Crowd sourced mapping with robust structural features
A location and mapping service is described that creates a global database of indoor navigation maps through crowd-sourcing and data fusion technologies. The navigation maps consist of a database of geo-referenced, uniquely described features in the multi-dimensional sensor space (e.g., including structural, RF, magnetic, image, acoustic, or other data) that are collected automatically as a tracked mobile device is moved through a building (e.g. a person with a mobile phone or a robot). The feature information can be used to create building models as one or more tracked devices traverse a building.
1. A device location method, comprising:
recording magnetic signal data from a tracked device traversing a route associated with a building structure, wherein the magnetic signature data corresponds to a first velocity of the tracked device traversing the route;
based on the recorded magnetic signal data, generating a magnetic signature indicative of changes in magnetic field strength along the route;
comparing the magnetic signature to at least one previously recorded magnetic signature associated with the building structure; and
estimating a location of the tracked device relative to the building structure based on comparing the magnetic signatures.
2. The method of claim 1 , wherein the magnetic signal data is indicative of magnetic field and altitude along the route.
3. The method of claim 1 , further comprising recording additional signal data including at least one of: radiofrequency signal data, Wi-Fi signal data, Bluetooth signal data, accelerometer data, gyroscope data, pressure data, light data, GPS data, vibration data, acoustic signature data, and image data; and estimating the location of the tracked device based, in part, on the recorded additional signal data.
4. The method of claim 1 , wherein comparing the magnetic signatures comprises matching at least one portion of the route.
5. The method of claim 1 , wherein the tracked device is at least one of a mobile computing device, a wearable accessory, a wireless communication device, and a smartphone.
6. The method of claim 1 , wherein the signal data is continuously recorded over a time interval.
7. The method of claim 1 , wherein only transitions in magnetic field magnitude data exceeding a predetermined threshold value are recorded.
8. The method of claim 1 , further comprising determining at least one feature along the route based on comparing the magnetic signatures.
9. The method of claim 8 , wherein the at least one feature is a hallway, a stairwell, a ramp, an escalator, and an elevator.
10. The method of claim 1 , further comprising comparing variability in measured magnetic magnitude.
11. The method of claim 1 , wherein the at least one previously recorded magnetic signature corresponds to a second velocity of the tracked device or a different tracked device traversing the route, and wherein comparing includes using dynamic time warping to match the magnetic signature corresponding to the first velocity to the at least one previously recorded magnetic signature corresponding to the second velocity.
12. The method of claim 11 , wherein recording includes compressing information within the magnetic signal data by only recording transitions in magnetic field magnitude data exceeding a predetermined threshold value.
13. A computing system comprising:
at least one processor; and
a memory in communication with the at least one processor and comprising instructions that, when executed by the one or more processors, cause the computing system to at least:
record magnetic signal data from a tracked device traversing a route associated with a building structure, wherein the magnetic signature data corresponds to a first velocity of the tracked device traversing the route;
based on the recorded magnetic signal data, generate a magnetic signature indicative of changes in magnetic field strength along the route;
compare the magnetic signature to at least one previously recorded magnetic signature associated with the building structure; and
estimate a location of the tracked device relative to the building structure based on comparing the magnetic signatures.
14. The computing system of claim 13 , wherein the instructions further cause the computing system to at least store the magnetic signature in a storage device.
15. The computing system of claim 13 , wherein previously recorded signatures are accessible from a storage device or a server.
16. The computing system of claim 13 , wherein the instructions further cause the computing system to at least compare the magnetic signatures by matching at least one portion of the route.
17. The computing system of claim 13 , wherein the instructions further cause the computing system to at least:
record signal data including at least one of: radiofrequency signal data, Wi-Fi signal data, Bluetooth signal data, accelerometer data, gyroscope data, pressure data, light data, GPS data, vibration data, acoustic signature data, and image data; and
estimate the location of the tracked device based, in part, on the signal data.
18. The computing system of claim 13 , wherein the tracked device is at least one of a mobile computing device, a wearable accessory, a wireless communication device, and a smartphone.
19. The computing system of claim 13 , wherein the signal data is continuously recorded over a time interval.
20. The computing system of claim 13 , wherein only transitions in magnetic field magnitude data exceeding a predetermined threshold value are recorded.
21. The computing system of claim 13 , wherein the instructions further cause the computing system to at least determine at least one feature along the route based on comparing the magnetic signatures.
22. The computing system of claim 13 , wherein the instructions further cause the computing system to at least compare variability in measured magnetic magnitude.
23. The computing system of claim 13 , wherein the magnetic signature corresponds to a first velocity of the tracked device traversing the route, wherein the at least one previously recorded magnetic signature corresponds to a second velocity of the tracked device or a different tracked device traversing the route, and wherein the instructions further cause the computing system to at least compare by using dynamic time warping to match the magnetic signature corresponding to the first velocity to the at least one previously recorded magnetic signature corresponding to the second velocity.
24. The computing system of claim 23 , wherein the instructions further cause the computing system to at least record by compressing information within the magnetic signal data by only recording transitions in magnetic field magnitude data exceeding a predetermined threshold value.