamiento de imágenesProcesamiento de señalesDescarga eléctrica atmosféricaProcesamiento imágenesRed neuronal convolucionalSegmentaciónConvolutional neural networkDetectionImage processingLightningMultiplicitySegmentationPropuesta metodológica para el procesamiento de señales y videos aplicada a la detección y caracterización de la multiplicidad de descargas eléctricas atmosféricasMethodological proposal for the signals and video processing applied to detection and multiplicity characterization of lightningTrabajo de grado - Maestríainfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/acceptedVersionTexthttp://purl.org/redcol/resource_type/TM[1] M. A. Uman, The lightning discharge, vol. 39. 1987.[2] H. H. Goh et al., “A review of lightning protection system - Risk assessment and application,” Indones. J. Electr. Eng. Comput. Sci., vol. 8, no. 1, pp. 221–229, 2017, doi: 10.11591/ijeecs.v8.i1.pp221-229.[3] E. Krausmann, E. Renni, M. Campedel, and V. Cozzani, “Industrial accidents triggered by earthquakes, floods and lightning: Lessons learned from a database analysis,” Nat. Hazards, vol. 59, no. 1, pp. 285–300, 2011, doi: 10.1007/s11069-011-9754-3.[4] E. Renni, E. Krausmann, and V. Cozzani, “Industrial accidents triggered by lightning,” J. Hazard. Mater., vol. 184, no. 1–3, pp. 42–48, 2010, doi: 10.1016/j.jhazmat.2010.07.118.[5] D. M. Elsom, “Factors contributing to a long-term decrease in national lightning fatality rates: case study of the United Kingdom with wider implications,” Int. J. Disaster Risk Reduct., vol. 31, pp. 341–353, 2018, doi: 10.1016/j.ijdrr.2018.06.001.[6] R. L. Holle, “A summary of recent national-Scale lightning fatality studies,” Weather. Clim. Soc., vol. 8, no. 1, pp. 35–42, 2016, doi: 10.1175/WCAS-D-15-0032.1.[7] A. E. Ritenour, M. J. Morton, J. G. McManus, D. J. Barillo, and L. C. Cancio, “Lightning injury: A review,” Burns, vol. 34, no. 5, pp. 585–594, 2008, doi: 10.1016/j.burns.2007.11.006.[8] A. Necci, G. Antonioni, V. Cozzani, E. Krausmann, A. Borghetti, and C. Alberto Nucci, “A model for process equipment damage probability assessment due to lightning,” Reliab. Eng. Syst. Saf., vol. 115, pp. 91–99, 2013, doi: 10.1016/j.ress.2013.02.018.[9] Y. Yasuda, S. Yokoyama, M. Minowa, and T. Satoh, “Classification of lightning damage to wind turbine blades,” IEEJ Trans. Electr. Electron. Eng., vol. 7, no. 6, pp. 559–566, 2012, doi: 10.1002/tee.21773.[10] M. Gagné and D. Therriault, “Lightning strike protection of composites,” Prog. Aerosp. Sci., vol. 64, pp. 1–16, 2014, doi: 10.1016/j.paerosci.2013.07.002.[11] J. E. Jerauld, M. A. Uman, V. A. Rakov, K. J. Rambo, D. M. Jordan, and G. H. Schnetzer, “Measured electric and magnetic fields from an unusual cloud-to-ground lightning flash containing two positive strokes followed by four negative strokes,” J. Geophys. Res. Atmos., vol. 114, no. D19, 2009, doi: 10.1029/2008jd011660.[12] M. M. F. Saba, C. Schumann, T. A. Warner, J. H. Helsdon Jr., W. Schulz, and R. E. Orville, “Bipolar cloud-to-ground lightning flash observations,” J. Geophys. Res. Atmos., vol. 118, no. 19, pp. 11,098-11,106, 2013, doi: 10.1002/jgrd.50804.[13] Y. Tian et al., “Characteristics of a bipolar cloud-to-ground lightning flash containing a positive stroke followed by three negative strokes,” Atmos. Res., vol. 176–177, pp. 222–230, 2016, doi: 10.1016/j.atmosres.2016.02.023.