Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ RUC. Repositorio da ...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Desarrollo de módulos de visión por computador en Python para la detección de objetos en un entorno de pruebas de conducción autónoma

Desenvolvemento de módulos de visión por computador en Python para a detección de obxectos nun entorno de probas de condución autónoma
Authors: Cruz Irimia, Miguel;

Desarrollo de módulos de visión por computador en Python para la detección de objetos en un entorno de pruebas de conducción autónoma

Abstract

[Resumen] Este trabajo de fin de grado se enmarca en la línea de investigación de conducción autónoma que se lleva a cabo en el Grupo Integrado de Ingeniería (GII) de la UDC. En esta línea se utiliza el robot educativo Robobo para realizar estudios en aspectos de la conducción autónoma en un entorno de pruebas real y simulado. En este TFG se desarrollaron módulos de visión por computador en Python que resuelven problemas habituales en este entorno, como la detección de señales en tiempo real. Para ello, se identificaron las principales técnicas existentes, basadas en procesado de imagen tradicional y en redes de neuronas artificiales, para luego ser analizadas y comparadas en el entorno de pruebas con el objetivo de seleccionar la más eficiente y fiable. Para este trabajo experimental, se hizo uso de librerías específicas de visión y aprendizaje, como Keras y OpenCV, que fueron implementadas en el robot Robobo para su aplicación en el entorno real.

[Resumo] Este proxecto de fin de grao forma parte da liña de investigación de condución autónoma realizada no Grupo de Enxeñaría Integrada (GII) da UDC. Nesta liña, o robot educativo Robobo úsase para realizar estudos en aspectos da condución autónoma nu contorno de probas real e simulado. Neste TFG desenvolvéronse módulos de visión por computador en Python para resolver problemas comúns neste contorno, como a detección de sinais en tempo real. Para iso, identificáronse as principais técnicas existentes, baseadas no procesamento de imaxes tradicionais e redes de neuronas artificiais, e logo foron analizadas e comparadas no entorno de probas para seleccionar a máis eficiente e fiable. Para este traballo experimental, o alumno fixo uso de bibliotecas específicas de visión e aprendizaxe, como Keras e OpenCV, que foron probadas no robot Robobo para a súa aplicación nun contorno real.

[Abstract] This final degree project is part of the autonomous driving research line carried out in the Integrated Engineering Group (GII) of the UDC. In this line, the educational robot Robobo is used to carry out studies in different aspects of autonomous driving using a real and simulated environment. In this TFG, computer vision modules in Python were developed to solve common problems in this environment, such as detection real-time signal. For this, the main existing techniques were identified, based on traditional image processing or artificial neuron networks, which were analysed and compared in the test environment to select the most efficient and reliable ones. For this experimental work, the student made use of specific vision and learning libraries, such as Keras and OpenCV, which were tested on the Robobo robot for later application in the real environment.

Traballo fin de grao (UDC.EPS). Enxeñaría en tecnoloxías industriais. Curso 2020/2021

Related Organizations
Keywords

Robots móviles, Visión por ordenador

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green