People counting using visible and infrared images

Mostrar todas las versiones(2)

"We propose the use of convolutional neural networks that consider as input four channels images (RGB+IR) for counting and positioning people in images. Our data set was made of images based on photographs taken from a drone using a dual FLIR camera. Comparison between 3 (RGB) and 4 (RGB+IR) ch...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Biagini, Martín, Filipic, Joaquín
Otros Autores: Parisi, Daniel
Formato: Proyecto final de Grado
Lenguaje:Inglés
Publicado: info
Materias:
REDES NEURONALES
PROCESAMIENTO DE IMAGENES
PEATONES
MULTITUDES
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3428
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3428
record_format dspace
spelling I32-R138-123456789-34282022-12-07T14:24:25Z People counting using visible and infrared images Biagini, Martín Filipic, Joaquín Parisi, Daniel REDES NEURONALES PROCESAMIENTO DE IMAGENES PEATONES MULTITUDES "We propose the use of convolutional neural networks that consider as input four channels images (RGB+IR) for counting and positioning people in images. Our data set was made of images based on photographs taken from a drone using a dual FLIR camera. Comparison between 3 (RGB) and 4 (RGB+IR) channels are studied for different lightning conditions. The four channel network performs better in all situations, particularly in cases of poor visible illumination that can be found in real night scenarios. The average precision of this network on a testing data set (independent from the training one) is approximately 1 cm in nding the positions of pedestrians (from 15 and 30 m altitude images) and 0.0001% in the relative counting error." Proyecto final Ingeniería Informática (grado) - Instituto Tecnológico de Buenos Aires, Buenos Aires, 2020 info:eu-repo/date/embargoEnd/2021-11-15 2021-04-07T14:57:14Z 2021-04-07T14:57:14Z 2020-10-19 Proyecto final de Grado http://ri.itba.edu.ar/handle/123456789/3428 en info:eu-repo/semantics/embargoedAccess application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Inglés
topic REDES NEURONALES
PROCESAMIENTO DE IMAGENES
PEATONES
MULTITUDES
spellingShingle REDES NEURONALES
PROCESAMIENTO DE IMAGENES
PEATONES
MULTITUDES
Biagini, Martín
Filipic, Joaquín
People counting using visible and infrared images
topic_facet REDES NEURONALES
PROCESAMIENTO DE IMAGENES
PEATONES
MULTITUDES
description "We propose the use of convolutional neural networks that consider as input four channels images (RGB+IR) for counting and positioning people in images. Our data set was made of images based on photographs taken from a drone using a dual FLIR camera. Comparison between 3 (RGB) and 4 (RGB+IR) channels are studied for different lightning conditions. The four channel network performs better in all situations, particularly in cases of poor visible illumination that can be found in real night scenarios. The average precision of this network on a testing data set (independent from the training one) is approximately 1 cm in nding the positions of pedestrians (from 15 and 30 m altitude images) and 0.0001% in the relative counting error."
author2 Parisi, Daniel
author_facet Parisi, Daniel
Biagini, Martín
Filipic, Joaquín
format Proyecto final de Grado
author Biagini, Martín
Filipic, Joaquín
author_sort Biagini, Martín
title People counting using visible and infrared images
title_short People counting using visible and infrared images
title_full People counting using visible and infrared images
title_fullStr People counting using visible and infrared images
title_full_unstemmed People counting using visible and infrared images
title_sort people counting using visible and infrared images
publishDate info
url http://ri.itba.edu.ar/handle/123456789/3428
work_keys_str_mv AT biaginimartin peoplecountingusingvisibleandinfraredimages
AT filipicjoaquin peoplecountingusingvisibleandinfraredimages
_version_ 1765661050058833920

Ejemplares similares