[14] M. D. Tran and V. A. Rakov, “Initiation and propagation of cloud-to-ground lightning observed with a high-speed video camera,” Sci. Rep., vol. 6, no. 39521, 2016, doi: 10.1038/srep39521.[15] M. M. F. Saba et al., “Upward lightning flashes characteristics from high-speed videos,” J. Geophys. Res. Atmos., vol. 121, no. 14, pp. 8493–8505, 2016, doi: 10.1002/2016JD025137.[16] J. Herrera, C. Younes, and L. Porras, “Cloud-to-ground lightning activity in Colombia: A 14-year study using lightning location system data,” Atmos. Res., vol. 203, pp. 164–174, 2018, doi: 10.1016/j.atmosres.2017.12.009.[17] G. Diendorfer et al., “Review of CIGRE Report ‘Cloud-to-Ground Lightning Parameters Derived from Lightning Location Systems – The Effects of System Performance,’” Cigre, no. 376, 2009.[18] M. M. F. Saba et al., “High-speed video observations of positive lightning flashes to ground,” J. Geophys. Res. Atmos., vol. 115, no. D24, 2010, doi: 10.1029/2010JD014330.[19] A. M. Hussein, S. Kazazi, M. Anwar, M. Yusouf, and P. Liatos, “Characteristics of the most intense lightning storm ever recorded at the CN Tower,” J. Atmos. Solar-Terrestrial Phys., vol. 154, pp. 195–206, 2017, doi: 10.1016/j.jastp.2016.05.002.[20] A. C. V. Saraiva, M. M. F. Saba, O. Pinto Jr., K. L. Cummins, E. P. Krider, and L. Z. S. Campos, “A comparative study of negative cloud-to-ground lightning characteristics in São Paulo (Brazil) and Arizona (United States) based on high-speed video observations,” J. Geophys. Res. Atmos., vol. 115, no. D11, 2010, doi: 10.1029/2009JD012604.[21] L. S. Antunes et al., “Day-to-day differences in the characterization of lightning observed by multiple high-speed cameras,” Electr. Power Syst. Res., vol. 118, pp. 93–100, 2015, doi: 10.1016/j.epsr.2014.07.030.[22] Y. Zhang, W. Lu, J. Li, W. Dong, D. Zheng, and S. Chen, “Luminosity characteristics of leaders in natural cloud-to-ground lightning flashes,” Atmos. Res., vol. 91, no. 2–4, pp. 326–332, 2009, doi: 10.1016/j.atmosres.2008.01.013.[23] M. M. F. Saba, C. Schumann, T. A. Warner, J. H. Helsdon, and R. E. Orville, “High-speed video and electric field observation of a negative upward leader connecting a downward positive leader in a positive cloud-to-ground flash,” Electr. Power Syst. Res., vol. 118, pp. 89–92, 2015, doi: 10.1016/j.epsr.2014.06.002.[24] L. Z. S. Campos, M. M. F. Saba, O. Pinto Jr., and M. G. Ballarotti, “Waveshapes of continuing currents and properties of M-components in natural negative cloud-to-ground lightning from high-speed video observations,” Atmos. Res., vol. 84, no. 4, pp. 302–310, 2007, doi: 10.1016/j.atmosres.2006.09.002.[25] C. J. Biagi, K. L. Cummins, K. E. Kehoe, and E. P. Krider, “National Lightning Detection Network (NLDN) performance in southern Arizona, Texas, and Oklahoma in 2003-2004,” J. Geophys. Res. Atmos., vol. 112, no. 5, pp. 1–17, 2007, doi: 10.1029/2006JD007341.[26] O. Pinto, I. R. C. A. Pinto, and K. P. Naccarato, “Geographical variations of negative cloud-to-ground lightning parameters: A review,” 2012 31st Int. Conf. Light. Prot. ICLP 2012, 2012, doi: 10.1109/ICLP.2012.6344292.[27] D. De Jesus Perez-Perez, J. G. Herrera-Murcia, and E. Perez-Gonzalez, “Experimental detection efficiency evaluation for a lightning location system on a mountainous region,” 2013 Int. Symp. Light. Prot. SIPDA 2013, pp. 73–78, 2013, doi: 10.1109/SIPDA.2013.6729235.