Pasar al contenido principal

GENERACION PROCEDURAL DE ESCENARIOS AUMENTADOS CON ANOTACION DE DATOS AUTOMATICA

PID2020-115734RB-C22

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DA CORUÑA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Highway Remodeling: Harnessing Georeferenced Data for Procedural Modeling

  • Noriega, M. A.
  • Ribelles, José
  • Seoane, Antonio
  • Martínez, Margarita
  • Taibo, Javier
  • Iglesias-Guitian, Jose A.
Cursos e Congresos, C-155, [Abstract] : This paper introduces a novel procedural modeling system for generating 3D highway models, leveraging real-world data inputs such as highway layouts and manual annotations of essential elements. Our highly parameterized system facilitates easy customization, including modifications to the number of lanes and other key features, broadening its applicability across diverse domains, from urban planning and transportation engineering to virtual simulations, Generalitat Valenciana; CIBEST/2022/139, Xunta de Galicia; ED431F 2021/11, This work has been supported by the Spanish Ministry of Science and Innovation (AEI/PID2020-115734RB-C22). The whole team also wants to acknowledge the support provided by Side Effects Software Inc. in developing our work. Jose Ribelles was supported by Generalitat Valenciana (CIBEST/2022/139). Javier Taibo and J.A. Iglesias-Guitian were supported by Xunta de Galicia (ED431F 2021/11). Additionally, J.A. Iglesias-Guitian also acknowledges the UDC-Inditex InTalent programme and the Ministry of Science and Innovation (AEI/RYC2018-025385-I)
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Understanding the Influence of Rendering Parameters in Synthetic Datasets for Neural Semantic Segmentation Tasks

  • Silva, Manuel
  • Mures, Omar A.
  • Seoane, Antonio
  • Iglesias-Guitian, Jose A.
Cursos e Congresos , C-155, [Abstract] Deep neural networks are well known for demanding large amounts of training data, motivating the appearance of multiple synthetic datasets covering multiple domains. However, synthetic datasets have not yet outperformed real data for autonomous driving applications, particularly for semantic segmentation tasks. Thus, a deeper comprehension about how the parameters involved in synthetic data generation could help in creating better synthetic datasets. This work provides a summary review of prior research covering how image noise, camera noise and rendering photorealism could affect learning tasks. Furthermore, we presents novel experiments aimed at advancing our understanding around generating synthetic data for autonomous driving neural networks aimed at semantic segmentation, Xunta de Galicia; ED431F 2021/11, This work has been supported by the Spanish Ministry of Science and Innovation (AEI/PID2020-115734RB-C22). We also want to acknowledge Side Effects Software Inc. for their support to this work. J.A. Iglesias-Guitian also acknowledges the UDC-Inditex InTalent programme, the Ministry of Science and Innovation (AEI/RYC2018-025385-I) and Xunta de Galicia (ED431F 2021/11). CITIC is funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS)