A Proposal for Discovering Hotspots Using 3D Coordinates from Geo-tagged Photographs

摘要

A hotspot is an interesting place where many people go for sightseeing. To extract hotspots, most of the existing research applies a density-based clustering algorithm, such as Density-based spatial clustering of applications with noise (DBSCAN) with latitude and longitude as its features. Therefore, the extracted hotspots are visualized as a two-dimensional space. However, large areas, landmarks, and buildings may include high hotspots or multiple hotspots with different altitudes. Therefore, in this research, we propose extracting hotspots based on altitude in addition to latitude and longitude and visualize these extracted hotspots in a three-dimensional space. To use those features, we apply ST-DBSCAN to extract hotspots and discuss the usefulness of extracting hotspots using altitude. In addition, as an application example, we classified hotspots as shooting spots, observation spots, areas of interest, among others and visualized the results.