3D track assessment system and method

• US 10,362,293 B2
• Filed: 05/29/2015
• Issued: 07/23/2019
• Est. Priority Date: 02/20/2015
• Status: Active Grant

• Current Assignee: Tetra Tech Incorporated
• Original Assignee: Tetra Tech Incorporated
• Inventors: Mesher, Darel
• Primary Examiner(s): Philippe, Gims S
• Assistant Examiner(s): Hasan, Mainul
• Application Number:
  US14/725,490
• Publication Number:
  US 20160249040A1
• Time in Patent Office: 1,516 Days
• 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: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30136 Metal
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: H04N 13/189 Recording image signals; Reproducing recorded image signals
• CPC Class Codes: H04N 13/243 using three or more 2D image sensors

Abstract

A 3D track assessment system for identifying and assessing features of a railway track bed based on 3D elevation and intensity data gathered from the railway track bed.

Claims

1. A system for assessing a railway track bed, the system comprising:

a power source;

a light emitting apparatus powered by the power source for emitting light energy toward a railway track;

a data storage apparatus in communication with at least one processor;

at least one sensor for sensing reflected light that was emitted from the light emitting apparatus and acquiring three dimensional surface elevation and intensity image data of the railway track to be stored in the data storage apparatus, wherein the at least one sensor is in communication with the at least one processor; and

wherein the at least one processor is configured to run an algorithm for processing three-dimensional surface elevation and intensity data gathered from the at least one sensor and saved in the data storage apparatus, the algorithm comprising the steps of;

a. acquiring three dimensional surface elevation and intensity data representative of an area segment of railway track bed;

b. generating a track elevation map based on the acquired three dimensional data;

c. identifying a railway track bed feature from the track elevation map further including the steps of;

i. defining an appropriate gradient neighborhood representing a small 2D track section over which differential vertical measurements are calculated and

ii. moving the gradient neighborhood like a sliding window over the 3D elevation data using the processor; and

d. storing information corresponding to the identified railway track bed feature in the data storage apparatus.

2. The system of claim 1 wherein the algorithm step of identifying a railway track bed feature further comprises the step of identifying a rail head edge by detecting significant vertical gradient edges over a two dimensional area wherein such vertical gradient edges are greater than a minimum rail height threshold.

3. The system of claim 2 wherein the algorithm step of identifying a railway track bed feature further comprises the step of identifying a rail base edge by detecting significant vertical gradient edges over a two dimensional area adjacent the detected rail head edge wherein such vertical gradient edges are greater than a minimum rail base height threshold.

4. The system of claim 2 wherein the algorithm further comprises the step of removing data corresponding to the rail head from the elevation map, thereby enhancing the detection of other smaller vertical components of the railway track bed.

5. The system of claim 4 wherein the algorithm step of identifying a railway track bed feature further comprises the step of detecting surfaces with surface normal values greater than a planar region surface normal value threshold and that are proximate to one another by less than a maximum proximity threshold.

6. The system of claim 5 wherein the algorithm step of identifying a railway track bed feature further comprises the step of defining an approximate tie surface plane based on the detected surfaces with surface normal values greater than the planar region surface normal value threshold that are proximate to one another by less than the maximum proximity threshold.

7. The system of claim 6 wherein the algorithm step of identifying a railway track bed feature further comprises the step of assigning a tie bounding box around the perimeter of the tie surface plane based at least on one measured parameter of the tie surface plane.

8. The system of claim 7 wherein the algorithm step of identifying a railway track bed feature further comprises the step of assigning an approximate tie length, an approximate tie width, and an approximate tie skew angle based on the bounding box assigned around the perimeter of the tie surface plane.

9. The system of claim 6 wherein the algorithm step of identifying a railway track bed feature further comprises the step of identifying and measuring surface cracks that are deeper than a minimum crack depth threshold and that are longer than a minimum crack length threshold based on the track elevation map.

