Paper
15 March 2019 Towards accurate camera geopositioning by image matching
Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter H. N. de With
Author Affiliations +
Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110411C (2019) https://doi.org/10.1117/12.2522999
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany
Abstract
In this work, we present a camera geopositioning system based on matching a query image against a database with panoramic images. For matching, our system uses memory vectors aggregated from global image descriptors based on convolutional features to facilitate fast searching in the database. To speed up searching, a clustering algorithm is used to balance geographical positioning and computation time. We refine the obtained position from the query image using a new outlier removal algorithm. The matching of the query image is obtained with a recall@5 larger than 90% for panorama-to-panorama matching. We cluster available panoramas from geographically adjacent locations into a single compact representation and observe computational gains of approximately 50% at the cost of only a small (approximately 3%) recall loss. Finally, we present a coordinate estimation algorithm that reduces the median geopositioning error by up to 20%.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, and Peter H. N. de With "Towards accurate camera geopositioning by image matching", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110411C (15 March 2019); https://doi.org/10.1117/12.2522999
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Panoramic photography

Databases

Image retrieval

Cameras

Feature extraction

Image processing

Convolutional neural networks

Back to Top