Vehicle localization precision enhancement via multi-sensor fusion
A method of determining a vehicle position and a vehicle velocity, including receiving a camera image sequence based on a camera borne by a vehicle and determining a camera pose based on the camera image sequence. The method includes determining a global position system location based on a global position system receiver borne by the vehicle, determining an inertial movement signal based on an inertial movement unit borne by the vehicle and receiving a wheel encoder signal from a wheel of the vehicle. The method additionally includes determining at least one of the vehicle positions and the vehicle velocity based on at least two of the camera pose, the global position system location, the inertial movement signal and the wheel encoder signal in temporal synchronization.
1. A method of determining a vehicle position, comprising:
receiving a camera image sequence from a camera borne by a vehicle;
determining a camera pose to determine the position and orientation of the camera on the vehicle based on the camera image sequence;
determining a global position system location from a global position system receiver borne by the vehicle;
determining an inertial movement signal based on an inertial movement unit borne by the vehicle;
receiving a wheel encoder signal from a wheel of the vehicle; and
determining at least one of the vehicle position and a vehicle velocity based on a fusion of at least one category with a least one different category, the categories selected from the group consisting of the camera pose, the global position system location, the inertial movement signal, and the wheel encoder signal in temporal synchronization.
2. The method of claim 1 further comprising correcting the camera pose based on at least one of the global position system location, the inertial movement signal, and the wheel encoder signal.
3. The method of claim 1 further comprising filtering of at least one of the vehicle position and the vehicle velocity.
4. The method of claim 1 further comprising extended Kalman filtering of at least one of the vehicle position and the vehicle velocity.
5. The method of claim 1 further comprising converting at least one of at least one of the vehicle position and the vehicle velocity to the global position system location.
6. The method of claim 1 further comprising converting a set of global position system earth-centered earth-fixed coordinates to a set of east north up coordinates.
7. The method of claim 1 further comprising converting a set of global position system earth-centered earth-fixed coordinates to a set of north east down coordinates.
8. The method of claim 1 further comprising initializing at least one of the vehicle position and the vehicle velocity based on the fusion at least one category with a least one different category, the categories selected from the group consisting of the camera pose, the global position system location, the inertial movement signal, and the wheel encoder signal.
9. The method of claim 1 further comprising correcting the camera pose based on a wheel encoder extrinsic parameter.
10. A method of determining a vehicle position, comprising:
receiving a camera image sequence from a camera borne by a vehicle;
determining a camera pose to determine the position and orientation of the camera on the vehicle based on the camera image sequence;
determining a global position system location from a global position system receiver borne by the vehicle;
determining an inertial movement signal based on an inertial movement unit borne by the vehicle;
receiving a wheel encoder signal from a wheel of the vehicle; and
initializing the vehicle position and a vehicle velocity based on a fusion of at least one category with a least one different category, the categories selected from the group consisting of the camera pose, the global position system location, the inertial movement signal, and the wheel encoder signal.
11. The method of claim 10 further comprising correcting the camera pose based on at least one of the global position system location, the inertial movement signal, and the wheel encoder signal.
12. The method of claim 10 further comprising filtering of at least one of the vehicle position and the vehicle velocity.
13. The method of claim 10 further comprising extended Kalman filtering of at least one of the vehicle position and the vehicle velocity.
14. The method of claim 10 further comprising converting at least one of at least one of the
vehicle position and the vehicle velocity to the global position system location.
15. The method of claim 10 further comprising converting a set of global position system earth-centered earth-fixed coordinates to a set of east north up coordinates.
16. The method of claim 10 further comprising converting a set of global position system earth-centered earth-fixed coordinates to a set of north east down coordinates.
17. The method of claim 10 further comprising correcting the camera pose based on a wheel encoder extrinsic parameter.