A study on Pedestrian detection using a deep convolutional neural network
Pedestrian detection is presently a topic of interest in computer vision due to its applications as an aid in car driving and in surveillance. The good results obtained using Convolutional Networks for vision tasks make them an attractive tool to improve the capabilities of pedestrian detection syst...
Guardado en:
Autor principal: | |
---|---|
Publicado: |
2016
|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS16454_v2016_n2_p_Orozco http://hdl.handle.net/20.500.12110/paper_NIS16454_v2016_n2_p_Orozco |
Aporte de: |
id |
paper:paper_NIS16454_v2016_n2_p_Orozco |
---|---|
record_format |
dspace |
spelling |
paper:paper_NIS16454_v2016_n2_p_Orozco2023-06-08T16:39:38Z A study on Pedestrian detection using a deep convolutional neural network Buemi, María Elena AdaBoost Convolutional neural network Deep learning Haar-like features Pedestrian detection Adaptive boosting Computer vision Convolution Face recognition Feature extraction Neural networks Object detection Pattern recognition systems Convolutional networks Convolutional neural network Deep learning Design parameters Haar-like features Pedestrian detection Pedestrian detection system Training and testing Pattern recognition Pedestrian detection is presently a topic of interest in computer vision due to its applications as an aid in car driving and in surveillance. The good results obtained using Convolutional Networks for vision tasks make them an attractive tool to improve the capabilities of pedestrian detection systems. In this work we study the use of a Convolutional Network as a refinement for classification of candidate regions previously detected using Haar features embedded in an AdaBoost scheme. The data used for training and testing come from the INRIA pedestrian database. The influence of design parameters, such as, the number of stages of the cascade in the detection stage and the scale factor in the pyramid of the multi-scale method, have been studied. Fil:Buemi, M.E. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2016 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS16454_v2016_n2_p_Orozco http://hdl.handle.net/20.500.12110/paper_NIS16454_v2016_n2_p_Orozco |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
AdaBoost Convolutional neural network Deep learning Haar-like features Pedestrian detection Adaptive boosting Computer vision Convolution Face recognition Feature extraction Neural networks Object detection Pattern recognition systems Convolutional networks Convolutional neural network Deep learning Design parameters Haar-like features Pedestrian detection Pedestrian detection system Training and testing Pattern recognition |
spellingShingle |
AdaBoost Convolutional neural network Deep learning Haar-like features Pedestrian detection Adaptive boosting Computer vision Convolution Face recognition Feature extraction Neural networks Object detection Pattern recognition systems Convolutional networks Convolutional neural network Deep learning Design parameters Haar-like features Pedestrian detection Pedestrian detection system Training and testing Pattern recognition Buemi, María Elena A study on Pedestrian detection using a deep convolutional neural network |
topic_facet |
AdaBoost Convolutional neural network Deep learning Haar-like features Pedestrian detection Adaptive boosting Computer vision Convolution Face recognition Feature extraction Neural networks Object detection Pattern recognition systems Convolutional networks Convolutional neural network Deep learning Design parameters Haar-like features Pedestrian detection Pedestrian detection system Training and testing Pattern recognition |
description |
Pedestrian detection is presently a topic of interest in computer vision due to its applications as an aid in car driving and in surveillance. The good results obtained using Convolutional Networks for vision tasks make them an attractive tool to improve the capabilities of pedestrian detection systems. In this work we study the use of a Convolutional Network as a refinement for classification of candidate regions previously detected using Haar features embedded in an AdaBoost scheme. The data used for training and testing come from the INRIA pedestrian database. The influence of design parameters, such as, the number of stages of the cascade in the detection stage and the scale factor in the pyramid of the multi-scale method, have been studied. |
author |
Buemi, María Elena |
author_facet |
Buemi, María Elena |
author_sort |
Buemi, María Elena |
title |
A study on Pedestrian detection using a deep convolutional neural network |
title_short |
A study on Pedestrian detection using a deep convolutional neural network |
title_full |
A study on Pedestrian detection using a deep convolutional neural network |
title_fullStr |
A study on Pedestrian detection using a deep convolutional neural network |
title_full_unstemmed |
A study on Pedestrian detection using a deep convolutional neural network |
title_sort |
study on pedestrian detection using a deep convolutional neural network |
publishDate |
2016 |
url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS16454_v2016_n2_p_Orozco http://hdl.handle.net/20.500.12110/paper_NIS16454_v2016_n2_p_Orozco |
work_keys_str_mv |
AT buemimariaelena astudyonpedestriandetectionusingadeepconvolutionalneuralnetwork AT buemimariaelena studyonpedestriandetectionusingadeepconvolutionalneuralnetwork |
_version_ |
1769175823743451136 |