Show simple item record

dc.contributor.advisorGarcia-Bedoya, Olmer
dc.coverage.spatialColombiaspa
dc.creatorCortes Capera, Miguel Angel
dc.date.accessioned2022-01-18T18:06:37Z
dc.date.available2022-01-18T18:06:37Z
dc.date.created2021
dc.identifier.urihttp://hdl.handle.net/20.500.12010/24559
dc.description.abstractSegún la organización mundial de la salud 1,3 millones de personas mueren en carreteras alrededor del mundo esto sin contar las personas que tienen traumatismos graves. Esto incentivo a enfocarnos en esta área trabajo por medio de la inteligencia artificial ya que permite desarrollar soluciones para estos problemas de manera efectiva. Por medio de aprendizaje profundo se logro generar una buena clasificación de algunas de las intenciones de los peatones permitiendo predecir los comportamientos.spa
dc.format.extent17 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.publisherUniversidad de Bogotá Jorge Tadeo Lozanospa
dc.sourceinstname:Universidad de Bogotá Jorge Tadeo Lozanospa
dc.sourcereponame:Expeditio Repositorio Institucional UJTLspa
dc.subjectInteligencia Artificialspa
dc.subjectDeep learningspa
dc.subjectRedes Neuronalesspa
dc.subjectLSTMspa
dc.subjectOpenCVspa
dc.subjectJAAD 2.0spa
dc.subjectTransferencia de conocimientospa
dc.subjectCRISP DMspa
dc.subjectYoloV4spa
dc.subjectKerasspa
dc.titleDeep learning models to detect pedestrian and intent estimation for autonomous vehiclesspa
dc.type.localTrabajo de grado de maestríaspa
dc.subject.lembInteligencia artificialspa
dc.subject.lembAprendizajespa
dc.subject.lembRedes neurales (Informática)spa
dc.subject.lembTransferencia de conocimientospa
dc.subject.lembPeatones--Enseñanzaspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersionspa
dc.rights.localAbierto (Texto Completo)spa
dc.subject.keywordArtificial Intelligencespa
dc.subject.keywordDeep Learningspa
dc.subject.keywordNeural Networksspa
dc.subject.keywordJAAD 2.0spa
dc.subject.keywordTransfer Learningspa
dc.subject.keywordAutonomous Vehiclesspa
dc.subject.keywordYoloV4spa
dc.subject.keywordKerasspa
dc.identifier.repourlhttp://expeditio.utadeo.edu.cospa
dc.creator.degreeMagíster en Ingeniería y Analítica de Datosspa
dc.publisher.programMaestría en Ingeniería y Analítica de Datosspa
dc.relation.references[1] Mart´ın Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. Tensorflow: A system for large-scale machine learning. In 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16), pages 265–283, 2016.spa
dc.relation.references[2] Sarfraz Ahmed, M Nazmul Huda, Sujan Rajbhandari, Chitta Saha, Mark Elshaw, and Stratis Kanarachos. Pedestrian and cyclist detection and intent estimation for autonomous vehicles: a survey. Applied Sciences, 9(11):2335, 2019.spa
dc.relation.references[3] Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.spa
dc.relation.references[4] Sebastian Bock and Martin Weiß. A proof of local convergence for the adam optimizer. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2019.spa
dc.relation.references[5] Ivan Nunes Da Silva, Danilo Hernane Spatti, Rogerio Andrade Flauzino, Luisa Helena Bartocci Liboni, and Silas Franco dos Reis Alves. Artificial neural network architectures and training processes. In Artificial neural networks, pages 21–28. Springer, 2017.spa
dc.relation.references[6] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.spa
dc.relation.references[7] O. Garcia and C. Diaz. Machine learning applied to autonomous vehicles. In Luis Rabelo, Sayli Bhide, and Edgar Gutierrez, editors, Artificial intelligence: Advances in research and applications, chapter 3, pages 49–74. Nova Science Publishers, Inc., Hauppauge, NY, 2018.spa
dc.relation.references[8] Olmer Garcia, Giovani Bernardes Vitor, Janito Vaqueiro Ferreira, Pablo Siqueira Meirelles, and Arthur de Miranda Neto. The vilma intelligent vehicle: an architectural design for cooperative control between driver and automated system. Journal of modern transportation, 26(3):220–229, 2018.spa
dc.relation.references[9] Antonio Gulli and Sujit Pal. Deep learning with Keras. Packt Publishing Ltd, 2017.spa
dc.relation.references[10] Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012.spa
dc.relation.references[11] Zhiheng Huang, Wei Xu, and Kai Yu. Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991, 2015.spa
dc.relation.references[12] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. nature, 521(7553):436–444, 2015.spa
dc.relation.references[13] Joe Minichino and Joseph Howse. Learning OpenCV 3 Computer Vision with Python. Packt Publishing Ltd, 2015.spa
dc.relation.references[14] A. Rasouli, I. Kotseruba, T. Kunic, and J. Tsotsos. Pie: A large-scale dataset and models for pedestrian intention estimation and trajectory prediction. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 6261–6270, 2019.spa
dc.relation.references[15] Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. Agreeing to cross: How drivers and pedestrians communicate. In IEEE Intelligent Vehicles Symposium (IV), pages 264–269, 2017.spa
dc.relation.references[16] Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. Are they going to cross? a benchmark dataset and baseline for pedestrian crosswalk behavior. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 206–213, 2017.spa
dc.relation.references[17] Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. Are they going to cross? a benchmark dataset and baseline for pedestrian crosswalk behavior. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 206–213, 2017.spa
dc.relation.references[18] Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. It’s not all about size: On the role of data properties in pedestrian detection. In ECCVW, 2018.spa
dc.relation.references[19] Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. Pedestrian action anticipation using contextual feature fusion in stacked rnns. arXiv preprint arXiv:2005.06582, 2020.spa
dc.relation.references[20] Khaled Saleh, Mohammed Hossny, and Saeid Nahavandi. Real-time intent prediction of pedestrians for autonomous ground vehicles via spatio-temporal densenet. In 2019 International Conference on Robotics and Automation (ICRA), pages 9704–9710. IEEE, 2019.spa
dc.relation.references[21] Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520, 2018.spa
dc.relation.references[22] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929– 1958, 2014spa
dc.relation.references[23] Jordi Torres. DEEP LEARNING Introduccion pr ´ actica con Keras ´ . Lulu.com, 2018.spa
dc.relation.references[24] Rudiger Wirth and Jochen Hipp. Crisp-dm: Towards a standard process model for data mining. In ¨ Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining, volume 1. Springer-Verlag London, UK, 2000.spa
dc.relation.references[25] Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. How transferable are features in deep neural networks? arXiv preprint arXiv:1411.1792, 2014.spa
dc.description.hashtag#DeepLearningModelsToDetectPedestrianAndIntentEstimationForAutonomousVehiclesspa
dc.description.abstractenglishAccording to the world health organization, 1.3 million people die on roads around the world, not counting people who have serious injuries. The article focus on computer vision and artificial intelligence to develop solutions for these problems effectively. Through deep learning, it was possible to generate a good classification of pedestrians' intentions, allowing us to predict behaviors.spa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record