Method of Augmenting GPS or GPS/Sensor Vehicle Positioning Using Additional In-Vehicle Vision Sensors

• US 20120116676A1
• Filed: 11/10/2010
• Published: 05/10/2012
• Est. Priority Date: 11/10/2010
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (General Motors Company)
• Inventors: Basnayake, Chaminda, Zhang, Wende
• Granted Patent: US 8,447,519 B2
• Time in Patent Office: Days
• US Class Current: 701/469
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01S 19/40 Correcting position, velocity or attitude
• CPC Class Codes: G01S 19/485 whereby the further system is an optical system or imaging system
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems

Abstract

A method is provided for augmenting GPS data using an in-vehicle vision-based module. A vehicle position is determined utilizing position-related data obtained from a position module. A position error is estimated on a periodic basis. A determination is made whether the position error estimate exceeds a first predetermined error threshold. Tracking data is generated for the vehicle over a course of travel utilizing captured images from the in-vehicle vision based module. The tracking data is integrated with the position-related data to estimate the vehicle position in response to the position error estimate exceeding the first predetermined error threshold. A determination is made whether the position error estimate decreases below a second predetermined error threshold. The vehicle position is re-determined using only the position-related data when the position error estimate decreases below the second predetermined error threshold.

Claims

1. A method of augmenting GPS data using an in-vehicle vision-based module, the method comprising:

determining a vehicle position utilizing position-related data obtained from a position module;

estimating a position error on a periodic basis determining whether the position error estimate exceeds a first predetermined error threshold;

generating tracking data for the vehicle over a course of travel utilizing captured images from the in-vehicle vision based module;

integrating the tracking data with the position-related data to estimate the vehicle position in response to the position error estimate exceeding the first predetermined error threshold;

determining whether the position error estimate decreases below a second predetermined error threshold; and

re-determining the vehicle position using only the position-related data when the position error estimate decreases below the second predetermined error threshold.

2. The method of claim 1 wherein the vehicle position module utilizes position-related data obtained from a GPS-based device.

3. The method of claim 1 wherein the vehicle position module utilizes position-related data obtained from a GPS-dead reckoning based device.

4. The method of claim 1 wherein the first predetermined location error threshold is greater than the second predetermined location error threshold.

5. The method of claim 1 wherein the in-vehicle vision based module uses a feature identification and classification function for identifying an object and classifying the object as a stationary object from the tracking data.

6. The method of claim 5 wherein the stationary objects are classified as far-distance stationary objects and close-distance stationary objects.

7. The method of claim 6 wherein the far-distance stationary objects are tracked over time for correcting yaw estimation.

8. The method of claim 6 wherein the far-distance stationary objects are tracked over time for correcting pitch estimation.

9. The method of claim 6 wherein the far-distance stationary objects are tracked over time for correcting roll estimation.

10. The method of claim 6 wherein the close-distance stationary objects are tracked over time for correcting yaw estimation.

11. The method of claim 6 wherein the far-distance stationary objects are tracked over time for correcting distance estimation.

12. The method of claim 10 wherein the close-distance stationary objects are tracked utilizing a flat ground assumption technique.

13. The method of claim 1 wherein the path of travel of the vehicle is continuously tracked by the in-vehicle vision based module.

14. An augmented vehicle positioning system comprising:

a vehicle-position module for determining a vehicle position of a vehicle utilizing position-related data, the vehicle position module further determining a position error estimate that provides a confidence level of an accuracy of the vehicle position; and

an in-vehicle vision based module for capturing images over a path of travel of the vehicle for generating tracking data;

wherein a determination is made whether the position error estimation exceeds a first predetermined error threshold, wherein the tracking data is integrated with the position-related data to estimate a current vehicle position when the position error exceeds the first predetermined error, and wherein the current vehicle position is re-determined using only the position-related data when the position error estimate is less than a second predetermined error threshold.

15. The augmented vehicle positioning system of claim 14 wherein the vehicle position module determines a GPS-related position of a vehicle utilizing GPS data obtained from GPS satellites.

16. The augmented vehicle positioning system of claim 15 further comprising at least one vehicle motion sensor for obtaining vehicle motion data, wherein the vehicle position module provides dead-reckoning functionality for estimating the GPS-related position using the vehicle motion data in cooperation with the GPS data, the vehicle position module updating the GPS-related position using the dead reckoning functionality during periods when GPS-satellite reception is limited.

17. The augmented vehicle positioning system of claim 16 wherein the in-vehicle vision based module identifies objects from the captured images, and wherein the in-vehicle vision based module classifies the object as a stationary object for tracking.

18. The augmented vehicle positioning system of claim 17 wherein the in-vehicle vision-based module classifies the stationary objects as far-distance stationary objects and close-distance stationary objects.

19. The augmented vehicle positioning system of claim 18 wherein the far-distance stationary objects are tracked over time for correcting a yaw and pitch estimation in the GPS-related position.

20. The augmented vehicle positioning system of claim 18 wherein the close-distance stationary objects are tracked over time for correcting a yaw and distance estimation in the GPS-related position.

21. The augmented GPS-related vehicle positioning system of claim 14 wherein the first predetermined error threshold is greater than the second predetermined error threshold.

22. The augmented vehicle positioning system of claim 21 wherein the in-vehicle vision module includes vision devices capturing images forward of the vehicle.

23. The augmented vehicle positioning system of claim 21 wherein the in-vehicle vision module includes vision devices capturing images rearward of the vehicle.