Intelligent railyard monitoring system

• US 20070291985A1
• Filed: 06/20/2006
• Published: 12/20/2007
• Est. Priority Date: 06/20/2006
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Krahnstoever, Nils Oliver, Bhotika, Rahul, Davenport, David Michael, Hershey, John Erik, Mitchell, Robert James, Andarawis, Emad Andarawis, Welles, Kenneth Brakeley
• Application Number:
  US11/471,156
• Publication Number:
  US 20070291985A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: B61L 17/00 Switching systems for classification yards
• CPC Class Codes: B61L 23/00 Control, warning or like safety means along the route or between vehicles or trains
• CPC Class Codes: B61L 23/041 Obstacle detection
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

Embodiments include an intelligent railyard monitoring system including a plurality of video devices, a device for interpreting captured images in operable communication with the plurality of video devices, a device controller in operable communication with the device for interpreting captured images wherein the system is capable of analyzing multiple video streams from the video devices to detect, locate, and track one or more targets and wherein the device for interpreting captured images includes a computing device.

Claims

1. An intelligent railyard monitoring system comprising:

a plurality of video devices disposed within a railyard;

a device for interpreting captured images in operable communication with the plurality of video devices; and

a device controller in operable communication with the device for interpreting captured images, wherein the system is capable of analyzing multiple video streams from the video devices to detect, locate, and track one or more targets, and wherein the device for interpreting captured images includes a computing device.

2. The intelligent railyard monitoring system of claim 1, wherein the device for interpreting captured images comprises:

a data storage device;

a communications device; and

a display device.

3. The intelligent railyard monitoring system of claim 2, wherein the communications device is a wireless communications device.

4. The intelligent railyard monitoring system of claim 1, wherein the device controller is in operable communication with at least a portion of the plurality of video devices and is operable for controlling the direction that the portion of the plurality of video devices is pointed.

5. An intelligent method for monitoring a railyard comprising:

receiving a plurality of video feeds from a plurality of video devices disposed within the railyard;

detecting a target in the railyard;

classifying the target; and

tracking the target through the railyard.

6. The intelligent method for monitoring a railyard of claim 5, wherein classifying the target in the railyard comprises comparing the target to a database of known target types.

7. The intelligent method for monitoring a railyard of claim 5, wherein detecting the target in the railyard comprises a foreground-background segmentation of at least a portion of the video feeds.

8. The intelligent method for monitoring a railyard of claim 5, wherein an optical illumination device is disposed on a yard asset to be tracked.

9. The intelligent method for monitoring a railyard of claim 8, wherein the optical illumination device is configured to flash at a specific rate or using a specific wavelength to facilitate classification of one type of asset from another.

10. The intelligent method for monitoring a railyard of claim 5, wherein classifying the target comprises a template-based target classification system.

11. The intelligent method for monitoring a railyard of claim 5, wherein tracking the target through the railyard includes the use of a global railyard coordinate system.

12. The intelligent method for monitoring a railyard of claim 5, wherein tracking the target through the railyard comprises tracking the target from frame to frame and from video device to video device.

13. The intelligent method for monitoring a railyard of claim 5, wherein the tracking of the target is preformed responsive to the classification of the target.

14. The intelligent method for monitoring a railyard of claim 5, further comprising activating an alert responsive to the classification of the target.

15. The intelligent method for monitoring a railyard of claim 5, further comprising activating an alert responsive to the tracking of the target.

16. A computer program for implementing an intelligent method for monitoring a railyard, the computer program product comprising:

a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for facilitating a method comprising;

receiving a plurality of video feeds from a plurality of video devices disposed within the railyard;

detecting a target in the railyard;

comparing the target to a database of known target types;

classifying the target; and

tracking the target through the railyard.

17. The computer program product of claim 16, wherein detecting the target in the railyard comprises a foreground-background segmentation of at least a portion of the video feeds.

18. The computer program product of claim 16, wherein classifying the target comprises a template-based target classification system.

19. The computer program product of claim 16, wherein tracking the target through the railyard includes the use of a global railyard coordinate system.

20. The computer program product of claim 16, wherein the tracking of the target is performed responsive to the classification of the target.