Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Repositorio Digital UPCT
Publicación Artículo científico (JournalArticle)

End-to-End deep neural network architectures for speed and steering wheel angle prediction in autonomous driving

  • Navarro Lorente, Pedro Javier
  • Miller, Leanne Rebecca
  • Rosique Contreras, María Francisca
  • Fernández Isla, Carlos
  • Gila Navarro, Alberto
The complex decision-making systems used for autonomous vehicles or advanced driverassistance systems (ADAS) are being replaced by end-to-end (e2e) architectures based on deep-neuralnetworks (DNN). DNNs can learn complex driving actions from datasets containing thousands of images and data obtained from the vehicle perception system. This work presents the classification, design and implementation of six e2e architectures capable of generating the driving actions of speed and steering wheel angle directly on the vehicle control elements. The work details the design stages and optimization process of the convolutional networks to develop six e2e architectures. In the metric analysis the architectures have been tested with different data sources from the vehicle, such as images, XYZ accelerations and XYZ angular speeds. The best results were obtained with a mixed data e2e architecture that used front images from the vehicle and angular speeds to predict the speed and steering wheel angle with a mean error of 1.06%. An exhaustive optimization process of the convolutional blocks has demonstrated that it is possible to design lightweight e2e architectures with high performance more suitable for the final implementation in autonomous driving., This work was partially supported by DGT (ref.SPIP2017-02286) and GenoVision (ref.BFU2017-88300-C2-2-R) Spanish Government projects, and the “Research Programe for Groups of Scientific Excellence in the Region of Murcia” of the Seneca Foundation (Agency for Science and Technology in the Region of Murcia—19895/GERM/15).
Repositorio Digital UPCT
Publicación Artículo científico (JournalArticle)

Using artificial vision for measuring the range of motion

  • Rosique Contreras, María Francisca
  • Losilla López, Fernando
  • Navarro Lorente, Pedro Javier
Measurement of joint range of motion is a common measure in the functional evaluation of a patient. This clinical measurement is performed through the use of mechanical goniometry, currently presenting various problems mainly of a human nature. This article introduces ROMCam, an alternative system for measuring joint range of motion, based on estimating the human pose in 2D. For this, use is made of artificial vision libraries and the use of an RGB webcam type camera. The results obtained corroborate the validity of the use of ROMCam as a low cost, accessible tool that can even be used as a resource in telerehabilitation treatments., Este trabajo ha sido financiado por el proyecto MINECO/FEDER con identificador TEC2016-76465-C2-1-R (AIM) y por el “Research Program for Groups of Scientific Excellence in the Region of Murcia" de la Fundación Seneca (Agency for Science and Technology in the Region of Murcia – 19895/GERM/15), España.
Repositorio Digital UPCT
Publicación Artículo científico (JournalArticle)

Defect detection in textures through the use of entropy as a means for automatically selecting the wavelet decomposition level

  • Navarro Lorente, Pedro Javier
  • Fernández Isla, Carlos
  • Alcover Garau, Pedro María
  • Suardiaz Muro, Juan
This paper presents a robust method for defect detection in textures, entropy-based automatic selection of the wavelet decomposition level (EADL), based on a wavelet reconstruction scheme, for detecting defects in a wide variety of structural and statistical textures. Two main features are presented. One of the new features is an original use of the normalized absolute function value (NABS) calculated from the wavelet coefficients derived at various different decomposition levels in order to identify textures where the defect can be isolated by eliminating the texture pattern in the first decomposition level. The second is the use of Shannon’s entropy, calculated over detail subimages, for automatic selection of the band for image reconstruction, which, unlike other techniques, such as those based on the co-occurrence matrix or on energy calculation, provides a lower decomposition level, thus avoiding excessive degradation of the image, allowing a more accurate defect segmentation. A metric analysis of the results of the proposed method with nine different thresholding algorithms determined that selecting the appropriate thresholding method is important to achieve optimum performance in defect detection. As a consequence, several different thresholding algorithms depending on the type of texture are proposed., The work submitted here has been conducted within the framework of the ViSel-TR project (Selective Computer Vision Techniques for Non-structured Environments, Grant TIN2012-39279) funded by the Spanish government under the National Plan for R&D. This article is the result of the activity carried out under the “Research Programme for Groups of Scientific Excellence at Region of Murcia” of the Seneca Foundation (Agency for Science and Technology of the Region of Murcia—19895/GERM/15).