Detección y conteo de evasores en el sistema de transporte Transmilenio

Vista sencilla de ítem
dc.contributor.advisorPedraza Bonilla, César Augustospa
dc.contributor.authorRodríguez Peraza, César Ivanspa
dc.contributor.refereePerdomo Charry, Oscar Julianspa
dc.contributor.refereeZona Ortiz, Angela Tatianaspa
dc.contributor.researchgroupPlas Programming languages And Systemsspa
dc.coverage.countryColombiaspa
dc.coverage.regionCundinamarcaspa
dc.coverage.tgnhttp://vocab.getty.edu/page/tgn/1000583
dc.date.accessioned2025-04-11T17:11:59Z
dc.date.available2025-04-11T17:11:59Z
dc.date.issued2024
dc.descriptionilustraciones, diagramas, fotografíasspa
dc.description.abstractBogotá se encuentra entre las veinte ciudades con peor tráfico del mundo de acuerdo con el Ranking del Índice de Tráfico. Además, carece de un sistema de transporte público robusto; el sistema TransMilenio, en particular, presenta deficiencias operativas y económicas que agravan los problemas de movilidad en la ciudad. La más destacada de estas deficiencias es la evasión de pago, un fenómeno que hasta ahora ha sido difícil de cuantificar y, por consiguiente, de mitigar. Por esta razón, el objetivo de este trabajo es detectar y cuantificar a los evasores en los torniquetes del sistema TransMilenio. Para lograrlo, se exploraron diversas técnicas de procesamiento de imágenes y video, así como aprendizaje automático e inteligencia artificial. Este trabajo enfrenta varios retos, entre los que destacan el marcado desequilibrio en el conjunto de datos (3 de cada 100 personas son evasores), la sutileza en algunos eventos de evasión y los complejos entornos de las estaciones. El modelo con mejores resultados es capaz de identificar el 95% de los evasores, gracias a la aplicación de conceptos de vanguardia en aprendizaje no supervisado y auto-supervisado. (Texto tomado de la fuente).spa
dc.description.abstractBogotá ranks among the top 20 cities with the worst traffic according to Traffic Index. Furthermore, Bogotá lacks a robust public transportation system; TransMilenio has significant operational and financial shortcomings, which worsen the mobility issues in the city. One of the most prominent issues is fare evasion, a phenomenon that has been difficult to quantify. The primary objective of this study is to detect and quantify fare evaders at the turnstiles of TransMilenio. To achieve this, a variety of techniques were explored across fields such as image and video processing, machine learning, and artificial intelligence. This work faces several challenges, mainly the heavily imbalanced dataset (3 out of 100 people are evaders), the subtlety of some evasion events, and the complex environments in the stations. The model that yielded the best results can detect approximately 95% of fare evaders through the application of cutting-edge concepts in unsupervised and self-supervised learning.eng
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería - Ingeniería de Sistemas y Computaciónspa
dc.description.researchareaVisión por computadora y aprendizaje de máquinaspa
dc.format.extentxi, 102 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/87944
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.facultyFacultad de Ingenieríaspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Ingeniería - Maestría en Ingeniería - Ingeniería de Sistemas y Computaciónspa
dc.relation.references15 de cada 100 usuarios se cuelan en el sistema, estrategia anti-evasión de TransMilenio. https://www.transmilenio.gov.co/publicaciones/151223/15-de-cada-100-usuarios-se-cuelan-en-el-sistema-estrategia-anti-evasion-de-transmilenio/spa
