Access count of this item: 82

Files in This Item:
File Description SizeFormat 
IJBDI.2017.10006525.pdf5.8 MBAdobe PDFView/Open
Title: Sightseeing Value Estimation by Analyzing Geosocial Images
Authors: Shen, Yizhu
Ge, Min
Zhuang, Chenyi
Ma, Qiang  kyouindb  KAKEN_id
Author's alias: 馬, 強
Keywords: points of interests
sightseeing value
geosocial image
human perception
image processing
UCG mining
Issue Date: Jan-2018
Publisher: Inderscience
Journal title: International Journal of Big Data Intelligence
Volume: 5
Issue: 1/2
Start page: 31
End page: 48
Abstract: Recommendation of points of interests (POIs) is drawing more attention to meet the growing demands of tourists. Thus, a POI's quality (sightseeing value) needs to be estimated. In contrast to conventional studies that rank POIs on the basis of user behaviour analysis, this paper presents methods to estimate quality by analysing geo-social images. Our approach estimates the sightseeing value from two aspects: 1) nature value; 2) culture value. For the nature value, we extract image features that are related to favourable human perception to verify whether a POI would satisfy tourists in terms of environmental psychology. Three criteria are defined accordingly: coherence, image-ability, and visual-scale. For the culture value, we recognise the main cultural element (i.e., architecture) included in a POI. In the experiments, we applied our methods to real POIs and found that our approach assessed sightseeing value effectively.
Rights: This is the accepted version of the article, which has been published in final form at https://doi.org/10.1504/IJBDI.2017.10006525.
The full-text file will be made open to the public on 01 June 2018 in accordance with publisher's 'Terms and Conditions for Self-Archiving'.
This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。
URI: http://hdl.handle.net/2433/228929
DOI(Published Version): 10.1504/IJBDI.2017.10006525
Appears in Collections:Journal Articles

Show full item record

Export to RefWorks


Export Format: 


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.