Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos

Esta tesis se centra en el desarrollo de una aplicación para seguridad ciudadana mediante técnicas de aprendizaje de máquina, con el objetivo principal de detectar delitos a través del análisis de archivos de video. La investigación comienza con una revisión sistemática de las técnicas más relevante...

Full description

Autores:
Londoño Lopera, Juan Camilo
Tipo de recurso:
Fecha de publicación:
2024
Institución:
Universidad Nacional de Colombia
Repositorio:
Universidad Nacional de Colombia
Idioma:
spa
OAI Identifier:
oai:repositorio.unal.edu.co:unal/86291
Acceso en línea:
https://repositorio.unal.edu.co/handle/unal/86291
https://repositorio.unal.edu.co/
Palabra clave:
000 - Ciencias de la computación, información y obras generales::003 - Sistemas
Aprendizaje automático (Inteligencia artificial)
Redes neuronales (computadores)
Predicción en la conducta criminal
Seguridad ciudadana
Aprendizaje de máquina
Detección de delitos
Modelos LSTM
Redes Neuronales Convolucionales 3D
Predicción de eventos
Sistemas de videovigilancia
Public safety
Machine learning
Crime detection
LSTM Models
3D Convolutional Neural Networks
Event Prediction
Videovigilancia IP
Rights
openAccess
License
Reconocimiento 4.0 Internacional
id UNACIONAL2_7028eb4a28db6a6ad656afa9704d79d0
oai_identifier_str oai:repositorio.unal.edu.co:unal/86291
network_acronym_str UNACIONAL2
network_name_str Universidad Nacional de Colombia
repository_id_str
dc.title.spa.fl_str_mv Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
dc.title.translated.eng.fl_str_mv Application of machine learning techniques to video file analysis for crime detection
title Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
spellingShingle Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
000 - Ciencias de la computación, información y obras generales::003 - Sistemas
Aprendizaje automático (Inteligencia artificial)
Redes neuronales (computadores)
Predicción en la conducta criminal
Seguridad ciudadana
Aprendizaje de máquina
Detección de delitos
Modelos LSTM
Redes Neuronales Convolucionales 3D
Predicción de eventos
Sistemas de videovigilancia
Public safety
Machine learning
Crime detection
LSTM Models
3D Convolutional Neural Networks
Event Prediction
Videovigilancia IP
title_short Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
title_full Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
title_fullStr Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
title_full_unstemmed Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
title_sort Aplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitos
dc.creator.fl_str_mv Londoño Lopera, Juan Camilo
dc.contributor.advisor.none.fl_str_mv Bolaños Martinez, Freddy
dc.contributor.author.none.fl_str_mv Londoño Lopera, Juan Camilo
dc.contributor.other.none.fl_str_mv Luis Alejandro Fletscher Bocanegra
dc.subject.ddc.spa.fl_str_mv 000 - Ciencias de la computación, información y obras generales::003 - Sistemas
topic 000 - Ciencias de la computación, información y obras generales::003 - Sistemas
Aprendizaje automático (Inteligencia artificial)
Redes neuronales (computadores)
Predicción en la conducta criminal
Seguridad ciudadana
Aprendizaje de máquina
Detección de delitos
Modelos LSTM
Redes Neuronales Convolucionales 3D
Predicción de eventos
Sistemas de videovigilancia
Public safety
Machine learning
Crime detection
LSTM Models
3D Convolutional Neural Networks
Event Prediction
Videovigilancia IP
dc.subject.lemb.none.fl_str_mv Aprendizaje automático (Inteligencia artificial)
Redes neuronales (computadores)
Predicción en la conducta criminal
dc.subject.proposal.spa.fl_str_mv Seguridad ciudadana
Aprendizaje de máquina
Detección de delitos
Modelos LSTM
Redes Neuronales Convolucionales 3D
Predicción de eventos
Sistemas de videovigilancia
dc.subject.proposal.eng.fl_str_mv Public safety
Machine learning
Crime detection
LSTM Models
3D Convolutional Neural Networks
Event Prediction
dc.subject.wikidata.none.fl_str_mv Videovigilancia IP