dc.relation.referencesMTA Board and Committee Meetings. https://new.mta.info/transparency/board-and-committee-meetings. – Accessed: 2024spa
dc.relation.referencesTomTom Tra!c Index Ranking. https://www.tomtom.com/traffic-index/ranking/?country=CO Accessed: March 30, 2024spa
dc.relation.referencesAggarwal, J. ; Ryoo, M.: Human Activity Analysis: A Review. En: ACM Comput. Surv. 43 (2011), 04, p. 16spa
dc.relation.referencesAlex Graves, J¨urgen S.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. En: Neural Networks 18 (2005), Nr. 5-6, p. 602–610spa
dc.relation.referencesAlex Kafkas, Daniela Montaldi: How do memory systems detect and respond to novelty? En: Neuroscience Letters 680 (2018), p. 60–68spa
dc.relation.referencesAndrej Karpathy, Sanketh Shetty Thomas Leung-Rahul S. ; Fei-Fei, Li: Large- scale video classification with convolutional neural networks. En: Conference on Com- puter Vision and Pattern Recognition (CVPR), 2014, p. 1725–1732spa
dc.relation.referencesArnab, Anurag ; Dehghani, Mostafa ; Heigold, Georg ; Sun, Chen ; Lucic, Mario; Schmid, Cordelia: Vivit: A video vision transformer. (2021)spa
dc.relation.referencesAssran, Mahmoud ; Caron, Mathilde ; Misra, Ishan ; Bojanowski, Piotr ; Jou- lin, Armand ; Ballas, Nicolas ; Rabbat, Michael G.: Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples. En: CoRR abs/2104.13963 (2021)spa
dc.relation.referencesBaik, Sungyong ; Choi, Janghoon ; Kim, Heewon ; Cho, Dohee ; Min, Jaesik ; Lee, Kyoung M.: Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning. En: CoRR abs/2110.03909 (2021)spa
dc.relation.referencesBarrett, Louise F.: Superior pattern processing is the essence of the evolved human brain. En: Frontiers in Neuroscience 6 (2012), p. 116spa
dc.relation.referencesBertasius, Gedas ; Wang, Heng ; Torresani, Lorenzo: Is Space-Time Attention All You Need for Video Understanding?, 2021spa
dc.relation.referencesBobick, A. F. ; Davis, J. W.: The recognition of human movement using temporal templates. En: IEEE Transactions on Pattern Analysis and Machine Intelligence 23 (2001), Nr. 3, p. 257–267spa
dc.relation.referencesde Bogotá, Consejo: Preocupante la situación del sistema integrado de transporte y el fondo. 2024. – Accessed: 2024-09-28spa
dc.relation.referencesC. R. Wren, T. D. ; Pentland, A. P.: Pfinder: Real-time tracking of the human body. En: IEEE Transactions on Pattern Analysis and Machine Intelligence 19 (1997), Nr. 7, p. 780–785spa
dc.relation.referencesCaron, Mathilde ; Touvron, Hugo ; Misra, Ishan ; J´ egou, Herv´e ; Mairal, Julien ; Bojanowski, Piotr ; Joulin, Armand: Emerging Properties in Self-Supervised Vision Transformers. En: CoRR abs/2104.14294 (2021)spa
dc.relation.referencesCarreira, Joao ; Zisserman, Andrew: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, 2018spa
dc.relation.referencesCarrillo, Libardo Andrés M.: ¿La política pública de transporte público masivo en Bogotá es adecuada para garantizar el derecho al acceso a un servicio de transporte de calidad? Caso TransMilenio como eje central de movilidad en Bogotá. https://repository.javeriana.edu.co/bitstream/handle/10554/21837/MarinCarrilloLibardoAndres2 →Accessed : M arch30, 2024spa
dc.relation.referencesCewu Lu, Jianping S. ; Jia, Jiaya: Abnormal Event Detection at 150 FPS in Matlab, 2013spa
dc.relation.referencesChalapathy, Raghavendra ; Chawla, Sanjay. Deep Learning for Anomaly Detection: A Survey. 2019spa
dc.relation.referencesChen, Chenliang ; Jafari, Roozbeh ; Kehtarnavaz, Nasser: UTD-MHAD: A Mul- timodal Dataset for Human Action Recognition Utilizing a Depth Camera and a Wea- rable Inertial Sensor. En: Proceedings of the IEEE International Conference on Image Processing (ICIP) (2015), p. 168–172spa
dc.relation.referencesChen, Chun-Fu ; Panda, Rameswar ; Fan, Quanfu: RegionViT: Regional-to-Local Attention for Vision Transformers, 2022spa
dc.relation.referencesChen, Renwang ; Chen, Xuanhong ; Ni, Bingbing ; Ge, Yanhao: SimSwap: An Effcient Framework For High Fidelity Face Swapping. En: Proceedings of the 28th ACM International Conference on Multimedia, ACM, Oktober 2020 (MM ’20)spa
dc.relation.referencesCho, Kyunghyun ; van Merrienboer, Bart ; Gulcehre, Caglar ; Bahdanau, Dzmitry ; Bougares, Fethi ; Schwenk, Holger ; Bengio, Yoshua: Learning phrase representations using RNN encoder-decoder for statistical machine translation. (2014)spa
dc.relation.referencesChong, Yong S. ; Tay, Yong H.: Abnormal Event Detection in Videos using Spatio- temporal Autoencoder. En: CoRR abs/1701.01546 (2017)spa
dc.relation.referencesCole, Leonard E.: The Central Nervous System and Behavior. New York : McGraw- Hill Book Company, 1939spa
dc.relation.referencesDoersch, Carl ; Yang, Yi ; Vecerik, Mel ; Gokay, Dilara ; Gupta, Ankush ; Aytar, Yusuf ; Carreira, Joao ; Zisserman, Andrew. TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement. 2023spa
dc.relation.referencesDonahue, Je# ; Hendricks, Lisa A. ; Rohrbach, Marcus ; Venugopalan, Sub- hashini ; Guadarrama, Sergio ; Saenko, Kate ; Darrell, Trevor: Long-term re- current convolutional networks for visual recognition and description. (2016)spa
dc.relation.referencesDosovitskiy, Alexey ; Beyer, Lucas ; Kolesnikov, Alexander ; Weissenborn, Dirk ; Zhai, Xiaohua ; Unterthiner, Thomas ; Dehghani, Mostafa ; Minderer, Matthias ; Heigold, Georg ; Gelly, Sylvain ; Uszkoreit, Jakob ; Houlsby, Neil: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. En: International Conference on Learning Representations (ICLR), 2021spa
dc.relation.referencesEl Colombiano: Dueños de perrita que quedó atrapada en los torniquetes anticolados de TransMilenio tuvieron que cortarlos con una segueta. 2024. – Consultado: 2024-10-21spa
dc.relation.referencesEl Espectador: Torniquetes anticolados: TransMilenio confirma que por ahora no instalarán más. 2024. – Consultado: 2024-10-21spa
dc.relation.referencesFabian Caba Heilbron, Bernard G. ; Niebles, Juan C. ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding. 2015spa
dc.relation.referencesFaisal I. Bashir, Ashfaq A. K. ; Schonfeld, Dan: Object Trajectory-Based Acti- vity Classification and Recognition Using Hidden Markov Models. En: IEEE Transac- tions on Image Processing 16 (2007), Nr. 7, p. 1912–1919spa
dc.relation.referencesFeichtenhofer, Christoph ; Fan, Haoqi ; Malik, Jitendra ; He, Kaiming: SlowFast Networks for Video Recognition, 2019spa
dc.relation.referencesFeichtenhofer, Christoph ; Pinz, Axel ; Zisserman, Andrew: Convolutional Two- Stream Network Fusion for Video Action Recognition, 2016spa
dc.relation.referencesFinn, Chelsea ; Abbeel, Pieter ; Levine, Sergey: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. En: CoRR abs/1703.03400 (2017)spa
dc.relation.referencesGong, Dong ; Liu, Lingqiao ; Le, Vuong ; Saha, Budhaditya ; Mansour, Mous- sa R. ; Venkatesh, Svetha ; van den Hengel, Anton: Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection. En: CoRR abs/1904.02639 (2019)spa
dc.relation.referencesHasan, Mahmudul ; Choi, Jonghyun ; Neumann, Jan ; Roy-Chowdhury, Amit K. ; Davis, Larry S.: Learning Temporal Regularity in Video Sequences. En: CoRR abs/1604.04574 (2016)spa
dc.relation.referencesHassan, Nasim ; Xu, Jie: An ensemble approach to anomaly detection. En: Procee- dings of the 2012 IEEE Symposium on Computational Intelligence and Data Mining, 2012, p. 135–142spa