[28] N. Shimoji, S. Kuninaka, and K. Izumi, “Evaluation of the brightness of lightning channels and branches using the magnitude system: Application of astronomical photometry,” Results Phys., vol. 7, pp. 2085–2095, 2017, doi: 10.1016/j.rinp.2017.06.013.[29] K. Berger, “Blitzstrom-Parameter von Aufwartsblitzen,” Bull. Schweiz. Elektrotech, vol. 69, pp. 353–360, 1978.[30] S. P. A. Vayanganie, M. Fernando, U. Sonnadara, V. Cooray, and C. Perera, “Optical observations of electrical activity in cloud discharges,” J. Atmos. Solar-Terrestrial Phys., vol. 172, pp. 24–32, 2018, doi: 10.1016/j.jastp.2018.03.007.[31] M. Boecker, G. Corpuz, G. Hargrave, S. Das, N. Fischer, and V. Skendzic, “Line current differential relay response to a direct lightning strike on a phase conductor,” 71st Annu. Conf. Prot. Relay Eng. CPRE 2018, vol. 2018-Janua, pp. 1–12, 2018, doi: 10.1109/CPRE.2018.8349805.[32] Nasa, “Where Lightning Strikes,” 2001. https://science.nasa.gov/science-news/science-at-nasa/2001/ast05dec_1.[33] Lightning Protection Devices SA, “Características principales del proceso de descarga de un rayo.” https://www.lpdargentina.com.ar/caracteristicas-principales-del-proceso-de-descarga-de-un-rayo/.[34] J. L. Bermudez Arboleda, “Lightning Currents and Electromagnetic Fields Associated With Return Strokes To Elevated Strike Objects,” vol. 2741, p. 178, 2003.[35] A. C. V. Saraiva et al., “High-speed video and electromagnetic analysis of two natural bipolar cloud-to-ground lightning flashes,” J. Geophys. Res. Atmos., vol. 119, no. 10, pp. 6105–6127, 2014, doi: 10.1002/2013JD020974.[36] M. Azadifar, F. Rachidi, M. Rubinstein, V. A. Rakov, M. Paolone, and D. Pavanello, “Bipolar lightning flashes observed at the säntis tower: Do we need to modify the traditional classification?,” J. Geophys. Res., vol. 121, no. 23, pp. 14,117-14,126, 2016, doi: 10.1002/2016JD025461.[37] Y. Zhu, V. A. Rakov, and M. D. Tran, “Optical and electric field signatures of lightning interaction with a 257-m tall tower in Florida,” Electr. Power Syst. Res., vol. 153, pp. 128–137, 2017, doi: 10.1016/j.epsr.2016.08.036.[38] B. Wu et al., “Synchronized Two-Station Optical and Electric Field Observations of Multiple Upward Lightning Flashes Triggered by a 310-kA +CG Flash,” J. Geophys. Res. Atmos., vol. 124, no. 2, pp. 1050–1063, 2019, doi: 10.1029/2018JD029378.[39] X. Kong, Y. Zhao, T. Zhang, and H. Wang, “Optical and electrical characteristics of in-cloud discharge activity and downward leaders in positive cloud-to-ground lightning flashes,” Atmos. Res., vol. 160, pp. 28–38, 2015, doi: 10.1016/j.atmosres.2015.02.014.[40] A. F. R. Leal, G. A. V. S. Ferreira, A. M. Morais, and A. R. A. Manito, “Automated low-cost setup for optical and E-field records of lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 214, no. January, p. 105552, 2021, doi: 10.1016/j.jastp.2021.105552.[41] M. Arcanjo, M. Guimarães, and S. Visacro, “On the interpeak interval of unipolar pulses of current preceding the return stroke in negative CG lightning,” Electr. Power Syst. Res., vol. 173, pp. 13–17, 2019, doi: 10.1016/j.epsr.2019.03.028.