City Scale Image Geolocalization via Dense Scene Alignment

WACV 2015: IEEE Winter Conference on Applications of Computer Vision

Semih Yagcioglu       Erkut Erdem       Aykut Erdem      

Hacettepe University Computer Vision Lab (HUCVL)
Dept. of Computer Engineering, Hacettepe University, Ankara, TURKEY


System Overview. For a query image, our coarse-to-fine approach first finds the top matches in the dataset using GIST and Tiny Image descriptors, which is followed by an outlier removal procedure. This initial set of images is then refined by densely aligning the retrieved images using DSP matching and accordingly removing the outliers this time by consider the alignment scores.

Abstract

Predicting where a photo was taken is quite important and yet a challenging task for computer vision algorithms. Our motivation is to solve this difficult problem in a city-scale setting by employing a data-driven approach. In order to pursue this goal, we developed a fast and robust scene matching method that follows a coarse-to-fine strategy. In particular, we combine scene retrieval via global features and dense scene alignment and use a large set of geo-tagged images of downtown San Francisco in our evaluation. The experimental results show that the proposed approach, despite its simplicity, is surprisingly effective and achieves comparable results with the state-of-the-art.

paper thumbnail

Paper

image-geolocalization-wacv2015.pdf (8.2MB)

Supplementary Material

Poster - image-geolocalization-poster-wacv2015.pdf (1MB)
Slides - image-geolocalization-slides-wacv2015.pdf (7.2MB)





Results


Query images (left) and retrieved images from the dataset (right).

Code

Github Repository with detailed instructions. You can also download Matlab code as master.zip

Citation

S. Yagcioglu, E. Erdem, A. Erdem. City Scale Image Geolocalization via Dense Scene Alignment. The WACV 2015: IEEE Winter Conference on Applications of Computer Vision, Hawaii, USA, January 2015

Bibtex

@inproceedings{yagcioglu2015city,
author 	= {Yagcioglu, Semih and Erdem, Erkut and Erdem, Aykut},
title 	= {City Scale Image Geolocalization via Dense Scene Alignment},
booktitle = {Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on},
year 	= {2015},
organization 	= {IEEE}}

Contact

For comments and questions, please contact Semih Yagcioglu.

Copyright

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without explicit permission of the copyright holder.