dc.relation.referencesHeng Wang, Cordelia S. ; Liu, Cheng-Lin: Dense trajectories and motion boundary descriptors for action recognition. En: International Journal of Computer Vision, 2011spa
dc.relation.referencesHuang, Xin ; Xiong, Yu ; Dai, Xiyang ; Theis, Lucas [u. a.]: E!cient Video Trans- former with Temporal Attention. En: arXiv preprint arXiv:2208.08613 (2022)spa
dc.relation.referencesIslam, Md. M. ; Nooruddin, Sheikh ; Karray, Fakhri ; Muhammad, Ghulam: Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and future prospects. En: Computers in Biology and Medicine 149 (2022), p. 106060. – ISSN 0010–4825spa
dc.relation.referencesIsola, Phillip ; Zhu, Jun-Yan ; Zhou, Tinghui ; Efros, Alexei A.: Image-to-Image Translation with Conditional Adversarial Networks. En: CoRR abs/1611.07004 (2016)spa
dc.relation.referencesIvan Laptev, Cordelia S. ; Rozenfeld, Benjamin: Learning realistic human actions from movies. En: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008spa
dc.relation.referencesIvanov, Y. A. ; Bobick, A. F.: Recognition of visual activities and interactions by sto- chastic parsing. En: IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (2000), Nr. 8, p. 852–872spa
dc.relation.referencesKaraev, Nikita ; Rocco, Ignacio ; Graham, Benjamin ; Neverova, Natalia ; Ve- daldi, Andrea ; Rupprecht, Christian. CoTracker: It is Better to Track Together. 2024spa
dc.relation.referencesKay, Will ; Carreira, Joao ; Simonyan, Karen ; Zhang, Brian ; Hillier, Chloe ; Vijayanarasimhan, Sudheendra ; Viola, Fabio ; Green, Tim ; Back, Trevor ; Natsev, Paul ; Suleyman, Mustafa ; Zisserman, Andrew. The Kinetics Human Action Video Dataset. 2017spa
dc.relation.referencesKe, Yan ; Sukthankar, Rahul: PCA-SIFT: A more distinctive representation for local image descriptors. En: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2004, p. 506–513spa
dc.relation.referencesKevin Chavez, Garrick Fernandez Noah Jackson Will L.: Course Notes. 2017-2018. – Retrieved from the Stanford Vision Lab websitespa
dc.relation.referencesKingma, Diederik P. ; Rezende, Danilo J. ; Mohamed, Shakir ; Welling, Max: Semi-Supervised Learning with Deep Generative Models. (2014)spa
dc.relation.referencesKirillov, Alexander ; Mintun, Eric ; Ravi, Nikhila ; Mao, Hanzi ; Rolland, Chloe ; Gustafson, Laura ; Xiao, Tete ; Whitehead, Spencer ; Berg, Alexander C. ; Lo, Wan-Yen ; Doll´ ar, Piotr ; Girshick, Ross. Segment Anything. 2023spa
dc.relation.referencesKoch, Gregory ; Zemel, Richard ; Salakhutdinov, Ruslan: Siamese Neural Net- works for One-shot Image Recognition. En: Proceedings of the International Conference on Machine Learning (ICML). University of Toronto, Toronto, Ontario, Canada, 2015spa
dc.relation.referencesKrizhevsky, Alex ; Sutskever, Ilya ; Hinton, Geoffrey E.: ImageNet classification with deep convolutional neural networks. En: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. Red Hook, NY, USA : Curran Associates Inc., 2012 (NIPS’12), p. 1097–1105spa
dc.relation.referencesKuehne, H. ; Jhuang, H. ; Garrote, E. ; Poggio, T. ; Serre, T. HMDB: A Large Human Motion Database. 2011spa
dc.relation.referencesKumar, Varun ; Nandi, G.C. ; Kala, Rahul: Static hand gesture recognition using stacked Denoising Sparse Autoencoders. En: 2014 Seventh International Conference on Contemporary Computing (IC3), 2014, p. 99–104spa
dc.relation.referencesLaptev, Ivan: On space-time interest points. En: International Journal of Computer Vision 64 (2005), Nr. 2-3, p. 107–123spa
dc.relation.referencesLaura Daniela Gómez Rodríguez, María García F.: ¿Por qué TransMilenio en Bogotá está en crisis? En: Revista Ciudad. Estados Pol´ıtica 4 (2017), Nr. 3, p. 103–118. – ISSN 2389–8437spa
