Towards accurate camera geopositioning by image matching

Onderzoeksoutput: Bijdrage aan congresPaperAcademic

Samenvatting

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%.
Originele taal-2Engels
StatusGepubliceerd - 2018
EvenementThe Netherlands Conference on Computer Vision 2018 -
Duur: 26 sep 201827 sep 2018

Congres

CongresThe Netherlands Conference on Computer Vision 2018
Verkorte titelNCCV18
Periode26/09/1827/09/18

Vingerafdruk Duik in de onderzoeksthema's van 'Towards accurate camera geopositioning by image matching'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Imbriaco, R., Sebastian, C., Bondarau, Y., & de With, P. H. N. (2018). Towards accurate camera geopositioning by image matching. Paper gepresenteerd op The Netherlands Conference on Computer Vision 2018, .