Towards Accurate Camera Geopositioning by Image Matching
This addresses accurate location estimation from images, which is incremental as it builds on existing image matching methods with specific optimizations.
The paper tackles camera geopositioning by matching query images to a panoramic database, achieving over 90% recall@5 for panorama-to-panorama matching and reducing median error by up to 20% with a new algorithm.
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%.