description Esta tesis se centra en el desarrollo de una aplicación para seguridad ciudadana mediante técnicas de aprendizaje de máquina, con el objetivo principal de detectar delitos a través del análisis de archivos de video. La investigación comienza con una revisión sistemática de las técnicas más relevantes, estableciendo criterios de selección que priorizan estructuras capaces de integrar eficientemente la dimensión temporal. Se favorecen modelos de aprendizaje de máquina, que ofrecen versatilidad para la incorporación de nuevos parámetros, especialmente aquellos basados en esquemas espacio-temporales, fundamentales para el análisis de video y la consideración del contexto temporal de los eventos. Dado que la recolección de datos extensos y etiquetados resulta inviable en el marco temporal del proyecto, se opta por utilizar simulaciones basadas en conjuntos de datos públicos en lı́nea diseñados especı́ficamente para la detección de delitos. Se selecciona cuidadosamente al menos un tipo de delito para la investigación, considerando su relevancia y disponibilidad de repeticiones para el desarrollo efectivo del modelo de predicción. La validación del modelo se lleva a cabo mediante una evaluación exhaustiva, utilizando diversos conjuntos de datos previamente seleccionados y parámetros clave de desempeño, como la curva ROC - AUC. Este enfoque integral busca garantizar la eficacia y aplicabilidad del modelo en entornos prácticos y del mundo real. (Texto tomado de la fuente)
publishDate 2024
dc.date.accessioned.none.fl_str_mv 2024-06-25T16:11:54Z
dc.date.available.none.fl_str_mv 2024-06-25T16:11:54Z
dc.date.issued.none.fl_str_mv 2024
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/86291
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/86291
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 [Acsintoae et al., 2021] Acsintoae, A., Florescu, A., Georgescu, M.-I., Mare, T., Sumedrea, P., Ionescu, R. T., Khan, F. S., and Shah, M. (2021). Ubnormal: New benchmark for supervised open-set video anomaly detection. Computer Vision and Pattern Recognition.
[Adam et al., 2008] Adam, A., Rivlin, E., Shimshoni, I., and Reinitz, D. (2008). Robust real- time unusual event detection using multiple fixed-location monitors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(3):555–560
[Althnian et al., 2021] Althnian, A., AlSaeed, D., Al-Baity, H., Samha, A., Dris, A. B., Al- zakari, N., Abou Elwafa, A., and Kurdi, H. (2021). Impact of dataset size on classification performance: An empirical evaluation in the medical domain. Applied Sciences, 11(2).
[Anthopoulos, 2015] Anthopoulos, L. G. (2015). Understanding the Smart City Domain: A Literature Review, pages 9–21. Springer International Publishing, Cham.
[Boekhoudt et al., 2021] Boekhoudt, K., Matei, A., Aghaei, M., and Talavera, E. (2021). Hr- crime: Human-related anomaly detection in surveillance videos. CoRR, abs/2108.00246.
[Carreira and Zisserman, 2017] Carreira, J. and Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. pages 4724–4733.
[Catlett et al., 2019] Catlett, C., Cesario, E., Talia, D., and Vinci, A. (2019). Spatio- temporal crime predictions in smart cities: A data-driven approach and experiments. Pervasive and Mobile Computing, 53.
[Cheng et al., 2021] Cheng, M., Cai, K., and Li, M. (2021). Rwf-2000: An open large scale video database for violence detection. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 4183–4190.
[Degardin and Proença, 2021] Degardin, B. and Proença, H. (2021). Iterative weak/self- supervised classification framework for abnormal events detection. Pattern Recognition Letters, 145:50–57.
[Dubey et al., 2019] Dubey, S., Boragule, A., and Jeon, M. (2019). 3d resnet with ranking loss function for abnormal activity detection in videos. In 2019 International Conference on Control, Automation and Information Sciences (ICCAIS), pages 1–6.
[Farnebäck, 2003] Farnebäck, G. (2003). Two-frame motion estimation based on polynomial expansion. volume 2749, pages 363–370
[Feng et al., 2021] Feng, J.-C., Hong, F.-T., and Zheng, W.-S. (2021). Mist: Multiple ins- tance self-training framework for video anomaly detection. pages 14004–14013.
