Deep learning techniques, especially convolutional neural networks, have shown good image processing capabilities in recent years. In this work we apply two convolutional models to automatically detect road damages from video frames. The former tries to solve the problem with a semantic segmentation approach while the latter uses an object detection approach. Our results show that the second model could be a valid decision support system to ease the work of human experts.

A deep learning approach for road damage classification

CIAPARRONE, GIOELE
;
Serra, Angela;Tagliaferri, Roberto
2019-01-01

Abstract

Deep learning techniques, especially convolutional neural networks, have shown good image processing capabilities in recent years. In this work we apply two convolutional models to automatically detect road damages from video frames. The former tries to solve the problem with a semantic segmentation approach while the latter uses an object detection approach. Our results show that the second model could be a valid decision support system to ease the work of human experts.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11386/4719573
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
social impact