Publicación: Urban Eye: transformación del monitoreo pasivo en analítica predictiva mediante Deep Learning y computación perimetral
| dc.contributor.author | Gaitán Barreto, Jorge Steven | |
| dc.contributor.author | Sierra Quintero, Juan Manuel | |
| dc.contributor.author | Moreno Poveda, Fabian Orlando | |
| dc.creator.id | 1001084307 | |
| dc.creator.id | 1000327788 | |
| dc.creator.id | 1075663723 | |
| dc.date.accessioned | 2026-08-03T22:36:43Z | |
| dc.date.issued | 2026-07-12 | |
| dc.description.abstract | Urban Eye es un prototipo que tiene como objetivo poder fortalecer los sistemas tradicionales de videovigilancia mediante la utilización de visión computacional. Edge Computing y Deep Learning. De esta manera la presente investigación surge debido a las limitaciones actuales que se encuentran presentes en los sistemas de monitoreo tradicionales, ya que estos dependen en gran medida de una supervisión humana, lo cual podría generar posibles retrasos en lo que se refiere a la detección de incidentes y anomalías en los entornos urbanos. Por lo mencionado anteriormente este proyecto se enfoco en desarrollar un sistema que fuera capaz de poder identificar eventos vehiculares en tiempo real mediante la implementación del algoritmo YOLO, Este algoritmo fue seleccionado debido a su gran capacidad para detectar objetos y su velocidad de procesamiento. además de esto se implementó una arquitectura Edge Computing para poder ejecutar parte de este procesamiento de manera local, reduciendo así la dependencia de servicios externos y disminuyendo la latencia para poder mejorar la eficiencia del sistema. Por otra parte, la metodología que fue empleada corresponde a un enfoque cuantitativo experimental que esta orientado a evaluar el desempeño del prototipo en unos escenarios urbanos de prueba. De esta manera durante la realización de las pruebas, el sistema logró mantener un procesamiento cercano a los 30 fotogramas por segundo, permitiendo así una detección estable de vehículos y un funcionamiento adecuado en condiciones de buena iluminación. Asimismo, el proyecto integró fundamentos de privacidad por diseño, enfocándose en el procesamiento local y la gestión de metadatos para minimizar riesgos vinculados al manejo de información delicada. De esta manera Urban Eye representa una alternativa tecnológica que esta orientada al fortalecimiento de soluciones de monitoreo inteligente en entornos urbanos. | spa |
| dc.description.abstract | Urban Eye is a prototype that aims to strengthen traditional video surveillance systems through the use of computer vision. Edge Computing and Deep Learning. In this way, the present research arises due to the current limitations that are present in traditional monitoring systems, since these depend largely on human supervision, which could generate possible delays in terms of the detection of incidents and anomalies in urban environments. As mentioned above, this project focused on developing a system that was capable of identifying vehicular events in real time through the implementation of the YOLO algorithm. This algorithm was selected due to its great capacity to detect objects and its processing speed. In addition to this, an Edge Computing architecture was implemented to be able to execute part of this processing locally, thus reducing dependence on external services and reducing latency to improve system efficiency. On the other hand, the methodology that was used corresponds to a quantitative experimental approach that is aimed at evaluating the performance of the prototype in urban test scenarios. In this way, during the tests, the system managed to maintain processing close to 30 frames per second, thus allowing stable vehicle detection and adequate operation in good lighting conditions. Likewise, the project integrated privacy by design fundamentals, focusing on local processing and metadata management to minimize risks linked to the handling of sensitive information. In this way, Urban Eye represents a technological alternative that is aimed at strengthening intelligent monitoring solutions in urban environments. | eng |
| dc.description.degreelevel | Trabajo de grado | spa |
| dc.description.degreename | Ingeniero de Sistemas | spa |
| dc.format | ||
| dc.format.extent | 36 páginas, 1 anexo | |
| dc.format.medium | Recurso electrónico | spa |
| dc.format.mimetype | application/pdf | |
| dc.identifier.instname | instname:Universidad Ean | spa |
| dc.identifier.local | BDM-FISV | |
| dc.identifier.reponame | reponame:Repositorio Institucional Biblioteca Digital Minerva | spa |
| dc.identifier.repourl | https://repository.ean.edu.co/ | |
| dc.identifier.uri | https://hdl.handle.net/10882/19452 | |
| dc.language.iso | spa | |
| dc.publisher.faculty | Facultad de Ingeniería | spa |
| dc.publisher.program | Ingeniería de Sistemas - Virtual | spa |