[Gemmeke et al., 2017] Gemmeke, J. F., Ellis, D. P. W., Freedman, D., Jansen, A., Law- rence, W., Moore, R. C., Plakal, M., and Ritter, M. (2017). Audio set: An ontology and human-labeled dataset for audio events. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 776–780.
[Gorr et al., 2003] Gorr, W., Olligschlaeger, A., and Thompson, Y. (2003). Short-term fo- recasting of crime. International Journal of Forecasting, 19.
[Hasan et al., 2016] Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A. K., and Davis, L. S. (2016). Learning temporal regularity in video sequences. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 733–742.
[Hershey et al., 2016] Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., Slaney, M., Weiss, R. J., and Wilson, K. W. (2016). CNN architectures for large-scale audio classification. CoRR, abs/1609.09430.
[Isafiade and Bagula, 2020] Isafiade, O. E. and Bagula, A. B. (2020). Series mining for public safety advancement in emerging smart cities. Future Generation Computer Systems, 108.
[Kamoona et al., 2023] Kamoona, A. M., Gostar, A. K., Bab-Hadiashar, A., and Hosein- nezhad, R. (2023). Multiple instance-based video anomaly detection using deep temporal encoding–decoding. Expert Systems with Applications, 214:119079.
[Karpathy et al., 2014] Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., and Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In CVPR.
[Kliper-Gross et al., 2012] Kliper-Gross, O., Hassner, T., and Wolf, L. (2012). The action similarity labeling challenge. IEEE Transactions on Pattern Analysis and Machine Inte- lligence, 34:615–621.
[Landi et al., 2019] Landi, F., Snoek, C. G. M., and Cucchiara, R. (2019). Anomaly locality in video surveillance. ArXiv, abs/1901.10364.
[Lu et al., 2013] Lu, C., Shi, J., and Jia, J. (2013). Abnormal event detection at 150 fps in matlab. In 2013 IEEE International Conference on Computer Vision, pages 2720–2727.
[Luo et al., 2017] Luo, W., Liu, W., and Gao, S. (2017). A revisit of sparse coding based anomaly detection in stacked rnn framework. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 341–349.
[Lv et al., 2021a] Lv, H., Chen, C., Cui, Z., Xu, C., Li, Y., and Yang, J. (2021a). Learning normal dynamics in videos with meta prototype network. Computer Vision and Pattern Recognition.
[Lv et al., 2021b] Lv, H., Zhou, C., Cui, Z., Xu, C., Li, Y., and Yang, J. (2021b). Localizing anomalies from weakly-labeled videos. Computer Vision and Pattern Recognition.
[Mahadevan et al., 2010] Mahadevan, V., Li, W., Bhalodia, V., and Vasconcelos, N. (2010). Anomaly detection in crowded scenes. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 1975–1981.
[Majhi et al., 2021] Majhi, S., Das, S., Bremond, F., Dash, R., and Sa, P. (2021). Weakly- supervised joint anomaly detection and classification. In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pages 1–7, Los Ala- mitos, CA, USA. IEEE Computer Society.
[Maqsood et al., 2021] Maqsood, R., Bajwa, U., Saleem, G., Raza, R., and Anwar, M. (2021). Anomaly recognition from surveillance videos using 3d convolutional neural networks.
[Medapati et al., 2019] Medapati, P. K., Murthy, P. H. S. T., and Sridhar, K. P. (2019). Lamstar: For iot-based face recognition system to manage the safety factor in smart cities. Transactions on Emerging Telecommunications Technologies.
[Mehran et al., 2009] Mehran, R., Oyama, A., and Shah, M. (2009). Abnormal crowd beha- vior detection using social force model. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 935–942.
[OECD, 2021] OECD (2021). OECD, “Better life index, security”. Accedido: 2022-03-17.
[Oh, 2011] Oh, S. (2011). A new dataset evaluation method based on category overlap. Computers in Biology and Medicine, 41(2):115–122.
[Pang et al., 2019] Pang, Y., Zhang, L., Ding, H., Fang, Y., and Chen, S. (2019). Spath: Fin- ding the safest walking path in smart cities. IEEE Transactions on Vehicular Technology, 68.
