OBJECT DETECTION USING COOPERATIVE SENSORS AND VIDEO TRIANGULATION

• US 20080279421A1
• Filed: 05/09/2007
• Published: 11/13/2008
• Est. Priority Date: 05/09/2007
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Hamza, Rida M., Blaser, Robert A.
• Granted Patent: US 8,260,036 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: B64G 1/646 Docking or rendezvous systems refuelling in space B64G1/4024
• CPC Class Codes: B64G 1/6462 characterised by the means for engaging other vehicles
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06T 7/285 using a sequence of stereo image pairs
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image

Abstract

Methods and apparatus are provided for detecting and tracking a target. Images are captured from a field of view by at least two cameras mounted on one or more platforms. These images are analyzed to identify landmarks with the images which can be used to track the targets position from frame to frame. The images are fused (merged) with information about the target or platform position from at least one sensor to detect and track the target. The targets position with respect to the position of the platform is displayed or the position of the platform relative to the target is displayed.

Claims

1. A method for detecting and tracking a target comprising:

capturing an image of a field of view from at least two cameras mounted on one or more platforms;

identifying landmarks within the images;

merging the images to detect the target;

comparing information about the target from at least one sensor; and

displaying the target location with respect to the position of the platform.

2. The method of claim 1, which includes the steps of predicting the next position of the target prior to capturing a next image of the field of view.

3. The method of claim 2, wherein the predicting is performed via a Kalman filter.

4. The method of claim 1, wherein the at least one sensor is selected from the group of:

absolute and relative position, absolute and relative attitude, acceleration, velocity, altitude or absolute and relative navigation information.

5. The method of claim 1, wherein the at least one sensor provides synthetic vision information from a synthetic vision database.

6. The method of claim 1, which includes the step of initializing camera position using inertia sensors.

7. The method of claim 1, which includes the step of displaying the platform location with respect to the target.

8. The method of claim 1, which includes the step of illuminating the field of vision with a structured light source prior to capturing the images.

9. The method of claim 8, wherein the structured light source produces a lighting pattern.

10. The method of claim 1, which includes the step of processing information about the platform from a second Kalman filter in the event of failure of the at least one sensor.

11. The method of claim 1, where the process iterates the estimation of the target position and the platform position.

12. The method of claim 11, where an updated estimate of the target with respect of the moving platform is estimated from a pre-estimate of the platform position using video triangulation, feature extraction and a Kalman filter process.

13. The method of claim 11, where an updated estimate of the moving platform position is estimated from a pre-estimate of the target position using an inverse process of the perspective orientation and a Kalman filter process.

14. A method for detecting and tracking a target comprising:

capturing an image of a field of view from at least two cameras mounted on a platform;

identifying landmarks within the images;

merging the images to detect the target;

comparing information about the target from at least one sensor; and

displaying the platform location with respect to the position of the target.

15. The method of claim 14, which includes the steps of predicting the next position of the target prior to capturing a next image of the field of view.

16. The method of claim 15, wherein the predicting is performed via a Kalman filter.

17. The method of claim 14, wherein the at least one sensor provides global positioning information.

18. The method of claim 14, wherein the at least one sensor provides synthetic vision information from a synthetic vision database.

19. The method of claim 14, which includes the step of initializing camera position using inertia sensors.

20. The method of claim 14, which includes the step of displaying the target location with respect to the platform.

21. The method of claim 14, which includes the step of illuminating the field of vision with a structured light source prior to capturing the images.

22. The method of claim 21, wherein the structured light source produces a lighting pattern.

23. The method of claim 14, which includes the step of processing information about the platform from a second Kalman filter in the event of failure of the at least one sensor.

24. The method of claim 14, where the process iterates the estimation of the target position and the platform position.

25. A method for detecting and tracking a target comprising:

capturing an image of a field of view from three cameras mounted on a platform;

identifying landmarks within the images utilizing a scale invariant feature process;

merging the images to detect the target using a Kalman filter video triangulation process;

comparing information about the target from at least one inertial sensor; and

displaying the platform location with respect to the position of the target or the target location with respect to the position of the platform.

26. A system for detecting and tracking a target comprising:

at least two cameras mounted on a platform;

a scale invariant feature processor capable of identifying landmarks within images captured by the cameras;

a Kalman filter video triangulation processor capable of merging the images to detect the target;

a comparator for comparing information about the target from at least one sensor; and

a display device for displaying the target location with respect to the position of the platform or the platform location with respect to the position of the target.

27. The system of claim 26, wherein the Kalman filter video triangulatin processor is capable of predicting the next position of the target prior to the cameras capturing a next image of the field of view.

28. The system of claim 26, wherein the at least one sensor comprises a global positioning system.

29. The system of claim 26, wherein the at least one sensor comprises a synthetic vision information from a synthetic vision database.

30. The system of claim 26, which includes a light source for illuminating the field of vision with structured light prior to capturing the images.

31. The system of claim 26, which a second Kalman filter for use in the event of failure of the at least one sensor.