[42] B. Fan, P. Yuan, X. Wang, Y. Zhao, J. Cen, and Y. Su, “Development characteristics of cloud-to-ground lightning with multiple grounding points,” Sci. China Earth Sci., vol. 61, no. 8, pp. 1127–1135, 2018, doi: 10.1007/s11430-017-9204-4.[43] C. Wang, Z. Sun, R. Jiang, Y. Tian, and X. Qie, “Characteristics of downward leaders in a cloud-to-ground lightning strike on a lightning rod,” Atmos. Res., vol. 203, pp. 246–253, 2018, doi: 10.1016/j.atmosres.2017.12.014.[44] Y. Li, S. Qiu, L. Shi, Z. Huang, T. Wang, and Y. Duan, “Three-Dimensional Reconstruction of Cloud-to-Ground Lightning Using High-Speed Video and VHF Broadband Interferometer,” J. Geophys. Res. Atmos., vol. 122, no. 24, pp. 13,420-13,435, 2017, doi: 10.1002/2017JD027214.[45] S. Visacro, M. Guimaraes, and M. H. Murta Vale, “Striking Distance Determined From High-Speed Videos and Measured Currents in Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 122, no. 24, pp. 13,356-13,369, 2017, doi: 10.1002/2017JD027354.[46] M. M. F. Saba et al., “Lightning attachment process to common buildings,” Geophys. Res. Lett., vol. 44, no. 9, pp. 4368–4375, 2017, doi: 10.1002/2017GL072796.[47] M. D. Tran and V. A. Rakov, “When does the lightning attachment process actually begin?,” J. Geophys. Res. Atmos., vol. 120, no. 14, pp. 6922–6936, 2015, doi: 10.1002/2015JD023155.[48] Q. Qi, W. Lu, Y. Ma, L. Chen, Y. Zhang, and V. A. Rakov, “High-speed video observations of the fine structure of a natural negative stepped leader at close distance,” Atmos. Res., vol. 178–179, pp. 260–267, 2016, doi: 10.1016/j.atmosres.2016.03.027.[49] W. Lu et al., “Three-dimensional propagation characteristics of the leaders in the attachment process of a downward negative lightning flash,” J. Atmos. Solar-Terrestrial Phys., vol. 136, pp. 23–30, 2015, doi: 10.1016/j.jastp.2015.07.011.[50] H. Zhang et al., “Single-Station-Based Lightning Mapping System with Electromagnetic and Thunder Signals,” IEEE Trans. Plasma Sci., vol. 47, no. 2, pp. 1421–1428, 2019, doi: 10.1109/TPS.2019.2891087.[51] C. Schumann et al., “On the Triggering Mechanisms of Upward Lightning,” Sci. Rep., vol. 9, no. 9576, 2019, doi: 10.1038/s41598-019-46122-x.[52] H. Huang, D. Wang, T. Wu, and N. Takagi, “Formation Features of Steps and Branches of an Upward Negative Leader,” J. Geophys. Res. Atmos., vol. 123, no. 22, pp. 12,597-12,605, 2018, doi: 10.1029/2018JD028979.[53] S. Visacro, M. Guimaraes, and M. H. Murta Vale, “Features of upward positive leaders initiated from towers in natural cloud-to-ground lightning based on simultaneous high-speed videos, measured currents, and electric fields,” J. Geophys. Res. Atmos., vol. 122, no. 23, pp. 12,786-12,800, 2017, doi: 10.1002/2017JD027016.[54] S. Yuan, R. Jiang, X. Qie, D. Wang, Z. Sun, and M. Liu, “Characteristics of Upward Lightning on the Beijing 325 m Meteorology Tower and Corresponding Thunderstorm Conditions,” J. Geophys. Res. Atmos., vol. 122, no. 22, pp. 12,093-12,105, 2017, doi: 10.1002/2017JD027198.[55] D. R. Poelman et al., “Global ground strike point characteristics in negative downward lightning flashes-Part 1: Observations,” Nat. Hazards Earth Syst. Sci., vol. 21, no. 6, pp. 1909–1919, 2021, doi: 10.5194/nhess-21-1909-2021.[56] F. H. Heidler and C. Paul, “High-Speed Video Observation, Currents, and EM-Fields From Four Negative Upward Lightning to the Peissenberg Tower, Germany,” IEEE Trans. Electromagn. Compat., pp. 18–25, 2020, doi: 10.1109/TEMC.2020.3032781.