DeepDBSCAN: Deep Density-Based Clustering for Geo-Tagged Photos

Abstract

Density-based clustering algorithms have been the most commonly used algorithms for discovering regions and points of interest in cities using global positioning system (GPS) information in geo-tagged photos. However, users sometimes find more specific areas of interest using real objects captured in pictures. Recent advances in deep learning technology make it possible to recognize these objects in photos. However, since deep learning detection is a very time-consuming task, simply combining deep learning detection with density-based clustering is very costly. In this paper, we propose a novel algorithm supporting deep content and density-based clustering, called deep density-based spatial clustering of applications with noise (DeepDBSCAN). DeepDBSCAN incorporates object detection by deep learning into the density clustering algorithm using the nearest neighbor graph technique. Additionally, this supports a graph-based reduction algorithm that reduces the number of deep detections. We performed experiments with pictures shared by users on Flickr and compared the performance of multiple algorithms to demonstrate the excellence of the proposed algorithm.

Discovering Homogeneous Groups from Geo-Tagged Videos

“…A density-based algorithm contains two parameters (eps and minPts) to identify dense regions based on density reachability [31,32]. Density clustering algorithms are suitable for clusters of arbitrary shapes in geo-tagged photos and videos with FoVs [4,[33][34][35]. In order to better avoid the lossy problem, the FoVs clustering method in our paper is based on DBSCAN.…”