10. The system of claim 9 wherein data corresponding to the measured surface cracks are saved to the data storage apparatus on a per tie basis so that the same tie can be re-examined at a later date to determine whether the measured surface cracks have changed.

11. The system of claim 9 wherein the algorithm step of identifying a railway track bed feature further comprises a step of assigning a severity value to each measured crack based on at least the measured length and measured width of the crack.

12. The system of claim 6 wherein the algorithm step of identifying a railway track bed feature further comprises the step of identifying and measuring a surface feature that is higher than a minimum tie height threshold.

13. The system of claim 12 wherein data corresponding to the measured surface feature are saved to the data storage apparatus on a per tie basis so that the same tie can be re-examined at a later date to determine whether the measured surface feature has changed.

14. The system of claim 6 wherein the algorithm step of identifying a railway track bed feature further comprises the step of detecting a broken tie based on an abrupt elevation shift along the tie surface plane.

15. The system of claim 1 wherein the algorithm step of identifying a railway track bed feature further comprises the step of comparing at least a portion of the track elevation map to a plurality of three dimensional features saved in a feature library to determine a best fit between the at least a portion of the track elevation map and the plurality of three dimensional features to properly identify the railway track bed feature.

16. The system of claim 15 wherein the step of comparing further comprises the step of applying a minimum correlation threshold so that a railway track bed feature will not be identified as a particular three dimensional feature from the feature library unless the minimum correlation threshold is met.

17. The system of claim 6 wherein the algorithm step of identifying a railway track bed feature further comprises the step of determining a shoulder ballast volume adjacent a tie based at least in part on the approximate tie surface plane defined for the tie.

18. The system of claim 7 wherein the algorithm step of identifying a railway track bed feature further comprises the step of defining a surface area region adjacent the tie bounding box, measuring the surface elevation of the surface area region, and determining the difference between the surface elevation of the surface area region and the surface elevation of the approximate tie surface plane to determine whether a positive volume or negative volume is present at the surface area region.

19. The system of claim 15 wherein the algorithm step of identifying a railway track bed feature further comprises the step of making a plurality of elevation measurements along and around an identified railway track bed feature and recording the measurements and the locations of the measurements in the data storage apparatus.

20. The system of claim 19 wherein the algorithm step of identifying a railway track bed feature further comprises the step of assigning a condition to the identified railway track bed feature based on the plurality of elevation measurements.

21. The system of claim 1 wherein the algorithm step of identifying a railway track bed feature further comprises the step of measuring the length of a joint bar candidate, determining whether the length of the joint bar candidate falls between a minimum joint bar length threshold and a maximum joint bar length threshold, and identifying the joint bar candidate as a joint bar if the length measurement of the joint bar candidate falls between a minimum joint bar length threshold and a maximum joint bar length threshold.

22. A method of assessing a railway track bed, the method comprising the steps of:

a. defining a three dimensional elevation map based on surface elevation and intensity data representative of an area segment of the railway track bed, the data gathered by a sensor sensing reflected light from a track bed surface;

b. storing the elevation map in a data storage apparatus;

c. identifying a railway track bed feature from the elevation map using a processor, further comprising the sub-steps of;

i. defining an appropriate gradient neighborhood representing a small 2D track section over which differential vertical measurements are calculated and

ii. moving the gradient neighborhood like a sliding window over the 3D elevation data using the processor; and

d. storing information corresponding to the identified railway track bed feature in the data storage apparatus.

23. The method of claim 22 wherein the step of identifying a railway track bed feature further comprises the step of identifying a rail head edge by detecting significant vertical gradient edges over a two dimensional area wherein such vertical gradient edges are greater than a minimum rail height threshold.

24. The method of claim 23 wherein the step of identifying a railway track bed feature further comprises the step of identifying a rail base edge by detecting significant vertical gradient edges over a two dimensional area adjacent the detected rail head edge wherein such vertical gradient edges are greater than a minimum rail base height threshold.