dc.relation.referencesLee, Kwonjoon ; Maji, Subhransu ; Ravichandran, Avinash ; Soatto, Stefano: Meta-Learning with Di#erentiable Convex Optimization. En: CoRR abs/1904.03758 (2019)spa
dc.relation.referencesLicheng Zhang, Xihong W. ; Luo, Dingsheng: Human activity recognition with HMM-DNN model. En: 2015 IEEE 14th International Conference on Cognitive Infor- matics Cognitive Computing (ICCI*CC), 2015, p. 192–197spa
dc.relation.referencesLin, Yuanze ; Guo, Xun ; Lu, Yan: Self-Supervised Video Representation Learning with Meta-Contrastive Network. En: CoRR abs/2108.08426 (2021)spa
dc.relation.referencesLiu, Wen ; Luo, Weixin ; Lian, Dongze ; Gao, Shenghua. Future Frame Prediction for Anomaly Detection – A New Baseline. 2018spa
dc.relation.referencesLiu, Zhuang ; Mao, Hanzi ; Wu, Chao-Yuan ; Feichtenhofer, Christoph ; Darrell, Trevor ; Xie, Saining. A ConvNet for the 2020s. 2022spa
dc.relation.referencesLuis A. Guzman, Jose Pablo C.: A Hybrid Discrete Choice Model to Understand the Effect of Public Policy on Fare Evasion Discouragement in Bogotá’s Bus Rapid Transit. En: Transportation Research Part A: Policy and Practice 151 (2021), p. 140–153spa
dc.relation.referencesLópez, Luis Alfonso G. Relación entre Políticas Públicas de Transporte y Ambiental sobre la dinámica de crecimiento del parque de motocicletas y la calidad del aire de Bogotá durante el período 2012-2015. URI: https://ridum.umanizales.edu.co/xmlui/handle/20.500.12746/4350. 2019spa
dc.relation.referencesMahadevan, Vijay ; AbdAlmageed, Wael ; Natarajan, Premkumar. UCSD Pe- destrian Dataset. http://www.svcl.ucsd.edu/projects/peoplecnt/db/readme.pdf. 2010spa
dc.relation.referencesMathieu, Michael ; Couprie, Camille ; LeCun, Yann. Deep multi-scale video pre- diction beyond mean square error. 2016spa
dc.relation.referencesMd Golam Morshed, Aftab A. ; Lee, Young-Koo: Human Action Recognition: A Taxonomy-Based Survey, Updates, and Opportunities. En: Sensors 23 (2023), p. 2182spa
dc.relation.referencesMisra, Ishan ; Zitnick, C. L. ; Hebert, Martial. Shuffle and Learn: Unsupervised Learning using Temporal Order Verification. 2016spa
dc.relation.referencesNeloy, Asif A. ; Turgeon, Maxime: A comprehensive study of auto-encoders for anomaly detection: Efficiency and trade-offs. En: Machine Learning with Applications 17 (2024), p. 100572. – ISSN 2666–8270spa
dc.relation.referencesPang, Guansong ; Shen, Chunhua ; Cao, Longbing ; Hengel, Anton Van D.: Deep Learning for Anomaly Detection: A Review. En: ACM Computing Surveys 54 (2021), März, Nr. 2, p. 1–38. – ISSN 1557–7341spa
dc.relation.referencesPiciarelli, Claudio ; Micheloni, Christian ; Foresti, Gian L.: Trajectory-based anomalous event detection. En: IEEE Transactions on Circuits and Systems for Video Technology Vol. 18, 2008, p. 1544–1554spa
dc.relation.referencesReiss, Tal ; Cohen, Niv ; Horwitz, Eliahu ; Abutbul, Ron ; Hoshen, Yedid. Anomaly Detection Requires Better Representations. 2022spa
dc.relation.referencesRombach, Robin ; Ho, Jonathan ; Salimans, Tim ; Kreis, Karsten ; Esser, Patrick ; Ommer, Björn: Latent Di#usion Models for Video Generation. En: arXiv preprint arXiv:2204.03692 (2022)spa
dc.relation.referencesS.A., TransMilenio: Notas de Estados Financieros - Diciembre 2023. https://www.transmilenio.gov.co/publicaciones/153921/notas-de-estados-financieros- diciembre-2023/. 2023. – Accessed: March 30, 2024spa
dc.relation.referencesS.A., TransMilenio: Informe 2024 sobre el sistema de TransMilenio. 2024. – Accessed: 2024-09-28spa
dc.relation.referencesSabokrou, Mohammad ; Fayyaz, Mohsen ; Fathy, Mahmood ; Klette, Reinhard: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes. En: CoRR abs/1609.00866 (2016)spa