[57] L. Schwalt, S. Pack, and W. Schulz, “Ground truth data of atmospheric discharges in correlation with LLS detections,” Electr. Power Syst. Res., vol. 180, no. March 2019, 2020, doi: 10.1016/j.epsr.2019.106065.[58] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “Leader observations during the initial breakdown stage of a lightning flash,” J. Geophys. Res. Atmos., vol. 119, no. 21, pp. 12,198-12,221, Feb. 2014, doi: 10.1002/2014JD021994.[59] S. Karunarathne, T. C. Marshall, M. Stolzenburg, N. Karunarathna, and R. E. Orville, “Modeling stepped leaders using a time-dependent multidipole model and high-speed video data,” J. Geophys. Res. Atmos., vol. 120, no. 6, pp. 2419–2436, 2015, doi: 10.1002/2014JD022679.[60] M. D. Tran and V. A. Rakov, “A study of the ground-attachment process in natural lightning with emphasis on its breakthrough phase,” Sci. Rep., vol. 7, no. 15761, 2017, doi: 10.1038/s41598-017-14842-7.[61] R. Jiang, Z. Wu, X. Qie, D. Wang, and M. Liu, “High-speed video evidence of a dart leader with bidirectional development,” Geophys. Res. Lett., vol. 41, no. 14, pp. 5246–5250, 2014, doi: 10.1002/2014GL060585.[62] W. R. Gamerota, V. P. Idone, M. A. Uman, T. Ngin, J. T. Pilkey, and D. M. Jordan, “Dart-stepped-leader step formation in triggered lightning,” Geophys. Res. Lett., vol. 41, no. 6, pp. 2204–2211, 2014, doi: 10.1002/2014GL059627.[63] L. Z. S. Campos and M. M. F. Saba, “Visible channel development during the initial breakdown of a natural negative cloud-to-ground flash,” Geophys. Res. Lett., vol. 40, no. 17, pp. 4756–4761, 2013, doi: 10.1002/grl.50904.[64] X. Wang et al., “Comparisons of optical characteristics of two upward lightning flashes triggered by a nearby positive cloud-to-ground lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 198, no. October 2019, 2020, doi: 10.1016/j.jastp.2020.105193.[65] A. Srivastava et al., “Intermittent Propagation of Upward Positive Leader Connecting a Downward Negative Leader in a Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 124, no. 24, pp. 13763–13776, 2019, doi: 10.1029/2019JD031148.[66] Q. Qi et al., “High-Speed Video Observations of Natural Lightning Attachment Process With Framing Rates up to Half a Million Frames per Second,” Geophys. Res. Lett., vol. 46, no. 21, pp. 12580–12587, 2019, doi: 10.1029/2019GL085072.[67] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, T. A. Warner, and R. E. Orville, “Stepped-to-dart leaders preceding lightning return strokes,” J. Geophys. Res. Atmos., vol. 118, no. 17, pp. 9845–9869, 2013, doi: 10.1002/jgrd.50706.[68] M. Stolzenburg, T. C. Marshall, and S. Karunarathne, “On the Transition From Initial Leader to Stepped Leader in Negative Cloud-to-Ground Lightning,” J. Geophys. Res. Atmos., vol. 125, no. 4, pp. 0–2, 2020, doi: 10.1029/2019JD031765.[69] X. Wang, X. Zhao, H. Cai, G. Liu, M. Liao, and L. Qu, “Optical characteristics of branched downward positive leader associated with recoil leader activity,” J. Atmos. Solar-Terrestrial Phys., vol. 196, 2019, doi: 10.1016/j.jastp.2019.105158.[70] J. D. Hill et al., “The attachment process of rocket-triggered lightning dart-stepped leaders,” J. Geophys. Res. Atmos., vol. 121, no. 2, pp. 853–871, 2016, doi: 10.1002/2015JD024269.