Vision and radio fusion based precise indoor localization
An embodiment includes at least one computer readable storage medium comprising instructions that when executed enable a system to: receive (a)(i) first radio signal location data for a first object from a radio sensor; and (a)(ii) first visual signal location data for the first object from a camera sensor; perform feature extraction on (b)(i) the first radio signal location data to determine first extracted radio signal features; and (b)(ii) the first visual signal location data to determine first extracted visual signal features; solve a first association problem between the first extracted radio signal features and the first extracted visual signal features to determine first fused location data; and store the first fused location data in the at least one computer readable storage medium. Other embodiments are described herein.
1. At least one storage device comprising instructions which, when executed, cause at least one processor to at least:
access sensor data from an environmental sensor, the environmental sensor carried by a tracked object;
identify image data from a camera system separate from the tracked object;
fuse the image data from the camera system with the sensor data from the environmental sensor to generate localization information representing a location of the tracked object, the fusion of the image data and the sensor data based on a first timestamp associated with the image data substantially matching a second timestamp associated with the sensor data; and
initiate upload of the localization information to a remote system for update of a map.
2. The at least one storage device of claim 1 , wherein the tracked object is a moving object.
3. The at least one storage device of claim 1 , wherein the camera system includes at least one stationary camera.
4. The at least one storage device of claim 1 , wherein the environmental sensor is internal to the tracked object.
5. The at least one storage device of claim 1 , wherein the camera system includes at least one monocular camera.
6. A system for localization of objects, the system comprising:
an environmental sensor carried by a tracked object;
a camera system separate from the tracked object;
a transceiver;
at least one processor;
at least one memory including instructions which, when executed, cause the at least one processor to at least:
identify sensor data from the environmental sensor;
identify image data from the camera system;
fuse the image data from the camera system with the sensor data from the environmental sensor to generate localization information representing a location of the tracked object, the fusion of the image data and the sensor data based on a first timestamp associated with the image data substantially matching a second timestamp associated with the sensor data; and
initiate upload of the localization information via the transceiver to a remote system for update of a map.
7. The system of claim 6 , wherein the transceiver is a wireless local area network transceiver.
8. The system of claim 6 , wherein the camera system includes at least one monocular camera.
9. The system of claim 6 , wherein the environmental sensor is to measure a signal received at the tracked object.
10. The system of claim 6 , wherein the tracked object is a moving object.
11. The system of claim 6 , wherein the localization information represents an orientation of the tracked object.
12. The system of claim 6 , further including a display to present the map.
13. A method for localization of objects, the method comprising:
identifying, by executing an instruction with at least one processor, sensor data from an environmental sensor, the environmental sensor carried by a tracked object;
identifying, by executing an instruction with the at least one processor, image data from a camera system, the camera system separate from the tracked object;
fusing, by executing an instruction with the at least one processor, the image data from the camera system with the sensor data from the environmental sensor to generate localization information representing a location of the tracked object, the fusion of the image data and the sensor data based on a first timestamp associated with the image data substantially matching a second timestamp associated with the sensor data; and
initiating upload of the localization information to a remote system for update of a map.
14. The method of claim 13 , further including calibrating timestamps associated with the image data.
15. The method of claim 14 , wherein the calibrating of the timestamps is performed using a network time protocol.
16. The method of claim 13 , further including calibrating timestamps associated with the sensor data.
17. The method of claim 13 , wherein the camera system includes at least one monocular camera external to the object.
18. The method of claim 17 , wherein the environmental sensor is internal to the tracked object.
19. An apparatus for localization of objects, the apparatus comprising:
means for identifying environmental sensor data, the means for identifying the environmental sensor data carried by a tracked object;
means for capturing image data, the means for capturing the image data separate from the tracked object;
means for fusing the image data with the environmental sensor data to generate localization information representing a location of the tracked object, the means for fusing to fuse the image data and the environmental sensor data based on a first timestamp associated with the image data substantially matching a second timestamp associated with the environmental sensor data; and
means for initiating upload of the localization information to a remote system for update of a map.
20. The apparatus of claim 19 , wherein the means for capturing includes at least one stationary camera.
21. The apparatus of claim 19 , wherein the means for identifying is internal to the tracked object.
22. The apparatus of claim 19 , wherein the means for capturing includes at least one monocular camera.