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/ UPCommons. Portal de...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 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/
versions View all 3 versions
addClaim

Entrenament d'un model deep learning de detecció de l'orientació dels caps de persones amb una base de dades sintètica

Authors: Bo Clotet, Marc;

Entrenament d'un model deep learning de detecció de l'orientació dels caps de persones amb una base de dades sintètica

Abstract

Hoy en día, la inteligencia artificial ha encontrado aplicaciones en un gran número de campos. Este trabajo se focaliza en uno de estos, la visión por computador. La visión por computador es el campo de la ciencia que se encarga de hacer que los ordenadores puedan entender imágenes o vídeos digitales utilizando inteligencia artificial. El objetivo de este proyecto es enforntar con uno de los grandes problemas de este campo: La falta de datos etiquetadas. En concreto, se ha generado una base de datos sintética con Unity3D para obtener imágenes etiquetadas con las que se ha entrenado una red neuronal. Ésta, se encarga de estimar la postura de la cabeza de personas en una sala a través de una cámara zential

La intel·ligència artificial ha trobat, avui en dia, aplicacions en un gran nombre de camps. Aquest treball es focalitza en un d'aquests, la visió per computador. La visió per computador és el camp de la ciència que s'encarrega de fer que els ordinadors puguin entendre imatges o vídeos digitals fent servir intel·ligència artificial. L'objectiu d'aquest projecte és enforntar-se amb un dels grans problemes d'aquest camp: La falta de dades etiquetades. En concret, s'ha generat una base de dades sintètica amb Unity3D per obtindre imatges etiquetades amb les quals s'ha entrenat una xarxa neuronal. Aquesta, s'encarrega d'estimar la postura del cap de persones en una sala a través d'una càmera zential.

Artificial intelligence has found applications in a large number of fields. This work focuses on one of these, computer vision. Computer vision is the field of science that is responsible for making computers able to understand digital images or videos using artificial intelligence. The aim of this project is to address one of the major problems in this field: The lack of labeled data. Specifically, a synthetic database has been generated with Unity3D to obtain tagged images with which a neural network has been trained. This one, is in charge to estimate the position of the head of people in a room through a zential camera.

La determinació de la orientació del cap de les persones és molt important en diferents aplicacions (seguretat al treball, marketing, etc.). En aques projecte es desenvoluparan mètodes per crear una base de dades si tètica per entrenar algorísmes de visió per computador amb Deep Learning.

Country
Spain
Keywords

Imatges digitals, dataset sintètico, Visió per ordinador, Unity3D, Computer simulation, :Enginyeria de la telecomunicació [Àrees temàtiques de la UPC], Neural networks (Computer science), Bases de dades, Databases, Deep Learning, Simulació per ordinador, Xarxes neuronals (Informàtica), Computer vision, synthetic datasets, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació, Digital images

  • 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
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 18
    download downloads 22
  • 18
    views
    22
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
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!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
18
22
Green