JavaScript is disabled for your browser. Some features of this site may not work without it.

    Listar

    Todo RIUMAComunidades & ColeccionesPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentrosDepartamentos/InstitutosEditoresEsta colecciónPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentrosDepartamentos/InstitutosEditores

    Mi cuenta

    AccederRegistro

    Estadísticas

    Ver Estadísticas de uso

    DE INTERÉS

    Datos de investigaciónReglamento de ciencia abierta de la UMAPolítica de RIUMAPolitica de datos de investigación en RIUMAOpen Policy Finder (antes Sherpa-Romeo)Dulcinea
    Preguntas frecuentesManual de usoContacto/Sugerencias
    Ver ítem 
    •   RIUMA Principal
    • Investigación
    • Artículos
    • Ver ítem
    •   RIUMA Principal
    • Investigación
    • Artículos
    • Ver ítem

    Improved detection of small objects in road network sequences using CNN and super resolution

    • Autor
      García Aguilar, Iván; Luque-Baena, Rafael MarcosAutoridad Universidad de Málaga; López-Rubio, EzequielAutoridad Universidad de Málaga
    • Fecha
      2021
    • Palabras clave
      Redes neuronales (Informática)
    • Resumen
      The detection of small objects is one of the problems present in deep learning due to the context of the scene or the low number of pixels of the objects to be detected. According to these problems, current pre-trained models based on convolutional neural networks usually give a poor average precision, highlighting some as CenterNet HourGlass104 with a mean average precision of 25.6%, or SSD-512 with 9%. This work focuses on the detection of small objects. In particular, our proposal aims to vehicle detection from images captured by video surveillance cameras with pretrained models without modifying their structures, so it does not require retraining the network to improve the detection rate of the elements. For better performance, a technique has been developed which, starting from certain initial regions, detects a higher number of objects and improves their class inference without modifying or retraining the network. The neural network is integrated with processes that are in charge of increasing the resolution of the images to improve the object detection performance. This solution has been tested for a set of traffic images containing elements of different scales to check the efficiency depending on the detections obtained by the model. Our proposal achieves good results in a wide range of situations, obtaining, for example, an average score of 45.1% with the EfficientDet-D4 model for the first video sequence, compared to the 24.3% accuracy initially provided by the pre-trained model.
    • URI
      https://hdl.handle.net/10630/23529
    • DOI
      https://dx.doi.org/10.1111/exsy.12930
    • Compartir
      RefworksMendeley
    Mostrar el registro completo del ítem
    Ficheros
    17275420.pdf (7.385Mb)
    Colecciones
    • Artículos

    Estadísticas

    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
     

     

    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA