V. A. Krylov, R. Dahyot. "Object Geolocation from Crowdsourced Street Level Imagery",
International Workshop on Urban Reasoning, European Conference on Machine Learning ECML PKDD 2018
Springer LNCS Vol. 11329, ECML PKDD Workshops 2018, pp. 79-83, Dublin (Ireland), September 14, 2018.
[link] [presentation] [pdf] [AIMapIT]
Abstract
We explore the applicability and limitations of a state-of-the-art object detection and geotagging system [4] applied to crowdsourced image data. Our experiments with imagery from Mapillary crowdsourcing platform demonstrate that with increasing amount of images, the detection accuracy is getting close to that obtained with high-end street level data. Nevertheless, due to excessive camera position noise, the estimated geolocation (position) of the detected object is less accurate on crowdsourced Mapillary imagery than with high-end street level imagery obtained by Google Street View.
Bibtex
@INPROCEEDINGS{KrylovECML18,
author = {Vladimir A. Krylov and Rozenn Dahyot},
title = {Object Geolocation from Crowdsourced Street Level Imagery},
year = {2019},
booktitle = {ECML PKDD 2018 Workshops. Springer LNCS 11329},
pages = {79--83},
address = {Dublin, Ireland}
}