Pedestrian identification through Deep Learning with classical and modern architecture of Convolutional Neural Networks
Palabras clave:
recognition of people, convolutional neural network, deep learningResumen
This article, refers to the research carried out at the National University Micaela Bastidas (UNAMBA), whose specific objectives were: To determine in a first stage of learning the proportion of accuracy of a classical architecture of Convolutionary Neural Network (CNN) in the identification of UNAMBA peoples, to determine in a second stage the proportion of precision in a modern architecture of RNC and finally compare the first stage with the second, to find the highest proportion. The training was given with a quantity of 242 people. Therefore, 27,996 images had to be generated through the technique of Video Scraping and data augmentation, which were divided into 19,700 images for training and 8,296 for the validation. Regarding the results in the first stage, a modified model VGG16-UNAMBA is proposed, with which a ratio of 0.9721 accuracy was achieved; while in the second stage it is proposed to DenseNet121-UNAMBA, with which a proportion of 0.9943 accuracy was achieved. Coming to the conclusion that the use of deep learning allows UNAMBA staff to be identified in a high proportion of accuracy
Citas
F. Chollet, Deep learning with Python. Shelter Island, NY: Manning, 2018.
D. TutorialsPoint, «Tensor Flow, Simply Easy Learning», 2018. .
S. J. Russell y P. Norvig, Inteligencia artificial: un enfoque moderno. Pearson Educación, 2008.
P. Ponce, Inteligencia Artificial con aplicaciones a la ingeniería., Primera Edición. Ciudad de México: Alfaomega, 2010.
J. Hurwitz y D. Kirsch, Machine Learning For Dummies. John Wiley & Sons, 2018.
C. Andreas y G. Sarah, Introduction to Machine Learning with Python, Third Realese. United States of America: O’Reilly Media, 2017.
B. García, «Implementación de Técnicas de Deep Learning», Trabajo de Fin de Grado, Universidad de la Laguna, La Laguna, 2015.
N. Shukla, Machine Learning with TensorFlow. Manning Publications Co, 2017.
J. Hearty, Advanced Machine Learning with Python, Primera edición. Reino Unido: Packt Publishing Ltd, 2016.
P. Viola y M. J. Jones, «Robust Real-Time Face Detection», International Journal of Computer Vision, 2004.
M. Mathias, R. Benenson, M. Pedersoli, y L. V. Gool, «Face Detection without Bells and Whistles», Springer International Publishing Switzerland, pp. 720–735, 2014.
D. Chen, S. Ren, Y. Wei, X. Cao, y J. Sun, «Joint Cascade Face Detection and Alignment», Computer Vision – ECCV, pp. 109-122, 2014.
W. Liu, S. Liao, y I. Hasan, «Center and Scale Prediction: A Box-free Approach for Object Detection», arXiv.org, abr. 23, 2019.
A. Mateus, D. Ribeiro, P. Miraldo, y J. Nascimento, «Efficient and robust Pedestrian Detection using Deep Learning for Human-Aware Navigation», Robotics and Autonomous Systems, n.o 113, pp. 23-37, 2019.
T. Xiao, S. Li, B. Wang, L. Lin, y X. Wang, «Joint Detection and Identification Feature Learning for Person Search», arXiv.org, n.o arXiv:1604.01850v3 [cs.CV], abr. 06, 2017.
J. Rojas y R. Trujillo, «Algoritmo meta-heurístico Firefly aplicado al pre-entrenamiento de redes neuronales artificiales», Rev. Cuba. Cienc. Informáticas, vol. 12, n.o 1, pp. 14-27, mar. 2018, Accedido: oct. 13, 2018. [En línea].
R. Vizcaya, «Deep Learning para la Detección de Peatones y Vehículos», Maestro en Ciencias de la Computación, Universidad Autónoma del Estado de México, México, 2018.
K. Tsampikos, G. Triantafyllidis, y L. Nalpantidis, «Deep learning-based visual recognition of rumex for robotic precision farming», Computers and Electronics in Agriculture, vol. 165, pp. 85-90, 2019.
Z. Kastrati, A. S. Imran, y A. Kurti, «Integrating word embeddings and document topics with deep learning in a video classification framework», Pattern Recognition Letters, vol. 128, pp. 85-92, 2019.
L. Ye, L. Gao, R. Martinez, D. Mallants, y B. Bryan, «Projecting Australia’s forest cover dynamics and exploring influential factors using deep learning», Environmental Modelling & Software, vol. 119, pp. 407-417, 2019.
INEI, «Evolución de la pobreza monetaria 2007 -2018», Instituto Nacional de Estadística e Informática, Perú, Informe Técnico, abr. 2019. [En línea]. Disponible en: https://bit.ly/2TKzaiF.
K. Simonyan y A. Zisserman, «Very Deep Convolutional Networks for Large-Scale Image Recognition», ArXiv14091556 Cs, abr. 2015, Accedido: dic. 29, 2019. [En línea]. Disponible en: http://arxiv.org/abs/1409.1556.
G. Huang, Z. Liu, L. Maaten, y K. Q. Weinberger, «Densely Connected Convolutional Networks», ArXiv160806993 Cs, ene. 2018, Accedido: dic. 29, 2019. [En línea].
Descargas
Publicado
Versiones
- 2020-12-20 (3)
- 2021-08-23 (2)
- 2021-05-15 (1)
Cómo citar
Licencia
Derechos de autor 2020 https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.es
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Licencia de publicación
Atribución-NoComercial-SinDerivadas
CC BY-NC-ND
Esta licencia es la más restrictiva de nuestras seis licencias principales, permitiendo a otras sólo descargar sus obras y compartirlas con otras siempre y cuando den crédito, pero no pueden cambiarlas de forma alguna ni usarlas de forma comercial.