[71] M. Stolzenburg, T. C. Marshall, S. Bandara, B. Hurley, and R. Siedlecki, “Ultra-high speed video observations of intracloud lightning flash initiation,” Meteorol. Atmos. Phys., no. 2013, 2021, doi: 10.1007/s00703-021-00803-3.[72] Y. Zhang, Y. Zhang, C. Li, W. Lu, and D. Zheng, “Simultaneous optical and electrical observations of ‘chaotic’ leaders preceding subsequent return strokes,” Atmos. Res., vol. 170, pp. 131–139, 2016, doi: 10.1016/j.atmosres.2015.11.012.[73] R. Jiang et al., “Characteristics of lightning leader propagation and ground attachment,” J. Geophys. Res. Atmos., vol. 120, no. 23, pp. 11,988-12,002, 2015, doi: 10.1002/2015JD023519.[74] L. Schwalt, S. Pack, W. Schulz, and G. Pistotnik, “Percentage of single-stroke flashes related to different thunderstorm types,” Electr. Power Syst. Res., vol. 194, no. January, p. 107109, 2021, doi: 10.1016/j.epsr.2021.107109.[75] W. Schulz, G. Diendorfer, S. Pedeboy, and D. Roel Poelman, “The European lightning location system EUCLID - Part 1: Performance analysis and validation,” Nat. Hazards Earth Syst. Sci., vol. 16, no. 2, pp. 595–605, 2016, doi: 10.5194/nhess-16-595-2016.[76] M. D. Tran and V. A. Rakov, “Attachment process in subsequent strokes and residual channel luminosity between strokes of natural lightning,” J. Geophys. Res., vol. 120, no. 23, pp. 12,248-12,258, 2015, doi: 10.1002/2015JD024032.[77] M. Guimaraes, M. Arcanjo, M. H. Murta Vale, and S. Visacro, “Unusual features of negative leaders’ development in natural lightning, according to simultaneous records of current, electric field, luminosity, and high-speed video,” J. Geophys. Res. Atmos., vol. 122, no. 4, pp. 2325–2333, 2017, doi: 10.1002/2016JD025891.[78] M. Stolzenburg, T. C. Marshall, S. Karunarathne, and R. E. Orville, “Length estimations of presumed upward connecting leaders in lightning flashes to flat water and flat ground,” Atmos. Res., vol. 211, pp. 85–94, 2018, doi: 10.1016/j.atmosres.2018.04.020.[79] X. Wang et al., “High-speed video observations of branching behaviors in downward stepped leaders and upward connecting leaders in negative natural lightning,” J. Atmos. Solar-Terrestrial Phys., vol. 183, pp. 61–66, 2019, doi: 10.1016/j.jastp.2018.12.010.[80] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “Branched dart leaders preceding lightning return strokes,” J. Geophys. Res. Atmos., vol. 119, no. 7, pp. 4228–4252, 2014, doi: 10.1002/2013JD021254.[81] L. Huang et al., “Correlation of Charge Distribution among Different Branches in a Natural Lightning Flash,” IEEE Access, vol. 6, pp. 42829–42836, 2018, doi: 10.1109/ACCESS.2018.2859399.[82] D. A. Kotovsky, M. A. Uman, R. A. Wilkes, and D. M. Jordan, “High-Speed Video and Lightning Mapping Array Observations of In-Cloud Lightning Leaders and an M Component to Ground,” J. Geophys. Res. Atmos., vol. 124, no. 3, pp. 1496–1513, 2019, doi: 10.1029/2018JD029506.[83] Y. Zhang, Y. Zhang, D. Zheng, and W. Lu, “Characteristics and Discharge Processes of M Events with Large Current in Triggered Lightning,” Radio Sci., vol. 53, no. 8, pp. 974–985, 2018, doi: 10.1029/2018RS006552.[84] M. Stolzenburg, T. C. Marshall, S. Karunarathne, N. Karunarathna, and R. E. Orville, “An M component with a concurrent dart leader traveling along different paths during a lightning flash,” J. Geophys. Res. Atmos., vol. 120, no. 19, pp. 10,267-10,284, 2015, doi: 10.1002/2015JD023417.