[Perez et al., 2019] Perez, M., Kot, A. C., and Rocha, A. (2019). Detection of real-world fights in surveillance videos. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2662–2666.
[Ramzan et al., 2019] Ramzan, M., Abid, A., Khan, H. U., Awan, S. M., Ismail, A., Ahmed, M., Ilyas, M., and Mahmood, A. (2019). A review on state-of-the-art violence detection techniques. IEEE Access, 7:107560–107575.
[Rathore et al., 2016] Rathore, M., Ahmad, A., Paul, A., and Rho, S. (2016). Urban planning and building smart cities based on the internet of things using big data analytics. Computer Networks, 101:63–80.
[Rathore et al., 2018] Rathore, M., Paul, A., Ahmad, A., Chilamkurti, N., Hong, W.-H., and Seo, H. (2018). Real-time secure communication for smart city in high-speed big data environment. Future Generation Computer Systems, 83:638–652.
[Sandler et al., 2018] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.
[SIEDCO, 2021] SIEDCO (2021). Estadı́stica delictiva. Accedido: 2022-03-23.
[Simić et al., 2020] Simić, M., Perić, M., Popadić, I., Perić, D., Pavlović, M., Vučetić, M., and Stanković, M. (2020). Big data and development of smart city: System architecture and practical public safety example. Serbian Journal of Electrical Engineering, 17:337–355.
[Soliman et al., 2019] Soliman, M. M., Kamal, M. H., El-Massih Nashed, M. A., Mostafa, Y. M., Chawky, B. S., and Khattab, D. (2019). Violence recognition from videos using deep learning techniques. In 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS), pages 80–85.
[Soomro et al., 2012] Soomro, K., Zamir, A. R., and Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. CoRR, abs/1212.0402.
[Sultani et al., 2019] Sultani, W., Chen, C., and Shah, M. (2019). Real-world anomaly de- tection in surveillance videos. Computer Vision and Pattern Recognition.
[Tian et al., 2021] Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J. W., and Carnei- ro, G. (2021). Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. Computer Vision and Pattern Recognition.
[Tran et al., 2015] Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. pages 4489–4497.
[Ullah and Petrosino, 2017] Ullah, I. and Petrosino, A. (2017). A spatiotemporal feature learning approach for dynamic scene recognition.
[Ullah et al., 2021a] Ullah, W., Ullah, A., Haq, I. U., Muhammad, K., Sajjad, M., and Baik, S. W. (2021a). Cnn features with bi-directional lstm for real-time anomaly detection in surveillance networks. Multimedia Tools and Applications.
[Ullah et al., 2021b] Ullah, W., Ullah, A., Hussain, T., Khan, A., and Baik, S. W. (2021b). An efficient anomaly recognition framework using an attention residual lstm in surveillance videos. Sensors.
[Vahdani and Tian, 2023] Vahdani, E. and Tian, Y. (2023). Deep learning-based action detection in untrimmed videos: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4302–4320.
[Wan et al., 2021] Wan, B., Jiang, W., Fang, Y., Luo, Z., and Ding, G. (2021). Ano- maly detection in video sequences: A benchmark and computational model. CoRR, abs/2106.08570.
[Wu et al., 2021] Wu, J., Zhang, W., Li, G., Wu, W., Tan, X., Li, Y., Ding, E., and Lin, L. (2021). Weakly-supervised spatio-temporal anomaly detection in surveillance video.
[Wu et al., 2020] Wu, P., Liu, J., Shi, Y., Sun, Y., Shao, F., Wu, Z., and Yang, Z. (2020). Not only look, but also listen: Learning multimodal violence detection under weak supervision. Computer Vision and Pattern Recognition.
[Xu et al., 2022] Xu, Y., Huang, C., Nan, Y., and Lian, S. (2022). Tad: A large-scale bench- mark for traffic accidents detection from video surveillance.
[Zhang and Yu, 2018] Zhang, S. and Yu, H. (2018). Person re-identification by multi-camera networks for internet of things in smart cities. IEEE Access, 6.
[Zhong et al., 2019] Zhong, J.-X., Li, N., Kong, W., Liu, S., Li, T. H., and Li, G. (2019). Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1237–1246.
