Track data determination system and method

• US 9,846,025 B2
• Filed: 12/21/2012
• Issued: 12/19/2017
• Est. Priority Date: 12/21/2012
• Status: Active Grant

• Current Assignee: Wabtec Holding Corp (Westinghouse Air Brake Technologies Corporation)
• Original Assignee: Wabtec Holding Corp (Westinghouse Air Brake Technologies Corporation)
• Inventors: Kirchner, Michael Charles, Kernwein, Jeffrey D., Diefenderfer, Chad E., Wall, Matthew T.
• Primary Examiner(s): Messmore, Jonathan
• Application Number:
  US13/723,378
• Publication Number:
  US 20140176711A1
• Time in Patent Office: 1,824 Days
• Field of Search: 348148
• CPC Class Codes: B61L 2205/04 Satellite based navigation systems, e.g. global positioning system [GPS]
• CPC Class Codes: B61L 23/041 Obstacle detection
• CPC Class Codes: B61L 25/025 Absolute localisation, e.g. providing geodetic coordinates
• CPC Class Codes: G01B 11/00 Measuring arrangements characterised by the use of optical techniques
• CPC Class Codes: G01S 19/485 whereby the further system is an optical system or imaging system
• CPC Class Codes: G01S 19/49 whereby the further system is an inertial position system, e.g. loosely-coupled
• CPC Class Codes: G01S 19/50 whereby the position solution is constrained to lie upon a particular curve or surface, e.g. for locomotives on railway tracks

Abstract

A track data determination system including: a video camera device positioned on a vehicle to capture video data in at least one field-of-view; a geographic positioning unit associated with the vehicle to generate position data and time data; a recording device to store at least one of the following: at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof; and a controller to: (i) receive the video data, the position data, and/or the time data; and (ii) determine track data based at least in part upon the video data, the position data, and/or the time data. A computer-implemented track data determination method is also disclosed.

Claims

1. A track data determination system for use in connection with at least one vehicle configured to traverse a track, the system comprising:

at least one video camera device positioned on a portion of the at least one vehicle and configured to capture video data in at least one field-of-view forward of the at least one vehicle;

at least one geographic positioning unit associated with the at least one vehicle and configured to generate position data and time data;

at least one recording device configured to store at least one of the following;

at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof; and

at least one controller configured to;

(i) receive at least one of the following;

at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof; and

(ii) determine track data based at least in part upon at least one of the following;

at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof,

wherein the track data comprises at least one of the following;

track centerline data, feature data, verification data, or any combination thereof,

wherein the track data comprises the track centerline data,

wherein the track centerline data comprises data sufficient to define a centerline between rails of the track along a section of the track,

wherein the track centerline data is used to determine a position and orientation of the at least one camera device to the centerline of the track, and

wherein the at least one controller is further configured to;

identify at least one point on a surface of at least one feature located outside of the rails and in the field of view forward of the at least one vehicle;

receive dimension data including known physical dimensions of the at least one feature;

determine the relative position of the at least one feature with respect to the at least one video camera device and the centerline of the track by processing the at least one point on the surface of the at least one feature against the known dimensions of the at least one feature and the track centerline data; and

determine the global position of the at least one feature by processing the relative position of the at least one feature with respect to the at least one video camera device and the centerline of the track against the at least a portion of the position data.

2. The track data determination system of claim 1, wherein the at least one controller is further configured to synchronize at least a portion of the video data with at least a portion of the position data based at least partially on at least a portion of the time data.

3. The track data determination system of claim 1, wherein, prior to the determination step (ii), the controller is configured to receive camera calibration data, and wherein the camera calibration data includes at least one of the following:

focal length, lens distortion, pose, measured data, position data, orientation data, viewpoint data, camera data, or any combination thereof.

4. The track data determination system of claim 1, wherein the at least one geographic positioning unit is a Global Positioning System device in communication with at least one Global Positioning System satellite, and wherein the position data comprises raw Global Positioning System data.

5. The track data determination system of claim 4, wherein the at least one controller is further configured to process at least a portion of the raw Global Positioning System data by applying at least one processing routine based at least partially on at least one of the following:

pseudo-range data, satellite data, ephemeris data, clock data, ionosphere data, correction data, third-party data, reference data, or any combination thereof.

6. The track data determination system of claim 5, wherein the at least one processing routine comprises a Precise Point Positioning technique.

7. The track data determination system of claim 1, further comprising at least one inertial measurement unit positioned on a portion of the vehicle and configured to generate inertial data.

8. The track data determination system of claim 7, wherein the at least one controller is further configured to process at least a portion of the position data by applying at least one processing routine based at least partially on the inertial data.

9. The track data determination system of claim 8, wherein the at least one processing routine comprises a Kalman filter.

10. The track data determination system of claim 1, wherein the at least one controller is further configured to:

determine camera calibration data comprising at least one of the position of the at least one video camera device and the orientation of the at least one video camera device; and

based at least partially on the time data, correlate at least a portion of the position data and at least a portion of the camera calibration data.

11. The track data determination system of claim 1, wherein the at least one controller is further configured to determine feature data.

