Header

UZH-Logo

Maintenance Infos

Automated motif identification: Analysing Flickr images to identify popular viewpoints in Europe’s protected areas


Hartmann, Maximilian C; Koblet, Olga; Baer, Manuel F; Purves, Ross S (2022). Automated motif identification: Analysing Flickr images to identify popular viewpoints in Europe’s protected areas. Journal of Outdoor Recreation and Tourism, 37:100479.

Abstract

Visiting landscapes and appreciating them from specific viewpoints is not a new phenomenon. Such so-called motifs were popularised by travel guides and art in the romantic era, and find their contemporary digital twins through images captured in social media. We developed and implemented a conceptual model of motifs, based around spatial clustering, image similarity and the appreciation of a motif by multiple individuals. We identified 119 motifs across Europe, using 2146176 georeferenced Creative Commons Flickr images found in Natura 2000 protected areas. About 65% of motifs contain cultural elements such as castles or bridges. The remaining 35% are natural features, and biased towards coastal elements such as cliffs. Characterisation and localisation of motifs could allow identification of locations subject to increased pressure, and thus disturbance, especially since the visual characteristics of motifs allow managers to explore why sites are being visited. Future work will include methods of calculating image similarity using tags, explore different algorithms for assessing content similarity and study the behaviour of motifs through time.

Abstract

Visiting landscapes and appreciating them from specific viewpoints is not a new phenomenon. Such so-called motifs were popularised by travel guides and art in the romantic era, and find their contemporary digital twins through images captured in social media. We developed and implemented a conceptual model of motifs, based around spatial clustering, image similarity and the appreciation of a motif by multiple individuals. We identified 119 motifs across Europe, using 2146176 georeferenced Creative Commons Flickr images found in Natura 2000 protected areas. About 65% of motifs contain cultural elements such as castles or bridges. The remaining 35% are natural features, and biased towards coastal elements such as cliffs. Characterisation and localisation of motifs could allow identification of locations subject to increased pressure, and thus disturbance, especially since the visual characteristics of motifs allow managers to explore why sites are being visited. Future work will include methods of calculating image similarity using tags, explore different algorithms for assessing content similarity and study the behaviour of motifs through time.

Statistics

Citations

Dimensions.ai Metrics
6 citations in Web of Science®
6 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

60 downloads since deposited on 16 Feb 2022
24 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
06 Faculty of Arts > Zurich Center for Linguistics
Dewey Decimal Classification:910 Geography & travel
Scopus Subject Areas:Social Sciences & Humanities > Tourism, Leisure and Hospitality Management
Uncontrolled Keywords:Tourism, Leisure and Hospitality Management
Language:English
Date:1 March 2022
Deposited On:16 Feb 2022 15:16
Last Modified:27 Apr 2024 01:35
Publisher:Elsevier
ISSN:2213-0780
OA Status:Hybrid
Publisher DOI:https://doi.org/10.1016/j.jort.2021.100479
Project Information:
  • : FunderSwiss National Science Foundation
  • : Grant ID
  • : Project Title
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)