dc.relation.referencesSchlegl, Thomas ; Seeböck, Philipp ; et al.: AnoGAN: Deep Anomaly Detection using Generative Adversarial Networks. En: Medical Image Analysis 53 (2017), p. 27–38spa
dc.relation.referencesShahroudy, Amir ; Liu, Jun ; Ng, Tian-Tsong ; Wang, Gang: NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis. En: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, p. 1010–1019spa
dc.relation.referencesShannon, C.E.: A Mathematical Theory of Communication. En: Bell System Technical Journal 27 (1948), Nr. 3, p. 379–423spa
dc.relation.referencesShuchang, Zhou. A Survey on Human Action Recognition. 2022spa
dc.relation.referencesSimonyan, Karen ; Zisserman, Andrew: Two-stream convolutional networks for action recognition in videos. (2014)spa
dc.relation.referencesSoomro, Khurram ; Zamir, Amir R. ; Shah, Mubarak. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. 2012spa
dc.relation.referencesSrivastava, Nitish ; Mansimov, Elman ; Salakhutdinov, Ruslan: Unsupervised learning of video representations using LSTMs. (2016)spa
dc.relation.referencesSultani, Waqas ; Chen, Chen ; Shah, Mubarak. Real-world Anomaly Detection in Surveillance Videos. 2019spa
dc.relation.referencesTran, Du ; Bourdev, Lubomir ; Fergus, Rob ; Torresani, Lorenzo ; Paluri, Manohar: Learning spatiotemporal features with 3D convolutional networks, 2015spa
dc.relation.referencesTran, Du ; Wang, Heng ; Torresani, Lorenzo ; Feiszli, Matt: Video Classification with Channel-Separated Convolutional Networks. En: CoRR abs/1904.02811 (2019)spa
dc.relation.referencesTran, Du ; Wang, Heng ; Torresani, Lorenzo ; Ray, Jamie ; LeCun, Yann ; Paluri, Manohar. A Closer Look at Spatiotemporal Convolutions for Action Recognition. 2018spa
dc.relation.referencesTransMilenio: Este 2023 la línea base de evasión disminuyó hasta ubicarse en 15.32 %. https://www.transmilenio.gov.co/publicaciones/153766/este-2023-la-linea-base-de-evasion-disminuyo-hasta-ubicarse-en-1532/descargar.php?idFile=57267. 2023. – Accessed: 2024-10-14spa
dc.relation.referencesVoleti, Vikram ; Jolicoeur-Martineau, Alexia ; Pal, Christopher. MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation. 2022spa
dc.relation.referencesWang, Heng ; Schmid, Cordelia: Action Recognition with Improved Trajectories. En: Proceedings of the IEEE International Conference on Computer Vision (ICCV) IEEE, 2013, p. 3351–3358spa
dc.relation.referencesWang, Jing ; Xu, Zhijie: Spatio-temporal texture modelling for real-time crowd anomaly detection. En: Computer Vision and Image Understanding 144 (2016), p. 177–187. – Individual and Group Activities in Video Event Analysis. – ISSN 1077–3142spa
dc.relation.referencesWang, Limin ; Qiao, Yu ; Tang, Xiaoou: Action recognition with trajectory-pooled deep-convolutional descriptors. En: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Juni 2015spa
dc.relation.referencesWang, Limin ; Xiong, Yuanjun ; Wang, Zhe ; Qiao, Yu ; Lin, Dahua ; Tang, Xiaoou ; Gool, Luc V.: Temporal Segment Networks: Towards Good Practices for Deep Action Recognition, 2016spa
dc.relation.referencesWang, Yunbo ; Gao, Zhifeng ; Long, Mingsheng ; Wang, Jianmin ; Yu, Philip S.: PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. En: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), 2017spa
dc.relation.referencesWang, Yunbo ; Long, Mingsheng ; Wang, Jianmin ; Yu, Philip S.: Spatiotemporal Pyramid Network for Video Action Recognition. (2019)spa
dc.relation.referencesXu, Jiehui ; Wu, Haixu ; Wang, Jianmin ; Long, Mingsheng. Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy. 2021spa
