International Journal of Human-Computer Studies
Mining flickr landmarks by modeling reconstruction sparsity
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) - Special section on ACM multimedia 2010 best paper candidates, and issue on social media
Hi-index | 0.00 |
Navigation is playing an increasingly important role in virtual environments (VE). Today virtual worlds are very large and present challenging navigation tasks. Usually a VE contains few visual details and hence few landmarks to support navigation. In this paper we propose a technique to automatic identify landmarks in large virtual environment using spatial data mining techniques. Identified landmarks are used to enrich landmark knowledge which is essential for navigation in VE. Initially three datasets with different number of objects have been generated based on a realistic distribution of buildings on one of newest and well designed Egyptian cities. A new model for extracting landmarks in VE was developed based on the models used in real environment. The proposed technique was applied on the generated cities and successfully identified the landmarks.