Stereo Matching through Squeeze Deep Neural Networks
Visual depth recognition through Stereo Matching is an active field of research due to the numerous applications in robotics, autonomous driving, user interfaces, etc. Multiple techniques have been developed in the last two decades to achieve accurate disparity maps in short time. With the arrival o...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | Objeto de conferencia |
Lenguaje: | Inglés |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/70713 http://47jaiio.sadio.org.ar/sites/default/files/ASAI-11.pdf |
Aporte de: |
id |
I19-R120-10915-70713 |
---|---|
record_format |
dspace |
institution |
Universidad Nacional de La Plata |
institution_str |
I-19 |
repository_str |
R-120 |
collection |
SEDICI (UNLP) |
language |
Inglés |
topic |
Ciencias Informáticas artificial intelligence stereo matching deep learning squeeze nets artificial vision disparity maps |
spellingShingle |
Ciencias Informáticas artificial intelligence stereo matching deep learning squeeze nets artificial vision disparity maps Caffaratti, Gabriel D. Marchetta, Martín G. Forradellas Martinez, Raymundo Quilez Stereo Matching through Squeeze Deep Neural Networks |
topic_facet |
Ciencias Informáticas artificial intelligence stereo matching deep learning squeeze nets artificial vision disparity maps |
description |
Visual depth recognition through Stereo Matching is an active field of research due to the numerous applications in robotics, autonomous driving, user interfaces, etc. Multiple techniques have been developed in the last two decades to achieve accurate disparity maps in short time. With the arrival of Deep Leaning architectures, different fields of Artificial Vision, but mainly on image recognition, have achieved a great progress due to their easier training capabilities and reduction of parameters. This type of networks brought the attention of the Stereo Matching researchers who successfully applied the same concept to generate disparity maps. Even though multiple approaches have been taken towards the minimization of the execution time and errors in the results, most of the time the number of parameters of the networks is neither taken into consideration nor optimized. Inspired on the Squeeze-Nets developed for image recognition, we developed a Stereo Matching Squeeze neural network architecture capable of providing disparity maps with a highly reduced network size without a significant impact on quality and execution time compared with state of the art architectures. |
format |
Objeto de conferencia Objeto de conferencia |
author |
Caffaratti, Gabriel D. Marchetta, Martín G. Forradellas Martinez, Raymundo Quilez |
author_facet |
Caffaratti, Gabriel D. Marchetta, Martín G. Forradellas Martinez, Raymundo Quilez |
author_sort |
Caffaratti, Gabriel D. |
title |
Stereo Matching through Squeeze Deep Neural Networks |
title_short |
Stereo Matching through Squeeze Deep Neural Networks |
title_full |
Stereo Matching through Squeeze Deep Neural Networks |
title_fullStr |
Stereo Matching through Squeeze Deep Neural Networks |
title_full_unstemmed |
Stereo Matching through Squeeze Deep Neural Networks |
title_sort |
stereo matching through squeeze deep neural networks |
publishDate |
2018 |
url |
http://sedici.unlp.edu.ar/handle/10915/70713 http://47jaiio.sadio.org.ar/sites/default/files/ASAI-11.pdf |
work_keys_str_mv |
AT caffarattigabrield stereomatchingthroughsqueezedeepneuralnetworks AT marchettamarting stereomatchingthroughsqueezedeepneuralnetworks AT forradellasmartinezraymundoquilez stereomatchingthroughsqueezedeepneuralnetworks |
bdutipo_str |
Repositorios |
_version_ |
1764820481707343872 |