[85] J. Montanyà, O. van der Velde, and E. R. Williams, “The start of lightning: Evidence of bidirectional lightning initiation,” Sci. Rep., vol. 5, no. 15180, 2015, doi: 10.1038/srep15180.[86] N. Shimoji and Y. Uehara, “Color analysis of lightning leaders: Application of astronomical photometry,” AIP Conf. Proc., vol. 1906, 2017, doi: 10.1063/1.5012310.[87] A. Sasithradevi, S. Mohamed Mansoor Roomi, and M. Mareeswari, “A vision based method for detecting lightning in surveillance videos,” Proc. IEEE Int. Conf. Emerg. Technol. Trends Comput. Commun. Electr. Eng. ICETT 2016, pp. 0–4, 2017, doi: 10.1109/ICETT.2016.7873685.[88] S. H. Mun et al., “Performance Analysis of Real Time Image Processing for Lightning Event Using Cython and Python Programming Languages,” IOP Conf. Ser. Earth Environ. Sci., vol. 228, no. 1, 2019, doi: 10.1088/1755-1315/228/1/012009.[89] Y. C. J. Liu, K. J. Nixon, and I. R. Jandrell, “A method to determine the lightning termination points using digital images,” 2011 7th Asia-Pacific Int. Conf. Light. APL2011, pp. 828–832, 2011, doi: 10.1109/APL.2011.6110242.[90] R. Gin, R. Bianchi, and B. Pilon, “A computer vision system to analyse images of lightning flashes,” in Seventh Conference on Artificial Intelligence and its Applications to the Environmental Sciences, 2009, pp. 1–4.[91] J. R. Smit, H. G. P. Huntt, T. Cross, C. Schumann, and T. A. Warner, “Generation of metrics by semantic segmentation of high speed lightning footage using machine learning,” 2020 Int. SAUPEC/RobMech/PRASA Conf. SAUPEC/RobMech/PRASA 2020, 2020, doi: 10.1109/SAUPEC/RobMech/PRASA48453.2020.9041123.[92] MathWorks, “Image Processing Toolbox,” 2021. https://la.mathworks.com/products/image.html.[93] MathWorks, “Matlab,” 2021. https://la.mathworks.com/.[94] J. B., “Close Lightning Strike Compilation,” 2021. https://www.youtube.com/watch?v=YJubbxyhvtY.[95] Pexels, “Las mejores fotos y vídeos de stock compartidos por talentosos creadores,” 2021. https://www.pexels.com/es-es/.[96] Pixabay, “Increíbles imágenes gratis para descargar,” 2021. https://pixabay.com/es/.[97] Videvo, “Free Stock Video Footage,” 2021. https://www.videvo.net/.[98] Python, “Python 3.8.0,” 2019. https://www.python.org/downloads/release/python-380/.[99] OpenCV, “OpenCV 4.4.0,” 2020. https://opencv.org/opencv-4-4-0/.[100] OpenCV, “Color conversions,” 2021. https://docs.opencv.org/4.4.0/de/d25/imgproc_color_conversions.html.[101] OpenCV, “Sobel Derivatives,” 2021. https://docs.opencv.org/4.4.0/d2/d2c/tutorial_sobel_derivatives.html.[102] OpenCV, “Laplace Operator,” 2021. https://docs.opencv.org/4.4.0/d5/db5/tutorial_laplace_operator.html.[103] OpenCV, “Canny Edge Detector,” 2021. https://docs.opencv.org/4.4.0/da/d5c/tutorial_canny_detector.html.[104] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Third Edit. Pearson Prentice Hall, 2008.[105] OpenCV, “Basic Thresholding Operations,” 2021. https://docs.opencv.org/4.4.0/db/d8e/tutorial_threshold.html.[106] Y. Benezeth, P. M. Jodoin, B. Emile, H. Laurent, and C. Rosenberger, “Review and evaluation of commonly-implemented background subtraction algorithms,” in 19th International Conference on Pattern Recognition, 2008, pp. 2–5, doi: 10.1109/icpr.2008.4760998.[107] OpenCV, “How to Use Background Subtraction Methods,” 2021. https://docs.opencv.org/4.4.0/d1/dc5/tutorial_background_subtraction.html.