Learning and Calibrating Per-Location Classifiers for Visual Place Recognition

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 907 - 914
• Main Authors: Gronat, Petr, Obozinski, Guillaume, Sivic, Josef, Pajdla, Toma
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Calibration; classifier calibration; Support vector machines; Training; Training data; Vectors; Visual place recognition; Visualization
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2013.122

The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are performed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work.