Building and tracking hierarchical geographical & temporal partitions for image collection management on mobile devices

ABSTRACT

Usage of mobile devices (phones, digital cameras) raises the need for organizing large personal image collections. In accordance with studies on user needs, we propose a statistical criterion and an associated optimization technique, relying on geo-temporal image metadata, for building and tracking a hierarchical structure on the image collection. In a mixture model framework, particularities of the application and typical data sets are taken into account in the design of the scheme (incrementality, ability to cope with non-Gaussian data, with both small and large samples). Results are reported on real data sets.

REFERENCES

• 1: Aris, A., Gemmel, J., and Lueder, R. Exploiting location and time for photo search and storytelling in MyLifeBits. Tech. Rep. MSR-TR-2004-102, Microsoft research, Sept. 2004.
• 2: D. Ashbrook, Learning Significant Locations and Predicting User Movement with GPS, Proceedings of the 6th IEEE International Symposium on Wearable Computers, p.101, October 07-10, 2002
• 3: Christophe Biernacki , Gilles Celeux , Gérard Govaert, Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.7, p.719-725, July 2000 [doi>10.1109/34.865189]
• 4: Bishop, C., and Svensen, M. Robust Bayesian mixture modelling. In Proceedings Twelfth European Symposium on Artificial Neural Networks (Bruges, Belgium, Apr. 2004), pp. 69--74.
• 5: Matthew Cooper , Jonathan Foote , Andreas Girgensohn , Lynn Wilcox, Temporal event clustering for digital photo collections, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957093]
• 6: Marc Davis, Mobile media metadata: metadata creation system for mobile images, Proceedings of the 12th annual ACM international conference on Multimedia, October 10-16, 2004, New York, NY, USA [doi>10.1145/1027527.1027741]
• 7: Chris Fraley, Algorithms for Model-Based Gaussian Hierarchical Clustering, SIAM Journal on Scientific Computing, v.20 n.1, p.270-281, Aug. 1998 [doi>10.1137/S1064827596311451]
• 8: Gargi, U., Deng, Y., and Tretter, D. R. Managing and searching personal photo collections. Tech. Rep. HPL-2002-67, HP Laboratories, Palo Alto, Mar. 2002.
• 9: Gelgon, M., and Tilhou., K. Structuring the personal multimedia collection of a mobile device user based on geolocation. In IEEE Int. conf. on Multimedia and Expo (ICME'2002) (Lausanne, Switzerland, Aug. 2002), pp. 248--252.
• 10: Jim Gemmell , Roger Lueder , Gordon Bell, The MyLifeBits lifetime store, Proceedings of the 2003 ACM SIGMM workshop on Experiential telepresence, November 07, 2003, Berkeley, California [doi>10.1145/982484.982500]
• 11: Adrian Graham , Hector Garcia-Molina , Andreas Paepcke , Terry Winograd, Time as essence for photo browsing through personal digital libraries, Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries, July 14-18, 2002, Portland, Oregon, USA [doi>10.1145/544220.544301]
• 12: Loui, A., and Savakis, A. E. Automatic image event segmentation and quality screening for albuming applications. In IEEE Proceedings Int. Conf. on Multimedia and Expo (ICME'2000) (New York, USA, Aug. 2000), pp. 1125--1128.
• 13: Luo, J., Savakis, A., and Singhal, A. A Bayesian network-based framework for semantic image understanding. Pattern Recognition 38, 6 (June 2005), 919--934.
• 14: Myka, A. Nokia lifeblog - towards a truly personal multimedia information system. In Proc. of Workshop des GI-Arbeitkreises "Mobile Datenbanken and Informationsysteme(Karlsruhe, Germany, Feb. 2005).
• 15: Mor Naaman , Yee Jiun Song , Andreas Paepcke , Hector Garcia-Molina, Automatic organization for digital photographs with geographic coordinates, Proceedings of the 4th ACM/IEEE-CS joint conference on Digital libraries, June 07-11, 2004, Tuscon, AZ, USA [doi>10.1145/996350.996366]
• 16: Pigeau, A., and Gelgon, M. Organizing a personal image collection with statistical model-based ICL clustering on spatio-temporal camera phone meta-data Journal of Visual Communication and Image Representation 15 3(2004), pp.-425--445.
• 17: A. Pigeau , M. Gelgon, Incremental Statistical Geo-Temporal Structuring of a Personal Camera Phone Image Collection, Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3, p.878-881, August 23-26, 2004 [doi>10.1109/ICPR.2004.493]
• 18: Platt, J. C., and M. Czerwinski, B. A. F. PhotoTOC: Automatic clustering for browsing personal photographs. Tech. Rep. MSR-TR-2002-17, Microsoft Research, Feb. 2002.
• 19: Kerry Rodden , Kenneth R. Wood, How do people manage their digital photographs?, Proceedings of the SIGCHI conference on Human factors in computing systems, April 05-10, 2003, Ft. Lauderdale, Florida, USA [doi>10.1145/642611.642682]
• 20: Kentaro Toyama , Ron Logan , Asta Roseway, Geographic location tags on digital images, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957046]
• 21: Ueda, N., Nakano, R., Gharhamani, Z., and Hinton, G. SMEM algorithm for mixture models. Neural computation 12, 9 (2000), 2109--2128.
• 22: Vermaak, J. Perez, P., and Gangnet, M. Rapid summarization and browsing of video sequences. In Proc. of British Machine Vision Conference (BVMC'2002) (Cardiff, U.K., Sept. 2002), pp. 145--151.
• 23: Anita Wilhelm , Yuri Takhteyev , Risto Sarvas , Nancy Van House , Marc Davis, Photo annotation on a camera phone, CHI '04 extended abstracts on Human factors in computing systems, April 24-29, 2004, Vienna, Austria [doi>10.1145/985921.986075]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

General Terms:
Algorithms

Keywords:
clustering, consumer, database, multimedia