[108] A. Fernández Villán, Mastering OpenCV 4 with Python: A Practical Guide Covering Topics from Image Processing, Augmented Reality to Deep Learning with OpenCV 4 and Python 3.7, vol. 1. Birmingham: Packt Publishing Ltd., 2019.[109] OpenCV, “Finding contours in your image,” 2021. https://docs.opencv.org/4.4.0/df/d0d/tutorial_find_contours.html.[110] A. Kowalczyk, Support Vector Machines Succinctly. Syncfusion, 2017.[111] Python, “CSV File Reading and Writing,” 2021. https://docs.python.org/3/library/csv.html.[112] Scikit-learn, “C-Support Vector Classification,” 2021. https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html.[113] Scikit-learn, “sklearn.metrics.precision_recall_fscore_support,” 2021. https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html.[114] Joblib, “Joblib: running Python functions as pipeline jobs,” 2021. https://joblib.readthedocs.io/en/latest/.[115] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol. 2016-Decem, pp. 770–778, doi: 10.1109/CVPR.2016.90.[116] M. Tan and Q. V Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in 36th International Conference on Machine Learning, ICML 2019, 2019, vol. 2019-June, pp. 10691–10700.[117] TensorFlow, “Una plataforma de extremo a extremo de código abierto para el aprendizaje automático,” 2021. https://www.tensorflow.org/.[118] Python, “Python - Download the latest version,” 2021. https://www.python.org/downloads/.[119] R. P. Foundation, “Raspberry Pi,” 2021. https://www.raspberrypi.org/.[120] “Jetson Nano Developer Kit,” 2021. https://developer.nvidia.com/embedded/jetson-nano-developer-kit.[121] Coral, “Build beneficial and privacy preserving AI,” 2021. https://coral.ai/.[122] O. Pi, “What’s Orange Pi Pc Plus?,” 2021. http://www.orangepi.org/.[123] R. P. Foundation, “Raspberry Pi 3 Model B+.” p. 5, [Online]. Available: https://static.raspberrypi.org/files/product-briefs/200206+Raspberry+Pi+3+Model+B+plus+Product+Brief+PRINT&DIGITAL.pdf.[124] CNET, “Genius FaceCam 310 - web camera Specs,” 2021. https://www.cnet.com/products/genius-facecam-310-web-camera/.[125] R. P. Foundation, “Camera Module V2.” https://www.raspberrypi.org/products/camera-module-v2/.[126] K. Technologies, “Chronos High-Speed Cameras User Manual Chronos 1.4 & Chronos 2.1-HD Software Version 0.5.1.” [Online]. Available: https://www.krontech.ca/wp-content/uploads/2020/10/Chronos-1.4-2.1-HD-User-Manual-Full-version-Software-Version-0.5.1.pdf.EstudiantesInvestigadoresMaestros, InvestigadoresORIGINAL98670607.2022.pdf98670607.2022.pdfTesis de Maestría en Ingeniería – Automatización Industrialapplication/pdf6240549https://repositorio.unal.edu.co/bitstream/unal/81443/1/98670607.2022.pdf54499482caec88619543d552d38658d6MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-84074https://repositorio.unal.edu.co/bitstream/unal/81443/2/license.txt8153f7789df02f0a4c9e079953658ab2MD52THUMBNAIL98670607.2022.pdf.jpg98670607.2022.pdf.jpgGenerated Thumbnailimage/jpeg5830https://repositorio.unal.edu.co/bitstream/unal/81443/3/98670607.2022.pdf.jpg935cd08550072392783a5434437df659MD53unal/81443oai:repositorio.unal.edu.co:unal/814432023-08-09 08:14:21.129Repositorio Institucional Universidad Nacional de Colombiarepositorio_nal@unal.edu.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 |