People counting using visible and infrared images

Mostrar todas las versiones(2)

"We propose the use of convolutional neural networks (CNN) for counting and positioning people in visible and infrared images. Our data set is made of semi-artificial images created from real photographs taken from a drone using a dual FLIR camera. We compare the performance between CNN’s using...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Biagini, Martín, Filipic, Joaquín, Mas, Ignacio, Pose, Claudio D., Giribet, Juan I., Parisi, Daniel
Formato: Artículos de Publicaciones Periódicas acceptedVersion
Lenguaje:Inglés
Publicado: info
Materias:
REDES NEURONALES
PROCESAMIENTO DE IMAGENES
PEATONES
MULTITUDES
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3504
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3504
record_format dspace
spelling I32-R138-123456789-35042022-12-07T13:06:34Z People counting using visible and infrared images Biagini, Martín Filipic, Joaquín Mas, Ignacio Pose, Claudio D. Giribet, Juan I. Parisi, Daniel REDES NEURONALES PROCESAMIENTO DE IMAGENES PEATONES MULTITUDES "We propose the use of convolutional neural networks (CNN) for counting and positioning people in visible and infrared images. Our data set is made of semi-artificial images created from real photographs taken from a drone using a dual FLIR camera. We compare the performance between CNN’s using 3 (RGB) and 4 (RGB+IR) channels, both under different lighting conditions. The 4-channel network responds better in all situations, particularly in cases of poor visible illumination that can be found in night scenarios. The proposed methodology could be applied to real situations when an extensive databank of 4-channel images will be available." info:eu-repo/date/embargoEnd/2022-10-31 2021-05-31T13:35:58Z 2021-05-31T13:35:58Z 2020-10 Artículos de Publicaciones Periódicas info:eu-repo/semantics/acceptedVersion 0925-2312 http://ri.itba.edu.ar/handle/123456789/3504 en información: eu-repo/semantics/altIdentifier/doi/10.1016/j.neucom.2021.03.089 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
Mas, Ignacio
Pose, Claudio D.
Giribet, Juan I.
Parisi, Daniel
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 (CNN) for counting and positioning people in visible and infrared images. Our data set is made of semi-artificial images created from real photographs taken from a drone using a dual FLIR camera. We compare the performance between CNN’s using 3 (RGB) and 4 (RGB+IR) channels, both under different lighting conditions. The 4-channel network responds better in all situations, particularly in cases of poor visible illumination that can be found in night scenarios. The proposed methodology could be applied to real situations when an extensive databank of 4-channel images will be available."
format Artículos de Publicaciones Periódicas
acceptedVersion
author Biagini, Martín
Filipic, Joaquín
Mas, Ignacio
Pose, Claudio D.
Giribet, Juan I.
Parisi, Daniel
author_facet Biagini, Martín
Filipic, Joaquín
Mas, Ignacio
Pose, Claudio D.
Giribet, Juan I.
Parisi, Daniel
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/123456789/3504
work_keys_str_mv AT biaginimartin peoplecountingusingvisibleandinfraredimages
AT filipicjoaquin peoplecountingusingvisibleandinfraredimages
AT masignacio peoplecountingusingvisibleandinfraredimages
AT poseclaudiod peoplecountingusingvisibleandinfraredimages
AT giribetjuani peoplecountingusingvisibleandinfraredimages
AT parisidaniel peoplecountingusingvisibleandinfraredimages
_version_ 1765660992767787008

Ejemplares similares