[Zhu and Yang, 2018] Zhu, C. and Yang, Y. (2018). Face detection and recognition ba- sed on deep learning in the monitoring environment. Communications in Computer and Information Science, pages 698–705.
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 91 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.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/86291/1/license.txt
https://repositorio.unal.edu.co/bitstream/unal/86291/2/1035421830.2024.pdf
https://repositorio.unal.edu.co/bitstream/unal/86291/3/1035421830.2024.pdf.jpg
bitstream.checksum.fl_str_mv eb34b1cf90b7e1103fc9dfd26be24b4a
4ecf56927d60e763d408fb33ef747a69
2d406dabb5968b5c3efabaf275295f98
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_ 1814089708115853312
spelling Reconocimiento 4.0 Internacionalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Bolaños Martinez, Freddye7acb79486e0b3abc2d30449661c78f9Londoño Lopera, Juan Camiloe9ea5c5274b189934a40536200a5f42cLuis Alejandro Fletscher Bocanegra2024-06-25T16:11:54Z2024-06-25T16:11:54Z2024https://repositorio.unal.edu.co/handle/unal/86291Universidad Nacional de ColombiaRepositorio Institucional Universidad Nacional de Colombiahttps://repositorio.unal.edu.co/Esta tesis se centra en el desarrollo de una aplicación para seguridad ciudadana mediante técnicas de aprendizaje de máquina, con el objetivo principal de detectar delitos a través del análisis de archivos de video. La investigación comienza con una revisión sistemática de las técnicas más relevantes, estableciendo criterios de selección que priorizan estructuras capaces de integrar eficientemente la dimensión temporal. Se favorecen modelos de aprendizaje de máquina, que ofrecen versatilidad para la incorporación de nuevos parámetros, especialmente aquellos basados en esquemas espacio-temporales, fundamentales para el análisis de video y la consideración del contexto temporal de los eventos. Dado que la recolección de datos extensos y etiquetados resulta inviable en el marco temporal del proyecto, se opta por utilizar simulaciones basadas en conjuntos de datos públicos en lı́nea diseñados especı́ficamente para la detección de delitos. Se selecciona cuidadosamente al menos un tipo de delito para la investigación, considerando su relevancia y disponibilidad de repeticiones para el desarrollo efectivo del modelo de predicción. La validación del modelo se lleva a cabo mediante una evaluación exhaustiva, utilizando diversos conjuntos de datos previamente seleccionados y parámetros clave de desempeño, como la curva ROC - AUC. Este enfoque integral busca garantizar la eficacia y aplicabilidad del modelo en entornos prácticos y del mundo real. (Texto tomado de la fuente)This thesis focuses on developing an application for public safety through machine learning techniques, with the primary goal of crime detection by analyzing video files. The research begins with a systematic review of the most relevant techniques, establishing selection criteria that prioritize structures capable of efficiently integrating the temporal dimension. Machine learning models are favored for their versatility in incorporating new parameters, especially those based on spatiotemporal schemes, crucial for video analysis and considering the temporal context of events. Since the collection of extensive and labeled data is impractical within the project’s timeframe, simulations based on publicly available online datasets specifically designed for crime detection are used. At least one type of crime is carefully selected for investigation, considering its relevance and the availability of repetitions for the effective development of the prediction model. Model validation is conducted through a comprehensive evaluation, utilizing various pre-selected datasets and key performance parameters, such as the ROC-AUC curve. This holistic approach seeks to ensure the effectiveness and applicability of the model in practical and real-world settings.MaestríaMagíster en Ingeniería - Automatización IndustrialSistemas de ingeniería inteligentesÁrea Curricular de Ingeniería Eléctrica