Online sensor calibration verification system

• US 10,165,265 B2
• Filed: 09/29/2015
• Issued: 12/25/2018
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Sikorsky Aircraft Corporation (Martin Marietta Corporation)
• Original Assignee: Sikorsky Aircraft Corporation (Martin Marietta Corporation)
• Inventors: Derenick, Jason C., Ding, Xuchu, Zhang, Shuo, Cherepinsky, Igor, Leland, Joshua M., Stathis, Christopher
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US15/328,782
• Publication Number:
  US 20170223346A1
• Time in Patent Office: 1,183 Days
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: B64U 10/13 Flying platforms
• CPC Class Codes: B64U 2101/30 for imaging, photography or videography
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

An online sensor calibration verification system includes at least one sensor configured to extract a calibration feature included in a field of view of the sensor. The online sensor calibration verification system further includes an electronic calibration verification module configured to determine a static reference feature model, and to verify a calibration of the at least one sensor based on a positional relationship between an extracted calibration feature and the static reference feature model.

Claims

1. An online sensor calibration verification system, comprising:

at least one sensor configured to extract a calibration feature formed on a portion of an unmanned vehicle included in a field of view of the sensor; and

an electronic calibration verification module configured to determine a static reference feature model, and to verify a calibration of the at least one sensor based on a comparison between a positional relationship between an extracted calibration feature and the static reference feature model and a threshold value.

2. The system of claim 1, wherein the electronic calibration verification module determines the at least one sensor is calibrated when the positional relationship between the extracted calibration feature and the static reference feature model is less than the threshold value, and wherein the electronic calibration verification module determines the at least one sensor is uncalibrated when the positional relationship between the extracted calibration feature and the static reference feature model is greater than the threshold value.

3. The system of claim 2, wherein the calibration feature is at least one feature selected from a group comprising a component part number, surface features, geometric vehicle structures, and a matrix bar code, and wherein the sensor is a camera.

4. The system of claim 3, wherein the calibration feature is continuously extracted without interruption.

5. The system of claim 3, wherein the calibration feature is periodically extracted according to a predetermined time period.

6. The system of claim 1, further comprising:

an electronic world model unit operable to generate a model of an environment surrounding the unmanned vehicle in signal communication with the at least one sensor, the electronic world model unit configured to selectively input at least one measured data value output from the at least one sensor to generate a world model that controls the unmanned vehicle.

7. The system of claim 6, wherein the electronic world model unit is in signal communication with the electronic calibration verification module, and wherein the electronic world model unit incorporates the at least one measured data value into the world model in response to the electronic calibration verification module determining the at least one sensor is calibrated.

8. The system of claim 7, wherein the electronic world model excludes the at least one measured data value from the world model in response to the electronic calibration verification module determining the at least one sensor is uncalibrated.

9. A method of verifying calibration of an online sensor, the method comprising:

extracting a calibration feature included in a field of view of at least one sensor;

determining a static reference feature model;

determining a positional relationship between the extracted calibration feature and the static reference feature model; and

verifying a calibration of the at least one sensor by comparing the positional relationship to a threshold value.

10. The method of claim 9, further comprising determining the at least one sensor is calibrated when the positional relationship between the extracted calibration feature and the static reference feature model is less than the threshold value, and determining the at least one sensor is uncalibrated when the positional relationship between the extracted calibration feature and the static reference feature model is greater than the threshold value.

11. The method of claim 10, further comprising extracting the calibration feature continuously without interruption.

12. The method of claim 10, further comprising extracting the calibration feature periodically according to a predetermined time period.

13. The method of claim 9, further comprising selectively processing at least one measured data value output from the at least one sensor to generate a world model of an environment surrounding the unmanned vehicle that controls an unmanned vehicle.

14. The method of claim 13, further comprising incorporating the at least one measured data value into the world model in response to the electronic calibration verification module determining the at least one sensor is calibrated.

15. The method of claim 14, further comprising excluding the at least one measured data value from the world model in response to the electronic calibration verification module determining the at least one sensor is uncalibrated.