Visual localization method
There is provided a visual localization method comprising: (a) transmitting data representative of one or more detected visual features from a mobile device to a server; (b) estimating the location of the mobile device at the server based on the visual features received from the mobile device; (c) transmitting reference data associated with the estimated location from the server to the mobile device; and (d) the mobile device determining its location based on the reference data received from the server.
1. A visual localization method comprising:
(a) maintaining, by a server, reference data that can be associated with a plurality of possible locations of a mobile device;
(b) receiving, by the server, information about a context of the mobile device;
(c) periodically determining, by the server based on the received information, approximate positions of the mobile device, and adaptive subsets of the reference data within vicinities of said approximate positions;
(d) periodically pushing the adaptive subsets of the reference data from the server to the mobile device;
(e) storing, by the mobile device, at least a portion of the adaptive subsets of the reference data received by the mobile device;
(f) generating, by the mobile device, using interest points tracked over multiple frames recorded by the mobile device, feature data representative of one or more features detected by the mobile device;
(g) determining, by the mobile device, location data representative of a location of the mobile device based on at least the feature data and the stored adaptive subsets of the reference data.
2. The method of claim 1 , wherein said received information includes at least one query image, and determining the adaptive subsets of the reference data in step c) is based on information taken from content of the at least one query image.
3. The method of claim 2 , wherein said information taken from the content of the at least one query image includes one or more of an exhibit, a store name or a trademark.
4. A mobile device pose estimation method comprising:
(a) maintaining, by a server, reference data in a database providing a distinctive description of recorded objects;
(b) receiving, by the server, information about a context of a mobile device;
(c) periodically determining, by the server, based on the received information, adaptive subsets of the reference data;
(d) periodically pushing the adaptive subsets of the reference data from the server to the mobile device;
(e) storing, by the mobile device, at least a portion of the adaptive subsets of the reference data;
(f) generating, by the mobile device, using interest points tracked over multiple frames recorded by the mobile device, feature data representative of one or more features detected by the mobile device;
(g) estimating, by the mobile device, the pose of the mobile device based on at least the feature data and the stored adaptive subsets of the reference data.
5. The method of claim 4 , wherein said received information includes at least one query image, and determining the adaptive subsets of the reference data in step c) is based on information taken from content of the at least one query image.
6. The method of claim 5 , wherein said information taken from the content of the at least one query image includes one or more of an exhibit, a store name or a trademark.