Seite - 356 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

Figure 4. Areas divided based on Wi-Fi RSSI values 6. Conclusion In this paper, we have proposed reorganization of the database by clustering the registered images based on the rough location estimated by Wi-Fi signals. There is still a discussion about the appropriate granularity of spatial clusters. This remains for our future work. References [1] C. Chen, Y. Chen, Y. Han, H. Lai, and K. J. R. Liu: Achieving Centimeter-Accuracy Indoor Localization on WiFi Platforms: A Frequency Hopping Approach, IEEE Internet of Things Journal, vol.4, issue 1, pp.111–121, 2017. J. Engel, T. Schöps and D. Cremers: LSD-SLAM: Large- Scale Direct Monocular SLAM, European Conference on Computer Vision (ECCV), 2014. F. Endres, J. Hess, J. Sturm, D. Cremers and W. Burgard: 3D Mapping with an RGB-D Camera, IEEE Transactions on Robotics (T-RO), vol. 30, no.1, pages. 177-187, 2013. [4] Yuki Tokunaga, Parallel Computing with GPU for Speeding up of Localization Algorithm based on line- segment matching, IPSJ SIG-MBL, 2017. [5] G. Grisetti, R. K ˘mmerle, C. Stachniss and W. Burgard:A Tutorial on Graph-Based SLAM, Vol. 2, No. 4, pp. 31–43 2010. S. Thrun, W. Burgard, and D. Fox: Probabilistic robotics, MIT press, 2005. S. Pandey and P. Khanna: A hierachical clustering approach for image datasets, 9th International Conference on Industrial and Information Systems (ICIIS), 2014. W.Takahashi etal. /UsingWi-FiSignals forCreatingaClustered ImageDatabase inUMap356