e Ingeniería de Control91 páginasapplication/pdfspaUniversidad Nacional de ColombiaMedellín - Minas - Maestría en Ingeniería - Automatización IndustrialFacultad de MinasMedellín, ColombiaUniversidad Nacional de Colombia - Sede Medellín000 - Ciencias de la computación, información y obras generales::003 - SistemasAprendizaje automático (Inteligencia artificial)Redes neuronales (computadores)Predicción en la conducta criminalSeguridad ciudadanaAprendizaje de máquinaDetección de delitosModelos LSTMRedes Neuronales Convolucionales 3DPredicción de eventosSistemas de videovigilanciaPublic safetyMachine learningCrime detectionLSTM Models3D Convolutional Neural NetworksEvent PredictionVideovigilancia IPAplicación de técnicas de aprendizaje de máquina al análisis de archivos de video para la detección de delitosApplication of machine learning techniques to video file analysis for crime detectionTrabajo de grado - Maestríainfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/acceptedVersionTexthttp://purl.org/redcol/resource_type/TM[Acsintoae et al., 2021] Acsintoae, A., Florescu, A., Georgescu, M.-I., Mare, T., Sumedrea, P., Ionescu, R. T., Khan, F. S., and Shah, M. (2021). Ubnormal: New benchmark for supervised open-set video anomaly detection. Computer Vision and Pattern Recognition.[Adam et al., 2008] Adam, A., Rivlin, E., Shimshoni, I., and Reinitz, D. (2008). Robust real- time unusual event detection using multiple fixed-location monitors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(3):555–560[Althnian et al., 2021] Althnian, A., AlSaeed, D., Al-Baity, H., Samha, A., Dris, A. B., Al- zakari, N., Abou Elwafa, A., and Kurdi, H. (2021). Impact of dataset size on classification performance: An empirical evaluation in the medical domain. Applied Sciences, 11(2).[Anthopoulos, 2015] Anthopoulos, L. G. (2015). Understanding the Smart City Domain: A Literature Review, pages 9–21. Springer International Publishing, Cham.[Boekhoudt et al., 2021] Boekhoudt, K., Matei, A., Aghaei, M., and Talavera, E. (2021). Hr- crime: Human-related anomaly detection in surveillance videos. CoRR, abs/2108.00246.[Carreira and Zisserman, 2017] Carreira, J. and Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. pages 4724–4733.[Catlett et al., 2019] Catlett, C., Cesario, E., Talia, D., and Vinci, A. (2019). Spatio- temporal crime predictions in smart cities: A data-driven approach and experiments. Pervasive and Mobile Computing, 53.[Cheng et al., 2021] Cheng, M., Cai, K., and Li, M. (2021). Rwf-2000: An open large scale video database for violence detection. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 4183–4190.[Degardin and Proença, 2021] Degardin, B. and Proença, H. (2021). Iterative weak/self- supervised classification framework for abnormal events detection. Pattern Recognition Letters, 145:50–57.[Dubey et al., 2019] Dubey, S., Boragule, A., and Jeon, M. (2019). 3d resnet with ranking loss function for abnormal activity detection in videos. In 2019 International Conference on Control, Automation and Information Sciences (ICCAIS), pages 1–6.[Farnebäck, 2003] Farnebäck, G. (2003). Two-frame motion estimation based on polynomial expansion. volume 2749, pages 363–370[Feng et al., 2021] Feng, J.-C., Hong, F.-T., and Zheng, W.-S. (2021). Mist: Multiple ins- tance self-training framework for video anomaly detection. pages 14004–14013.[Gemmeke et al., 2017] Gemmeke, J. F., Ellis, D. P. W., Freedman, D., Jansen, A., Law- rence, W., Moore, R. C., Plakal, M., and Ritter, M. (2017). Audio set: An ontology and human-labeled dataset for audio events. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 776–780.[Gorr et al., 2003] Gorr, W., Olligschlaeger, A., and Thompson, Y. (2003). Short-term fo- recasting of crime. International Journal of Forecasting, 19.[Hasan et al., 2016] Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A. K., and Davis, L. S. (2016). Learning temporal regularity in video sequences. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 733–742.