Stop the Bus!: computer vision for automatic recognition of urban bus lines
In the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images...
Guardado en:
Autores principales: | , |
---|---|
Formato: | Objeto de conferencia |
Lenguaje: | Inglés |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/114923 http://49jaiio.sadio.org.ar/pdfs/asai/ASAI-10.pdf |
Aporte de: |
id |
I19-R120-10915-114923 |
---|---|
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 Computer vision Object detection Text recognition Text detection Buses Visual impairment |
spellingShingle |
Ciencias Informáticas Computer vision Object detection Text recognition Text detection Buses Visual impairment Maina, Hernán J. Sánchez, Jorge A. Stop the Bus!: computer vision for automatic recognition of urban bus lines |
topic_facet |
Ciencias Informáticas Computer vision Object detection Text recognition Text detection Buses Visual impairment |
description |
In the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images for the generation of a tool that potentially allows people with visual impairments to be assisted. To achieve this, a modular architecture based on object detectors and optical character recognition is presented and evaluated, mainly constituted by two stages:
one for the detection buses, based on the SSD-MobileNet object detection model; and another, responsible for line number recognition, where the EAST and OCR-Tesseract text detection and recognition models are tested, respectively. With a maximum probability of recognition of 62% in a simple image; over an image sequence, the nal system was able to correctly recognize the bus line in 72% of the cases tested. |
format |
Objeto de conferencia Objeto de conferencia |
author |
Maina, Hernán J. Sánchez, Jorge A. |
author_facet |
Maina, Hernán J. Sánchez, Jorge A. |
author_sort |
Maina, Hernán J. |
title |
Stop the Bus!: computer vision for automatic recognition of urban bus lines |
title_short |
Stop the Bus!: computer vision for automatic recognition of urban bus lines |
title_full |
Stop the Bus!: computer vision for automatic recognition of urban bus lines |
title_fullStr |
Stop the Bus!: computer vision for automatic recognition of urban bus lines |
title_full_unstemmed |
Stop the Bus!: computer vision for automatic recognition of urban bus lines |
title_sort |
stop the bus!: computer vision for automatic recognition of urban bus lines |
publishDate |
2020 |
url |
http://sedici.unlp.edu.ar/handle/10915/114923 http://49jaiio.sadio.org.ar/pdfs/asai/ASAI-10.pdf |
work_keys_str_mv |
AT mainahernanj stopthebuscomputervisionforautomaticrecognitionofurbanbuslines AT sanchezjorgea stopthebuscomputervisionforautomaticrecognitionofurbanbuslines |
bdutipo_str |
Repositorios |
_version_ |
1764820446117625860 |