Abstract
In this chapter, we explore the characteristics of geographically tagged Internet photos and determine their location based on the visual content. We develop a principled machine learning model to estimate geographical locations of photos by modeling the relationship between location and the photo content. To build reliable geographical estimators, it is important to find distinguishable geographical clusters in the world. These clusters cover general geographical regions not limited to just landmarks. Geographical clusters provide more training samples and hence lead to better recognition accuracy. We develop a framework for geographical cluster estimation, and employ latent variables to estimate the geographical clusters. To solve this estimation problem, we propose to build an efficient solver to find the latent clusters. We illustrate detailed qualitative results obtained from beaches photos taken at different continents. In addition, we show significantly improved quantitative results over other approaches for recognizing different beaches using the Flickr beach dataset as validation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hays J, Efros AA (2008) Im2gps: estimating geographic information from a single image. In: IEEE conference on computer vision and pattern recognition
Crandall D, Backstrom L, Huttenlocher D, Kleinberg J (2009) Mapping the world’s photos. In: International conference on world wide web, pp 761–770
Chen W, Battestini A, Gelfand N, Setlur V (2009) Visual summaries of popular landmarks from community photo collections. In: ACM international conference on Multimedia, pp 789–792
Yin Z, Cao L, Han J, Zhai C, Huang T (2011) Geographical topic discovery and comparison. In: Proceedings of the 20th international conference on world wide web. ACM, pp 247–256
Zheng Y, Zhao M, Song Y, Adam H, Buddemeier U, Bissacco A, Brucher F, Chua T, Neven H (2009) Tour the World: building a web-scale landmark recognition engine. In: IEEE conference on computer vision and pattern recognition
Cao L, Smith J, Wen Z, Yin Z, Jin X, Han J (2012) BlueFinder: estimate where a beach photo was taken. In: WWW
Wang Y, Cao L (2013) Discovering latent clusters from geotagged beach images. In: Advances in multimedia modeling. Springer, pp 133–142
Naaman M, Song Y, Paepcke A, Garcia-Molina H (2004) Automatic organization for digital photographs with geographic coordinates. In: International conference on digital libraries, vol 7. pp 53–62
Agarwal M, Konolige K (2006) Real-time localization in outdoor environments using stereo vision and inexpensive GPS. In: International conference on pattern recognition
Cao L, Yu J, Luo J, Huang T (2009) Enhancing semantic and geographic annotation of web images via logistic canonical correlation regression. In: Proceedings of the seventeen ACM international conference on multimedia, pp 125–134
Yu J, Luo J (2008) Leveraging probabilistic season and location context models for scene understanding. In: International conference on content-based image and video retrieval, pp 169–178
Joshi D, Luo J (2008) Inferring generic places based on visual content and bag of geotags. In: ACM conference on content-based image and video retrieval
Yuan J, Luo J, Wu Y (2008) Mining compositional features for boosting. In: IEEE conference on computer vision and pattern recognition
Kennedy L, Naaman M, Ahern S, Nair R, Rattenbury T (2007) How flickr helps us make sense of the world: context and content in community-contributed media collections. In: ACM conference on multimedia
Naaman M (2005) Leveraging geo-referenced digital photographs. PhD thesis, Stanford University
Quack T, Leibe B, Van Gool L (2008) World-scale mining of objects and events from community photo collections. In: ACM conference on image and video retrieval, pp 47–56
Luo J, Yu J, Joshi D, Hao W (2008) Event recognition: viewing the world with a third eye. In: ACM international conference on multimedia, pp 1071–1080
Schindler G, Krishnamurthy P, Lublinerman R, Liu Y, Dellaert F (2008) Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In: IEEE conference on computer vision and pattern recognition
Cao L, Luo J, Gallagher A, Jin X, Han J, Huang T (2010) A worldwide tourism recommendation system based on geotagged web photos. In: International conference on acoustics, speech, and signal processing (ICASSP)
Bush V (1945) As we may think. The Atlantic Monthly
Agarwal S, Snavely N, Simon I, Seitz SM, Szeliski R (2009) Building rome in a day. In: International conference on computer vision
Ji R, Xie X, Yao H, Ma WY (2009) Mining city landmarks from blogs by graph modeling. In: ACM Multimedia, pp 105–114
Gallagher A, Joshi D, Yu J, Luo J (2009) Geo-location inference from image content and user tags. In: Workshop on internet vision
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell 32:1672–1645
Xu L, Neufeldand J, Larson B, Schuurmans D (2005) Maximum margin clustering. In Saul LK, Weiss Y, Bottou L (eds) Advances in neural information processing systems, vol 17. MIT Press, Cambridge, MA, pp 1537–1544
Choi J, Lei H, Ekambaram V, Kelm P, Gottlieb L, Sikora T, Ramchandran K, Friedland G (2013) Human vs machine: establishing a human baseline for multimodal location estimation. In: Proceedings of the 21st ACM international conference on multimedia, MM ’13 pp 867–876
Xu L, Wilkinson D, Southey F, Schuurmans D (2006) Discriminative unsupervised learning of structured predictors. In: Proceedings of the 23th international conference on machine learning
Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Li, LJ., Jha, R.K., Thomee, B., Shamma, D.A., Cao, L., Wang, Y. (2016). Where the Photos Were Taken: Location Prediction by Learning from Flickr Photos. In: Zamir, A., Hakeem, A., Van Gool, L., Shah, M., Szeliski, R. (eds) Large-Scale Visual Geo-Localization. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-25781-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-25781-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25779-2
Online ISBN: 978-3-319-25781-5
eBook Packages: Computer ScienceComputer Science (R0)