[Hershey et al., 2016] Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., Slaney, M., Weiss, R. J., and Wilson, K. W. (2016). CNN architectures for large-scale audio classification. CoRR, abs/1609.09430.[Isafiade and Bagula, 2020] Isafiade, O. E. and Bagula, A. B. (2020). Series mining for public safety advancement in emerging smart cities. Future Generation Computer Systems, 108.[Kamoona et al., 2023] Kamoona, A. M., Gostar, A. K., Bab-Hadiashar, A., and Hosein- nezhad, R. (2023). Multiple instance-based video anomaly detection using deep temporal encoding–decoding. Expert Systems with Applications, 214:119079.[Karpathy et al., 2014] Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., and Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In CVPR.[Kliper-Gross et al., 2012] Kliper-Gross, O., Hassner, T., and Wolf, L. (2012). The action similarity labeling challenge. IEEE Transactions on Pattern Analysis and Machine Inte- lligence, 34:615–621.[Landi et al., 2019] Landi, F., Snoek, C. G. M., and Cucchiara, R. (2019). Anomaly locality in video surveillance. ArXiv, abs/1901.10364.[Lu et al., 2013] Lu, C., Shi, J., and Jia, J. (2013). Abnormal event detection at 150 fps in matlab. In 2013 IEEE International Conference on Computer Vision, pages 2720–2727.[Luo et al., 2017] Luo, W., Liu, W., and Gao, S. (2017). A revisit of sparse coding based anomaly detection in stacked rnn framework. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 341–349.[Lv et al., 2021a] Lv, H., Chen, C., Cui, Z., Xu, C., Li, Y., and Yang, J. (2021a). Learning normal dynamics in videos with meta prototype network. Computer Vision and Pattern Recognition.[Lv et al., 2021b] Lv, H., Zhou, C., Cui, Z., Xu, C., Li, Y., and Yang, J. (2021b). Localizing anomalies from weakly-labeled videos. Computer Vision and Pattern Recognition.[Mahadevan et al., 2010] Mahadevan, V., Li, W., Bhalodia, V., and Vasconcelos, N. (2010). Anomaly detection in crowded scenes. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 1975–1981.[Majhi et al., 2021] Majhi, S., Das, S., Bremond, F., Dash, R., and Sa, P. (2021). Weakly- supervised joint anomaly detection and classification. In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pages 1–7, Los Ala- mitos, CA, USA. IEEE Computer Society.[Maqsood et al., 2021] Maqsood, R., Bajwa, U., Saleem, G., Raza, R., and Anwar, M. (2021). Anomaly recognition from surveillance videos using 3d convolutional neural networks.[Medapati et al., 2019] Medapati, P. K., Murthy, P. H. S. T., and Sridhar, K. P. (2019). Lamstar: For iot-based face recognition system to manage the safety factor in smart cities. Transactions on Emerging Telecommunications Technologies.[Mehran et al., 2009] Mehran, R., Oyama, A., and Shah, M. (2009). Abnormal crowd beha- vior detection using social force model. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 935–942.[OECD, 2021] OECD (2021). OECD, “Better life index, security”. Accedido: 2022-03-17.[Oh, 2011] Oh, S. (2011). A new dataset evaluation method based on category overlap. Computers in Biology and Medicine, 41(2):115–122.[Pang et al., 2019] Pang, Y., Zhang, L., Ding, H., Fang, Y., and Chen, S. (2019). Spath: Fin- ding the safest walking path in smart cities. IEEE Transactions on Vehicular Technology, 68.[Perez et al., 2019] Perez, M., Kot, A. C., and Rocha, A. (2019). Detection of real-world fights in surveillance videos. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2662–2666.[Ramzan et al., 2019] Ramzan, M., Abid, A., Khan, H. U., Awan, S. M., Ismail, A., Ahmed, M., Ilyas, M., and Mahmood, A. (2019). A review on state-of-the-art violence detection techniques. IEEE Access, 7:107560–107575.[Rathore et al., 2016] Rathore, M., Ahmad, A., Paul, A., and Rho, S. (2016). Urban planning and building smart cities based on the internet of things using big data analytics. Computer Networks, 101:63–80.[Rathore et al., 2018] Rathore, M., Paul, A., Ahmad, A., Chilamkurti, N., Hong, W.-H., and Seo, H. (2018). Real-time secure communication for smart city in high-speed big data environment. Future Generation Computer Systems, 83:638–652.