Landslide Detection in Real-Time Social Media Image Streams

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ofli, Ferda, Imran, Muhammad, Qazi, Umair, Roch, Julien, Pennington, Catherine, Banks, Vanessa J., Bossu, Remy
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909179219804160
author Ofli, Ferda
Imran, Muhammad
Qazi, Umair
Roch, Julien
Pennington, Catherine
Banks, Vanessa J.
Bossu, Remy
author_facet Ofli, Ferda
Imran, Muhammad
Qazi, Umair
Roch, Julien
Pennington, Catherine
Banks, Vanessa J.
Bossu, Remy
contents Lack of global data inventories obstructs scientific modeling of and response to landslide hazards which are oftentimes deadly and costly. To remedy this limitation, new approaches suggest solutions based on citizen science that requires active participation. However, as a non-traditional data source, social media has been increasingly used in many disaster response and management studies in recent years. Inspired by this trend, we propose to capitalize on social media data to mine landslide-related information automatically with the help of artificial intelligence (AI) techniques. Specifically, we develop a state-of-the-art computer vision model to detect landslides in social media image streams in real time. To that end, we create a large landslide image dataset labeled by experts and conduct extensive model training experiments. The experimental results indicate that the proposed model can be deployed in an online fashion to support global landslide susceptibility maps and emergency response.
format Preprint
id arxiv_https___arxiv_org_abs_2110_04080
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Landslide Detection in Real-Time Social Media Image Streams
Ofli, Ferda
Imran, Muhammad
Qazi, Umair
Roch, Julien
Pennington, Catherine
Banks, Vanessa J.
Bossu, Remy
Computer Vision and Pattern Recognition
Lack of global data inventories obstructs scientific modeling of and response to landslide hazards which are oftentimes deadly and costly. To remedy this limitation, new approaches suggest solutions based on citizen science that requires active participation. However, as a non-traditional data source, social media has been increasingly used in many disaster response and management studies in recent years. Inspired by this trend, we propose to capitalize on social media data to mine landslide-related information automatically with the help of artificial intelligence (AI) techniques. Specifically, we develop a state-of-the-art computer vision model to detect landslides in social media image streams in real time. To that end, we create a large landslide image dataset labeled by experts and conduct extensive model training experiments. The experimental results indicate that the proposed model can be deployed in an online fashion to support global landslide susceptibility maps and emergency response.
title Landslide Detection in Real-Time Social Media Image Streams
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2110.04080