Method and system for rail track scanning and foreign object detection

• US 20060098843A1
• Filed: 06/11/2005
• Published: 05/11/2006
• Est. Priority Date: 06/11/2004
• Status: Active Grant

• Current Assignee: Stratech Systems Limited (In Liquidation) (The Stratech Group Ltd.)
• Original Assignee: Stratech Systems Limited (In Liquidation) (The Stratech Group Ltd.)
• Inventors: Chew, Khien Meow David
• Granted Patent: US 7,999,848 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: B61K 9/08 Measuring installations for surveying permanent way applications of measuring apparatus or devices for track building purposes E01B35/00; measuring techniques G01
• CPC Class Codes: B61L 23/041 Obstacle detection

Abstract

A method and system for detecting an object or abnormality on or near a rail track. The system comprises scanning means for scanning on and near a portion of the rail track; and detection means for determining the presence and location of the object or abnormality on or near the portion of the rail track based on information from the scanning means.

Claims

1. A system for detecting an object or abnormality on or near a rail track, the system comprising:

scanning means for scanning on and near a portion of the rail track; and

detection means for determining the presence and location of the object or abnormality on or near the portion of the rail track based on information from the scanning means.

2. A system as claimed in claim 1, further comprising

camera means for capturing one or more images of the object or abnormality based on information from the detection means;

and

image processing means for processing the images captured by the camera means for deriving detection information.

3. A system according to claim 2, wherein the I detection information comprises a nature of the object or abnormality.

4. A system according to claims 2 or 3, further comprising checking means for checking the detection information derived against reference data in a database of the system.

5. A system according to any one of the preceding claims, wherein the scanning means comprises one or more wide angle cameras and the detection means is operable to determine the presence and location of the object or abnormality based on image processing of images captured by the wide angle cameras.

6. A system according to any one of the preceding claims, wherein the camera means comprises one or more zoom cameras.

7. A system according to any one of the preceding claims, capable of automatic, real-time processing.

8. A system according to any one of the preceding claims, comprising one or more of:

i.) a high resolution image of a captured object or abnormality;

ii.) object and/or abnormality position in a geographical co-ordinate system, e.g., latitude and longitude or distance along a track from known reference point;

iii.) object and/or abnormality distance from a scanning platform or some other known rail vehicle;

iv.) object and/or abnormality size, luminous intensity, colour or dimensions, and/or other visual characteristics;

v.) possible object and/or abnormality classification or identification e.g., by matching information from object/rail database(s) or other sources or by using a set of rules or a rule based engine or an expert system.

9. A system according to any one of the preceding claims, comprising one or more image devices for capturing continuous images of track with date/time stamp, latitude and longitude positioning, milestones, vehicle speed, and other parameters for easy retrieval and verification, the images being stitched together to enable a decision-maker to review images.

10. A system according to any one of the preceding claims, operable to compensate or adjust for one or more of varying terrain, curvature, environment, weather and switching track.

11. A system according to any one of the preceding claims, operable to detect and locate a relevant track and associated structures for different viewing angles of an imaging device.

12. A system according to any one of the preceding claims, operable to maintain and/or uses a database of potential foreign objects and/or abnormalities, as well as objects and features that are expected to be found along a track.

13. A system according to any one of the preceding claims, operable to classify a detected object as normal or abnormal based on a set of rules or a rule based engine or an expert system.

14. A system according to any one of the preceding claims, operable to recognise a rail line for defining an image boundary and automatically adjust an area of interest and camera view as the rail track manoeuvres around curved rail track.

15. A system according to any one of the preceding claims, operable to adjust to gradual or even drastic background changes by continually updating background key image parameters.

16. A system according to any one of the preceding claims, operable to adjust to sudden or gradual background changes by comparing a capture image with stored image templates.

17. A system according to any one of the preceding claims, operable to reduce false alarms due to normal foreign objects by adjusting a level of sensitivity.

18. A system according to any one of the preceding claims, operable to reduce false alarms due to normal foreign objects by making use of visual attributes object such as size, perimeter, area, profile, luminous intensity, colour.

19. A system according to any one of the preceding claims, operable to detect non visible physical foreign objects by analysing track bed disturbances.

20. A method of detecting an object or abnormality on or near a rail track, the method comprising:

scanning on and near a portion of the rail track utilising a scanning device; and

determining the presence and location of the object or abnormality on or near the portion of the rail track based on information from the scanning means utilising a detection device coupled to the scanning device.