dc.relation.referencesYan, Shen ; Xiong, Xuehan ; Arnab, Anurag ; Lu, Zhichao ; Zhang, Mi ; Sun, Chen ; Schmid, Cordelia: Multiview Transformers for Video Recognition, 2022spa
dc.relation.referencesYunbo Wang, Ming-Hsuan Yang Li-Jia Li Mingsheng Long Li Fei-Fei: Eidetic 3D LSTM: A Model for Video Prediction and Beyond. En: Proceedings of the 6th International Conference on Learning Representations (ICLR), 2018spa
dc.relation.referencesZhang, Bowen ; Yu, Jiahui ; Fifty, Christopher ; Han, Wei ; Dai, Andrew M. ; Pang, Ruoming ; Sha, Fei: Co-training Transformer with Videos and Images Improves Action Recognition. (2021)spa
dc.relation.referencesZhao, Hang ; Gallo, Orazio ; Frosio, Iuri ; Kautz, Jan: Loss Functions for Image Restoration With Neural Networks. En: IEEE Transactions on Computational Imaging 3 (2017), Nr. 1, p. 47–57spa
dc.relation.referencesZhou, Shifu ; Shen, Wei ; Zeng, Dan ; Fang, Mei ; Wei, Yuanwang ; Zhang, Zhijiang: Spatial-temporal Convolutional Neural Networks for Anomaly Detection and Localization in Crowded Scenes. En: Signal Processing: Image Communication 47 (2016), 07spa
dc.relation.referencesZhu, Yi ; Zolfaghari, Mohammadreza ; Zeng, Zhaoyang [u. a.]: MOLO-VT: Motion and Location-aware Video Transformer for Action Recognition. En: arXiv preprint arXiv:2207.05920 (2022)spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseReconocimiento 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/spa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::004 - Procesamiento de datos Ciencia de los computadoresspa
dc.subject.ddc360 - Problemas y servicios sociales; asociaciones::361 - Problemas sociales y serviciosspa
dc.subject.proposalAprendizaje de máquinaspa
dc.subject.proposalProcesamiento de videospa
dc.subject.proposalAumento de datosspa
dc.subject.proposalAprendizaje no supervisadospa
dc.subject.proposalAprendizaje auto-supervisadospa
dc.subject.proposalMachine learningeng
dc.subject.proposalVideo processingeng
dc.subject.proposalData augmentationeng
dc.subject.proposalUnsupervised learningeng
dc.subject.proposalSelf-supervised learningeng
dc.subject.wikidataprevención del delitospa
dc.subject.wikidatacrime preventioneng
dc.subject.wikidataaprendizaje automáticospa
dc.subject.wikidatamachine learningeng
dc.subject.wikidataTransMileniospa
dc.subject.wikidataTransMilenioeng
dc.titleDetección y conteo de evasores en el sistema de transporte Transmileniospa
dc.title.translatedDetection and counting of fare evaders in the TransMilenio transport systemeng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentAdministradoresspa
dcterms.audience.professionaldevelopmentBibliotecariosspa
dcterms.audience.professionaldevelopmentConsejerosspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentGrupos comunitariosspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentMaestrosspa
dcterms.audience.professionaldevelopmentMedios de comunicaciónspa
dcterms.audience.professionaldevelopmentPadres y familiasspa
dcterms.audience.professionaldevelopmentPersonal de apoyo escolarspa
dcterms.audience.professionaldevelopmentProveedores de ayuda financiera para estudiantesspa
dcterms.audience.professionaldevelopmentPúblico generalspa
dcterms.audience.professionaldevelopmentReceptores de fondos federales y solicitantesspa
dcterms.audience.professionaldevelopmentResponsables políticosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Miniatura
Nombre:
1030584108.2024.pdf
Tamaño:
19.65 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Ingeniería de Sistemas y Computación
Descargar

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Maestría en Ingeniería - Sistemas y Computación