The presence of volcanic ashes, especially in urban areas, have possible repercussions on both citizens health and everyday life activities, such as industrial plants, civil infrastructure, air and road traffic. It is then strategic the availability of a dense network of monitoring stations allowing an effective estimation of ash particles characteristics such as size and shapes, which could enable the use of models forecasting ashes dispersions. In this paper an approach for the classification of volcanic ash particles, on the basis of their shapes, is presented. The methodology proposed exploits a vision-based approach, a dedicated image processing and a rule-based classification algorithm. An experimental survey has been performed to assess features of the classification system, which highlighted suitable performance, showing an accuracy and specificity indexes greater or equal to 0.86 and 0.97, respectively.

A Vision-Based Methodology for the Recognition and Classification of Volcanic Ash Shapes

Ando, Bruno;Baglio, Salvatore;Castorina, Salvatore;Graziani, Salvatore
2024-01-01

Abstract

The presence of volcanic ashes, especially in urban areas, have possible repercussions on both citizens health and everyday life activities, such as industrial plants, civil infrastructure, air and road traffic. It is then strategic the availability of a dense network of monitoring stations allowing an effective estimation of ash particles characteristics such as size and shapes, which could enable the use of models forecasting ashes dispersions. In this paper an approach for the classification of volcanic ash particles, on the basis of their shapes, is presented. The methodology proposed exploits a vision-based approach, a dedicated image processing and a rule-based classification algorithm. An experimental survey has been performed to assess features of the classification system, which highlighted suitable performance, showing an accuracy and specificity indexes greater or equal to 0.86 and 0.97, respectively.
2024
classification algorithms
experimental survey
shape
vision system
Volcanic ashes
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/20.500.11769/671249
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact