City-Scale Location Recognition Export

@inproceedings{Schindler:2007:CityScale, abstract = {We look at the problem of location recognition in a large image dataset using a vocabulary tree. This entails finding the location of a query image in a large dataset containing 3 \~{A}ƒ\^{a}€” 104 streetside images of a city. We investigate how the traditional invariant feature matching approach falls down as the size of the database grows. In particular we show that by carefully selecting the vocabulary using the most informative features, retrieval performance is significantly improved, allowing us to increase the number of database images by a factor of 10. We also introduce a generalization of the traditional vocabulary tree search algorithm which improves performance by effectively increasing the branching factor of a fixed vocabulary tree.}, author = {Schindler, Grant and Brown, Matthew and Szeliski, Richard}, booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, citeulike-article-id = {1645838}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270175}, journal = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, keywords = {bibtex-import, city, greedy, location, recognition, scale, thesis, tree, vocabulary}, pages = {1--7}, posted-at = {2007-09-11 23:35:26}, priority = {0}, title = {City-Scale Location Recognition}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270175}, year = {2007} }

TY - CONF ID - Schindler:2007:CityScale L3 - citeulike-article-id:1645838 N2 - We look at the problem of location recognition in a large image dataset using a vocabulary tree. This entails finding the location of a query image in a large dataset containing 3 × 104 streetside images of a city. We investigate how the traditional invariant feature matching approach falls down as the size of the database grows. In particular we show that by carefully selecting the vocabulary using the most informative features, retrieval performance is significantly improved, allowing us to increase the number of database images by a factor of 10. We also introduce a generalization of the traditional vocabulary tree search algorithm which improves performance by effectively increasing the branching factor of a fixed vocabulary tree. JF - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on EP - 7 TI - City-Scale Location Recognition T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on SP - 1 KW - bibtex-import KW - city KW - greedy KW - location KW - recognition KW - scale KW - thesis KW - tree KW - vocabulary AU - Schindler, Grant AU - Brown, Matthew AU - Szeliski, Richard PY - 2007/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270175 ER -