25. The method of claim 24 further comprising the step of removing data corresponding to the rail head from the elevation map, thereby enhancing the detection of other smaller vertical components of the railway track bed.

26. The method of claim 22 wherein the method further comprises the step of detecting surfaces with surface normal values greater than a planar region surface normal value threshold and that are proximate to one another by less than a maximum proximity threshold.

27. The method of claim 26 wherein the method further comprises the step of defining an approximate tie surface plane based on the detected surfaces with surface normal values greater than the planar region surface normal value threshold that are proximate to one another by less than the maximum proximity threshold.

28. The method of claim 27 wherein the method further comprises the step of assigning a tie bounding box around the perimeter of the tie surface plane based at least on one measured parameter of the tie surface plane.

29. The method of claim 28 wherein the method further comprises the step of assigning an approximate tie length, an approximate tie width, and an approximate tie skew angle based on the bounding box assigned around the perimeter of the tie surface plane.

30. The method of claim 29 wherein the method further comprises the step of identifying and measuring surface cracks in an identified tie that are deeper than a minimum crack depth threshold and that are longer than a minimum crack length threshold based on the track elevation map.

31. The method of claim 30 wherein the method further comprises the step of saving data corresponding to the measured surface cracks to the data storage apparatus on a per tie basis so that the same tie can be re-examined at a later date to determine whether the measured surface cracks have changed.

32. The method of claim 31 wherein the method further comprises a step of assigning a severity value to each measured crack based on at least the measured length and measured width of the crack.

33. The method of claim 32 wherein the method further comprises the step of identifying and measuring a surface feature that is higher than a minimum tie height threshold.

34. The method of claim 33 wherein the method further comprises the step of saving data corresponding to the measured surface feature to the data storage apparatus on a per tie basis so that the same tie can be re-examined at a later date to determine whether the measured surface feature has changed.

35. The method of claim 29 wherein the method further comprises the step of detecting a broken tie based on an abrupt elevation shift along the tie surface plane.

36. The method of claim 22 wherein the step of identifying a railway track bed feature further comprises the step of comparing at least a portion of the track elevation map to a plurality of three dimensional features saved in a feature library to determine a best fit to properly identify the railway track bed feature.

37. The method of claim 36 wherein the step of comparing further comprises the step of applying a minimum correlation threshold so that a railway track bed feature will not be identified as a particular three dimensional feature from the feature library unless the minimum correlation threshold is met.

38. The method of claim 29 wherein the method further comprises the step of determining a shoulder ballast volume adjacent a tie based at least in part on the approximate tie surface plane defined for the tie.

39. The method of claim 29 wherein the method further comprises the step of defining a surface area region adjacent the tie bounding box, measuring the surface elevation of the surface area region, and determining the difference between the surface elevation of the surface area region and the surface elevation of the approximate tie surface plane to determine whether a positive volume or negative volume is present at the surface area region.

40. The method of claim 36 wherein the method further comprises the step of making a plurality of elevation measurements along and around an identified railway track bed feature and recording the measurements and the locations of the measurements in the data storage apparatus.

41. The method of claim 40 wherein the method further comprises the step of assigning a condition to the identified railway track bed feature based on the plurality of elevation measurements.

42. The method of claim 22 wherein the step of identifying a railway track bed feature further comprises the step of measuring the length of a joint bar candidate, determining whether the length of the joint bar candidate falls between a minimum joint bar length threshold and a maximum joint bar length threshold, and identifying the joint bar candidate as a joint bar if the length measurement of the joint bar candidate falls between a minimum joint bar length threshold and a maximum joint bar length threshold.

43. The method of claim 22 further comprising the step of calculating ballast volume using the processor by performing the sub-steps of:

(i) calculating an approximate track bed surface plane;

(ii) referencing ballast volumes to the approximate track bed surface plane; and

(iii) calculating the volume for a plurality of ballast zones.