LOCALISATION OF MOBILE DEVICE USING IMAGE AND NON-IMAGE SENSOR DATA IN SERVER PROCESSING
The present invention relates to method of localisation for devices. More particularly, it relates the use of both local and remote resources to provide substantially real time localisation at a device. According to an aspect, there is provided a method of determining a location of a device having one or more sensors comprising the steps of: sending a localisation request to a server system, the localisation request comprising at least a portion of data from the one or more sensors; receiving localisation data from the server system in response to the localisation request; and determining a location of the device from the received localisation data. Optionally, the method includes the further step of estimating a location of the device based on data from the one or more sensors and wherein the step of determining a location of the device includes determining the location of the device using the estimated location.
1 . A computer-implemented method comprising:
receiving, by a computing system, a localisation request, wherein the localisation request includes sensor data associated with a device;
determining, by the computing system, one or more localisation nodes from a global map based on the sensor data;
generating, by the computing system, localisation data based on an aggregation of the one or more localisation nodes; and
providing, by the computing system, the localisation data, wherein the localisation data facilitates a localisation process for the device.
2 . The computer-implemented method of claim 1 , wherein determining the one or more localisation nodes from the global map comprises:
determining, by the computing system, a location estimate associated with the localisation request; and
performing, by the computing system, a search of localisation nodes within a threshold proximity of the location estimate for the one or more localisation nodes.
3 . The computer-implemented method of claim 2 , wherein performing the search of localisation nodes comprises:
extracting, by the computing system, visual signatures from the sensor data; and
determining, by the computing system, the one or more localisation nodes based on the visual signatures, wherein the one or more localisation nodes are associated with signatures that satisfy a threshold similarity with the visual signatures.
4 . The computer-implemented method of claim 1 , further comprising:
generating, by the computing system, a new localisation node in the global map based on the sensor data; and
updating, by the computing system, the global map based on the new localisation node.
5 . The computer-implemented method of claim 4 , wherein updating the global map comprises:
determining, by the computing system, the new localisation node has a same position as a localisation node in the global map; and
linking, by the computing system, the new localisation node with the localisation node in the global map.
6 . The computer-implemented method of claim 4 , wherein updating the global map comprises:
determining, by the computing system, the new localisation node has a position outside the global map; and
extending, by the computing system, the global map based on the new localisation node.
7 . The computer-implemented method of claim 4 , wherein updating the global map is based on a determination that a threshold number of new localisation nodes have been generated for the global map.
8 . The computer-implemented method of claim 1 , wherein the aggregation of the one or more localisation nodes includes a global pose of the device determined based on the one or more localisation nodes.
9 . The computer-implemented method of claim 1 , wherein the global map includes links between localisation nodes in the global map, wherein the links include relative position differences and relative rotation differences between positions of the localisation nodes.
10 . The computer-implemented method of claim 1 , wherein each of the one or more localisation nodes includes at least one of: a picture, a position of a visual feature, a depth map, a three-dimensional point cloud, and metadata for a location.
11 . A system comprising:
at least one processor; and
a memory storing instructions that, when executed, cause the system to perform operations comprising:
receiving a localisation request, wherein the localisation request includes sensor data associated with a device;
determining one or more localisation nodes from a global map based on the sensor data;
generating localisation data based on an aggregation of the one or more localisation nodes; and
providing the localisation data, wherein the localisation data facilitates a localisation process for the device.
12 . The system of claim 11 , wherein determining the one or more localisation nodes from the global map comprises:
determining a location estimate associated with the localisation request; and
performing a search of localisation nodes within a threshold proximity of the location estimate for the one or more localisation nodes.
13 . The system of claim 12 , wherein performing the search of localisation nodes comprises:
extracting visual signatures from the sensor data; and
determining the one or more localisation nodes based on the visual signatures, wherein the one or more localisation nodes are associated with signatures that satisfy a threshold similarity with the visual signatures.
14 . The system of claim 11 , the operations further comprising:
generating a new localisation node in the global map based on the sensor data; and
updating the global map based on the new localisation node.
15 . The system of claim 14 , wherein updating the global map comprises:
determining the new localisation node has a same position as a localisation node in the global map; and
linking the new localisation node with the localisation node in the global map.
16 . A non-transitory computer-readable storage medium including instructions that, when executed, cause a computing system to perform operations comprising:
receiving a localisation request, wherein the localisation request includes sensor data associated with a device;
determining one or more localisation nodes from a global map based on the sensor data;
generating localisation data based on an aggregation of the one or more localisation nodes; and
providing the localisation data, wherein the localisation data facilitates a localisation process for the device.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein determining the one or more localisation nodes from the global map comprises:
determining a location estimate associated with the localisation request; and
performing a search of localisation nodes within a threshold proximity of the location estimate for the one or more localisation nodes.
18 . The non-transitory computer-readable storage medium of claim 17 , wherein performing the search of localisation nodes comprises:
extracting visual signatures from the sensor data; and
determining the one or more localisation nodes based on the visual signatures, wherein the one or more localisation nodes are associated with signatures that satisfy a threshold similarity with the visual signatures.
19 . The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:
generating a new localisation node in the global map based on the sensor data; and
updating the global map based on the new localisation node.
20 . The non-transitory computer-readable storage medium of claim 19 , wherein updating the global map comprises:
determining the new localisation node has a same position as a localisation node in the global map; and
linking the new localisation node with the localisation node in the global map.