[Sandler et al., 2018] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.[SIEDCO, 2021] SIEDCO (2021). Estadı́stica delictiva. Accedido: 2022-03-23.[Simić et al., 2020] Simić, M., Perić, M., Popadić, I., Perić, D., Pavlović, M., Vučetić, M., and Stanković, M. (2020). Big data and development of smart city: System architecture and practical public safety example. Serbian Journal of Electrical Engineering, 17:337–355.[Soliman et al., 2019] Soliman, M. M., Kamal, M. H., El-Massih Nashed, M. A., Mostafa, Y. M., Chawky, B. S., and Khattab, D. (2019). Violence recognition from videos using deep learning techniques. In 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS), pages 80–85.[Soomro et al., 2012] Soomro, K., Zamir, A. R., and Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. CoRR, abs/1212.0402.[Sultani et al., 2019] Sultani, W., Chen, C., and Shah, M. (2019). Real-world anomaly de- tection in surveillance videos. Computer Vision and Pattern Recognition.[Tian et al., 2021] Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J. W., and Carnei- ro, G. (2021). Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. Computer Vision and Pattern Recognition.[Tran et al., 2015] Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. pages 4489–4497.[Ullah and Petrosino, 2017] Ullah, I. and Petrosino, A. (2017). A spatiotemporal feature learning approach for dynamic scene recognition.[Ullah et al., 2021a] Ullah, W., Ullah, A., Haq, I. U., Muhammad, K., Sajjad, M., and Baik, S. W. (2021a). Cnn features with bi-directional lstm for real-time anomaly detection in surveillance networks. Multimedia Tools and Applications.[Ullah et al., 2021b] Ullah, W., Ullah, A., Hussain, T., Khan, A., and Baik, S. W. (2021b). An efficient anomaly recognition framework using an attention residual lstm in surveillance videos. Sensors.[Vahdani and Tian, 2023] Vahdani, E. and Tian, Y. (2023). Deep learning-based action detection in untrimmed videos: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4302–4320.[Wan et al., 2021] Wan, B., Jiang, W., Fang, Y., Luo, Z., and Ding, G. (2021). Ano- maly detection in video sequences: A benchmark and computational model. CoRR, abs/2106.08570.[Wu et al., 2021] Wu, J., Zhang, W., Li, G., Wu, W., Tan, X., Li, Y., Ding, E., and Lin, L. (2021). Weakly-supervised spatio-temporal anomaly detection in surveillance video.[Wu et al., 2020] Wu, P., Liu, J., Shi, Y., Sun, Y., Shao, F., Wu, Z., and Yang, Z. (2020). Not only look, but also listen: Learning multimodal violence detection under weak supervision. Computer Vision and Pattern Recognition.[Xu et al., 2022] Xu, Y., Huang, C., Nan, Y., and Lian, S. (2022). Tad: A large-scale bench- mark for traffic accidents detection from video surveillance.[Zhang and Yu, 2018] Zhang, S. and Yu, H. (2018). Person re-identification by multi-camera networks for internet of things in smart cities. IEEE Access, 6.[Zhong et al., 2019] Zhong, J.-X., Li, N., Kong, W., Liu, S., Li, T. H., and Li, G. (2019). Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1237–1246.[Zhu and Yang, 2018] Zhu, C. and Yang, Y. (2018). Face detection and recognition ba- sed on deep learning in the monitoring environment. Communications in Computer and Information Science, pages 698–705.Público generalLICENSElicense.txtlicense.txttext/plain; charset=utf-85879https://repositorio.unal.edu.co/bitstream/unal/86291/1/license.txteb34b1cf90b7e1103fc9dfd26be24b4aMD51ORIGINAL1035421830.2024.pdf1035421830.2024.pdfTesis de Maestría en Ingeniería - Automatización Industrialapplication/pdf1334831https://repositorio.unal.edu.co/bitstream/unal/86291/2/1035421830.2024.pdf4ecf56927d60e763d408fb33ef747a69MD52THUMBNAIL1035421830.2024.pdf.jpg1035421830.2024.pdf.jpgGenerated Thumbnailimage/jpeg5276https://repositorio.unal.edu.co/bitstream/unal/86291/3/1035421830.2024.pdf.jpg2d406dabb5968b5c3efabaf275295f98MD53unal/86291oai:repositorio.unal.edu.co:unal/862912024-08-25 23:11:51.677Repositorio Institucional Universidad Nacional de Colombiarepositorio_nal@unal.edu.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

Publicaciones similares