| dc.relation.references | Batty, M. (2013). The New Science of Cities. MIT Press. Bettencourt, L. M. A. (2021). Introduction to Urban Science: Evidence and Theory of Cities as Complex Systems. MIT Press. Cavoukian, A. (2011). Privacy by Design: The 7 Foundational Principles. Information and Privacy Commissioner of Ontario. Giffinger, R., Fertner, C., Kramar, H., Kalasek, R., Pichler-Milanović, N., & Meijers, E. (2007). Smart cities: Ranking of European medium-sized cities. Vienna University of Technology. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. Han, S., Pool, J., Tran, J., & Dally, W. (2015). Learning both Weights and Connections for Efficient Neural Network. Advances in Neural Information Processing Systems (NIPS), 28, 1135 1143. Hartley, R., & Zisserman, A. (2004). Multiple View Geometry in Computer Vision (2ª ed.). Cambridge University Press. Hernández-Sampieri, R., & Mendoza, C. (2018). Metodología de la investigación: Las rutas cuantitativa, cualitativa y mixta. McGraw-Hill. Lee, K., & Williams, P. (2026). Federated Learning in Urban Edge Intelligence: Privacy and Efficiency. International Journal of Smart Cities, 8(1), 45–62. Mell, P., & Grance, T. (2011). The NIST Definition of Cloud Computing. National Institute of Standards and Technology. Special Publication 800-145. U.S. Department of Commerce. Moher, D., Liberati, A., Tetzlaff, J., & Altman, D. G. (2009). Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement. PLoS Medicine, 6(7), e1000097. https://doi.org/10.1371/journal.pmed.1000097 Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788. Roche, S., Nabian, N., Kloeckl, K., & Ratti, C. (2012). Are 'Smart Cities' Smart Enough? Global Geospatial Conference, 1, 215–235. Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 3(5), 637–646. Smith, R., et al. (2023). Edge Computing for Road Safety: Evaluation of hardware performance. Future Generation Computer Systems, 145, 332–345. Sommerville, I. (2011). Software Engineering. Addison-Wesley... Wan, F., Sun, C., He, H., Lei, G., Xu, L., & Xiao, T. (2022). YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s. EURASIP Journal on Advances in Signal Processing, 2022(1). https://doi.org/10.1186/s13634-022-00931-x Guo, G., & Zhang, Z. (2022). Road damage detection algorithm for improved YOLOv5. Scientific Reports, 12(1), 15523. https://doi.org/10.1038/s41598-022-19674-8 Park, S., Tran, V., & Lee, D. (2021). Application of various YOLO models for computer Vision Based Real-Time pothole detection. Applied Sciences, 11(23), 11229. https://doi.org/10.3390/app112311229 Ramesh, A., Nikam, D., Balachandran, V. N., Guo, L., Wang, R., Hu, L., Comert, G., & Jia, Y. (2022). Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones. Sustainability, 14(14), 8682. https://doi.org/10.3390/su14148682 Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002 | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.coar | http://purl.org/coar/access_right/c_abf2 | |
| dc.rights.creativecommons | Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0) | |
| dc.rights.license | Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0) | |
| dc.rights.local | Abierto (Texto Completo) | spa |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| dc.subject.armarc | Visión por computador | spa |
| dc.subject.armarc | Procesamiento de imágenes | spa |
| dc.subject.armarc | Inteligencia artificial | spa |
| dc.subject.armarc | Reconocimiento de modelos por computador | spa |
| dc.subject.armarc | Sistemas de imágenes | spa |
| dc.subject.proposal | Visión computacional | spa |
| dc.subject.proposal | Deep learning | spa |
| dc.subject.proposal | Videovigilancia inteligente | spa |
| dc.subject.proposal | Edge computing | spa |
| dc.subject.proposal | Inteligencia artificial | spa |
| dc.subject.proposal | Monitoreo urbano | spa |
| dc.subject.proposal | Yolo | spa |
| dc.subject.proposal | Movilidad urbana | spa |
| dc.subject.proposal | Computational vision | eng |
| dc.subject.proposal | Deep learning | eng |
| dc.subject.proposal | Intelligent video surveillance | eng |
| dc.subject.proposal | Edge Computing | eng |
| dc.subject.proposal | Artificial intelligence | eng |
| dc.subject.proposal | Urban monitoring | eng |
| dc.subject.proposal | YOLO | eng |
| dc.subject.proposal | Urban Mobility | eng |
| dc.title | Urban Eye: transformación del monitoreo pasivo en analítica predictiva mediante Deep Learning y computación perimetral | spa |
| dc.title | Urban Eye: transforming passive monitoring into predictive analytics using deep learning and edge computing. | eng |
| dc.type | Trabajo de grado - Pregrado | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_7a1f | |
| dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | |
| dc.type.content | Text | |
| dc.type.driver | info:eu-repo/semantics/bachelorThesis | |
| dc.type.other | Trabajo de grado - Pregrado | |
| dc.type.redcol | http://purl.org/redcol/resource_type/TP | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dspace.entity.type | Publication | |
| person.affiliation.name | Ingeniería de Sistemas - Virtual | |
| person.affiliation.name | Ingeniería de Sistemas - Virtual | |
| person.affiliation.name | Ingeniería Industrial - Virtual |
Archivos
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 1.92 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción:
