Semantic and Structural Image Segmentation for Prosthetic Vision

Autores/as

  • Melani Sanchez Garcia Universidad de Zaragoza
  • Rubén Martínez Cantín Grupo de Robótica, Percepción y Tiempo Real (RoPERT)
  • José J. Guerrero Grupo de Robótica, Percepción y Tiempo Real (RoPERT)

DOI:

https://doi.org/10.26754/jji-i3a.003511

Resumen

We present a new approach to build a schematic representation of indoor environments for phosphene images. The proposed method combines a variety of convolutional neural networks for extracting and conveying relevant information about the scene such as structural informative edges of the environment and silhouettes of segmented objects. Experiments were conducted with normal sighted subjects with a Simulated Prosthetic Vision system.

Descargas

Publicado

2019-05-20