Detecting tourist attractions using geo-tagged photo clustering

Abstract

Millions of geo-tagged photos are becoming available due to the wide spread of photo-sharing websites, which provide valuable information to mine spatial patterns from human activities. In this study, we present a simple and fast density-based spatial clustering algorithm to detect popular scenic spots using geo-tagged photos collected from Flickr. In this algorithm, Gaussian kernel is applied to estimate local density of data points, and a decision graph is used to obtain cluster centers easily. More than 289,000 geo-tagged photos located in five typical cities of China are downloaded as case studies, and data pre-processing such as duplicate removing is performed to improve the quality of clustering result. Finally, popular tourist attractions of each sample city are successfully detected with this algorithm, and our result is useful for recommending some interesting destinations which might not be on the list of tourist website or mobile guide applications. The proposed solution is robust with respect to different distributions of photos, and it is efficient by comparing with other popular clustering approaches.