System and method for component detection

• US 9,536,311 B2
• Filed: 09/29/2014
• Issued: 01/03/2017
• Est. Priority Date: 09/29/2014
• Status: Active Grant

• Current Assignee: Westinghouse Air Brake Technologies Corporation
• Original Assignee: General Electric Company
• Inventors: Song, Guiju, Theurer, Charles Burton, Tian, Tai-Peng, Kannan, Balajee, Jain, Arpit
• Primary Examiner(s): Chawan, Sheela C
• Application Number:
  US14/500,352
• Publication Number:
  US 20160093054A1
• Time in Patent Office: 827 Days
• Field of Search: 382/106, 382/104, 382/154, 382/195, 382/225, 382/141, 736/36, 348/148, 348/158, 348/241, 348/222, 250/559.29, 250/559.38, 703/1
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/446 using Haar-like filters, e.g. using integral image techniques
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A method and system that include an imaging device configured to capture image data of the vehicle. The vehicle includes one or more components of interest. The method and system include a memory device configured to store an image detection algorithm based on one or more image templates corresponding to the one or more components of interest. The method and system also includes an image processing unit operably coupled to the imaging device in the memory device. The image processing unit is configured to determine one or more shapes of interest of the image data using the image detection algorithm that correspond to the one or more components of interest, and determine one or more locations of the one or more shapes of interest respective to the vehicle.

Claims

1. A component identification system comprising:

an imaging device configured to capture image data of a vehicle, wherein the vehicle includes one or more components of interest;

an image processing unit operably coupled to the imaging device, the image processing unit configured to;

determine one or more shapes of interest of the image data that corresponds to the one or more components of interest; and

determine one or more locations of the one or more shapes of interest respective to the vehicle, wherein the image data includes three dimensional (3D) point cloud information and two dimensional (2D) imaging information of the vehicle;

a memory device that includes one or more identification images corresponding to identification information positioned on an outer surface of the vehicle, wherein the determine the one or more shapes of interest operation is based on one or more image templates corresponding to the identification information; and

a communication device configured to receive identification information from the vehicle wirelesslv, the identification information includes at least one of a manufacturer of the vehicle or a description of one or more components of interest on the vehicle,

wherein the image processing unit determines one or more shapes of interest of the image data that corresponds to the one or more components of interest with an object detection algorithm that is trained using ate least one of the one or more image templates.

2. The component identification system of claim 1, wherein the one or more image templates is based on the identification information.

3. The component identification system of claim 1, wherein the one or more image templates include at least one of shape information, location information relative to the vehicle, or dimension information of the one or more components of interest.

4. The component identification system of claim 1, wherein the image processing unit is configured to determine an orientation of the one or more shapes of interest relative to the vehicle.

5. The component identification system of claim 1, wherein the one or more components of interest is at least one of a wheel, a brake pad, a brake rod, or a coupling mechanism configured to couple the vehicle to another vehicle.

6. The component identification system of claim 1, wherein the vehicle is a part of a rail vehicle system.

7. The component identification system of claim 1, wherein the image processing unit is configured to communicate the one or more locations to a remote location.

8. The component identification system of claim 1, wherein the object detection algorithm is a Viola-Jones algorithm.

9. The component identification system of claim 1, wherein the object detection algorithm is an Adaptive Boosting or AdaBoost learning algorithm.

10. The component identification system of claim 1, wherein the object detection algorithm constructs one or more classifiers from at least one of the one or more image templates.

11. The component identification system of claim 10, wherein the classifiers are based on Haar feature values from the at least one of the one or more image templates.

12. The component identification system of claim 11, wherein the classifiers are based on Histogram of Oriented Gradients from the at least one of the one or more image templates.

13. The component identification system of claim 11, wherein the classifiers are based on Local Binary Patterns from the at least one of the one or more image templates.

14. The component identification system of claim 10, wherein the classifiers are based on Histogram of Oriented Gradients from the at least one of the one or more image templates.

15. The component identification system of claim 14, wherein the classifiers are based on Local Binary Patterns from the at least one of the one or more image templates.

16. The component identification system of claim 10 wherein the classifiers are based on Local Binary Patterns from the at least one of the one or more image templates.