12. The track data determination system of claim 11, wherein at least a portion of the feature data is determined by applying at least one object recognition routine to at least a portion of the video data.

13. The track determination system of claim 11, wherein at least a portion of the feature data is determined by applying at least one pose estimation routine to at least a portion of the video data.

14. The track data determination system of claim 1, wherein at least one component of the at least one video camera device is mounted to a front of the at least one locomotive that is spaced apart from a roof of the at least one locomotive and substantially in line with the centerline of the track and a forward wheel assembly kingpin.

27. The track data determination system of claim 1, wherein the relative position of the at least one feature with respect to the at least one video camera device is determined based on a known standard width of the rails of the track and a pixel width of the track in the video data.

28. The track data determination system of claim 27, further comprising determining a lateral distance to the at least one feature from the centerline of the track based on a pixel width from the centerline of the track to the at least one feature in the video data at an area perpendicular to the track.

29. The track data determination system of claim 1, wherein the at least a portion of the track data including the track centerline data is used to build an initial track database, and wherein the at least one controller is configured to:

(i) receive track data including track centerline data from the initial track database;

(ii) determine track centerline data based on the position data generated by the at least one geographic positioning unit;

(iii) determine the position and orientation of the at least one camera device to the centerline of the track based on a difference between a position of the at least one geographic positioning unit and a position of the at least one camera device and the determined track centerline data;

(iv) compare at least a portion of the track data including the track centerline data from the initial track database to at least a portion of the determined track centerline data;

(v) based at least partially on the comparison, generate improved track data; and

(vi) populate the initial track database with the improved track data.

15. A computer-implemented track data determination method, comprising:

capturing video data in at least one field-of-view forward of the at least one vehicle by at least one video camera device positioned on a portion of at least one vehicle configured to traverse a track;

generating position data and time data by at least one geographic positioning unit associated with the at least one vehicle;

storing, by at least one recording device, at least one of the following;

at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof; and

determining track data based at least in part upon at least one of the following;

at least a portion of the video data, at least a portion of the position data, at least a portion of the time data, or any combination thereof,

wherein the track data comprises at least one of the following;

track centerline data, feature data, verification data, or any combination thereof,

wherein the track data comprises the track centerline data,

wherein the track centerline data comprises data sufficient to define a centerline between rails of the track along a section of the track,

wherein the track centerline data is used to determine a position and orientation of the at least one video camera device to the centerline of the track, and

wherein the method further comprises;

identifying at least one point on a surface of at least one feature located outside of the rails and in the field of view forward of the at least one vehicle;

receiving dimension data including known physical dimensions of the at least one feature;

determining the relative position of the at least one feature with respect to the at least one video camera device and the centerline of the track by processing the at least one point on the surface of the at least one feature against the known dimensions of the at least one feature and the track centerline data; and

determining the global position of the at least one feature by processing the relative position of the at least one feature with respect to the at least one video camera device and the centerline of the track against the at least a portion of the position data.

16. The track data determination method of claim 15, further comprising synchronizing at least a portion of the video data with at least a portion of the position data based at least partially on at least a portion of the time data.

17. The track data determination method of claim 15, wherein, prior to the determination step, the method further comprises generating camera calibration data, and wherein the camera calibration data includes at least one of the following:

focal length, lens distortion, pose, measured data, position data, orientation data, viewpoint data, camera data, or any combination thereof.

18. The track data determination method of claim 15, further comprising applying, to at least a portion of the position data, at least one processing routine based at least partially on at least one of the following:

pseudo-range data, satellite data, ephemeris data, clock data, ionosphere data, correction data, third-party data, reference data, or any combination thereof.

19. The track data determination method of claim 18, wherein the at least one processing routine comprises a Precise Point Positioning technique.

20. The track data determination method of claim 15, further comprising:

generating inertial data by at least one inertial measurement unit positioned on a portion of the vehicle; and

applying, to at least a portion of the position data, at least one processing routine based at least partially on the inertial data.

21. The track data determination method of claim 20, wherein the at least one processing routine comprises a Kalman filter.

22. The track data determination method of claim 15, further comprising:

determining camera calibration data comprising at least one of the position of the at least one video camera device and the orientation of the at least one video camera device; and

based at least partially on the time data, correlating at least a portion of the position data and at least a portion of the camera data.

23. The track data determination method of claim 15, further comprising determining feature data by at least one of the following:

applying at least one object recognition routine to at least a portion of the video data; and

applying at least one pose estimation routine to at least a portion of the video data.

24. The track data determination method of claim 15, further comprising building an initial track database based at least partially on at least a portion of the track data.

25. The track data determination method of claim 15, further comprising:

receiving track data from an existing track database;

comparing at least a portion of the track data from the existing track database to at least a portion of the determined track data; and

based at least partially on the comparison, building a corrected track database.

26. The track data determination system of claim 15, the method further comprising mounting at least one component of the at least one video camera device to a front of the at least one locomotive that is spaced apart from a roof of the at least one locomotive and substantially in line with the centerline of the track and a forward wheel assembly kingpin.