Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations
In computer vision, Wide Baseline Stereo (WxBS) refers to Vision System configurations on which their images come from cameras with non parallel and widely separated views. One common task in reconstruction algorithms of WxBS consists of subvididing the stereo images in multiple image patches and t...
| Autores principales: | , , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/151619 https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/259/211 |
| Aporte de: |
| id |
I19-R120-10915-151619 |
|---|---|
| record_format |
dspace |
| spelling |
I19-R120-10915-1516192023-05-03T20:02:12Z http://sedici.unlp.edu.ar/handle/10915/151619 https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/259/211 issn:2451-7496 Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations Durante, Diego Patricio Verrastro, Ramiro Gómez, Juan Carlos Verrastro, Claudio Abel 2022-10 2022 2023-04-18T14:27:35Z en Ciencias Informáticas Computer Vision Machine Learning Wide Baseline Stereo Labeling Tool Siamese Convolutional Neural Networks In computer vision, Wide Baseline Stereo (WxBS) refers to Vision System configurations on which their images come from cameras with non parallel and widely separated views. One common task in reconstruction algorithms of WxBS consists of subvididing the stereo images in multiple image patches and then associate homologous patches between homologous images. Multiple approaches can be used to associate homologous patches. To train and test supervised learning algorithms for this tasks, a labeled dataset is required. In this work, a semi-automated method to generate patches and their labels from WxBS images is presented. It allows to calculate thousands of positive and negative pairs of patches with a score of correspondence between a pair of potentially homologous image patches. This method largely solves the problems of traditional approach, which requires a lot of hand labeled work and time. To apply the method, images from different viewpoints of objects with planar faces and their corner locations are required. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 22-35 |
| institution |
Universidad Nacional de La Plata |
| institution_str |
I-19 |
| repository_str |
R-120 |
| collection |
SEDICI (UNLP) |
| language |
Inglés |
| topic |
Ciencias Informáticas Computer Vision Machine Learning Wide Baseline Stereo Labeling Tool Siamese Convolutional Neural Networks |
| spellingShingle |
Ciencias Informáticas Computer Vision Machine Learning Wide Baseline Stereo Labeling Tool Siamese Convolutional Neural Networks Durante, Diego Patricio Verrastro, Ramiro Gómez, Juan Carlos Verrastro, Claudio Abel Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| topic_facet |
Ciencias Informáticas Computer Vision Machine Learning Wide Baseline Stereo Labeling Tool Siamese Convolutional Neural Networks |
| description |
In computer vision, Wide Baseline Stereo (WxBS) refers to Vision System configurations on which their images come from cameras with non parallel and widely separated views.
One common task in reconstruction algorithms of WxBS consists of subvididing the stereo images in multiple image patches and then associate homologous patches between homologous images. Multiple approaches can be used to associate homologous patches. To train and test supervised learning algorithms for this tasks, a labeled dataset is required.
In this work, a semi-automated method to generate patches and their labels from WxBS images is presented. It allows to calculate thousands of positive and negative pairs of patches with a score of correspondence between a pair of potentially homologous image patches. This method largely solves the problems of traditional approach, which requires a lot of hand labeled work and time. To apply the method, images from different viewpoints of objects with planar faces and their corner locations are required. |
| format |
Objeto de conferencia Objeto de conferencia |
| author |
Durante, Diego Patricio Verrastro, Ramiro Gómez, Juan Carlos Verrastro, Claudio Abel |
| author_facet |
Durante, Diego Patricio Verrastro, Ramiro Gómez, Juan Carlos Verrastro, Claudio Abel |
| author_sort |
Durante, Diego Patricio |
| title |
Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| title_short |
Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| title_full |
Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| title_fullStr |
Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| title_full_unstemmed |
Semi-Automated Stereo Image Patches Generation and Labeling Method Based on Perspective Transformations |
| title_sort |
semi-automated stereo image patches generation and labeling method based on perspective transformations |
| publishDate |
2022 |
| url |
http://sedici.unlp.edu.ar/handle/10915/151619 https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/259/211 |
| work_keys_str_mv |
AT durantediegopatricio semiautomatedstereoimagepatchesgenerationandlabelingmethodbasedonperspectivetransformations AT verrastroramiro semiautomatedstereoimagepatchesgenerationandlabelingmethodbasedonperspectivetransformations AT gomezjuancarlos semiautomatedstereoimagepatchesgenerationandlabelingmethodbasedonperspectivetransformations AT verrastroclaudioabel semiautomatedstereoimagepatchesgenerationandlabelingmethodbasedonperspectivetransformations |
| _version_ |
1765659991161700352 |