Mean Shift, Mode Seeking, and Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
World explorer: visualizing aggregate data from unstructured text in geo-referenced collections
Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries
Image and depth from a conventional camera with a coded aperture
ACM SIGGRAPH 2007 papers
Towards automatic extraction of event and place semantics from flickr tags
SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Automatic construction of travel itineraries using social breadcrumbs
Proceedings of the 21st ACM conference on Hypertext and hypermedia
Energy-efficient rate-adaptive GPS-based positioning for smartphones
Proceedings of the 8th international conference on Mobile systems, applications, and services
Identifying points of interest by self-tuning clustering
Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Proceedings of the 18th Brazilian symposium on Multimedia and the web
Identification of scene locations from geotagged images
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
| Hi-index | 0.00 |
The geographic coordinates automatically assigned to photos by the built-in GPS devices of cameras register the location a photo was taken at, rather than the location of the main point of interest within the depicted scene. While scientific advances have been made in the efforts to accurately locate the actual positions of such points of interest, these resort to either crude clustering-based approaches or expensive content-based approaches in order to estimate their geographic coordinates. In this paper we propose a novel technique that incorporates the compass direction supplied by modern cameras, allowing us to compute the most probable locations of the point of interest by analyzing intersections between the lines of sight originating from the cameras focusing on the same scene. Since the accuracy of the digital devices that supply the geographic coordinates and the compass direction can vary, we take these imprecisions into account when estimating the location.