Video navigation

• US 20090125223A1
• Filed: 03/31/2006
• Published: 05/14/2009
• Est. Priority Date: 03/31/2006
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Higgins, Robert P.
• Granted Patent: US 8,666,661 B2
• Time in Patent Office: Days
• US Class Current: 701/200
• CPC Class Codes: G06T 2207/30181 Earth observation
• 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

Abstract

A system and method for video navigation are disclosed. Motion analysis can be performed upon camera images to determine movement of a vehicle, and consequently present position of the vehicle. Feature points can be identified upon a video image. Movement of the feature points between video frames is indicative of movement of the vehicle. Video navigation can be used, for example, in those instances wherein GPS navigation is unavailable.

Claims

1. A method of navigation, the method comprising performing motion analysis upon information from a video camera.

2. The method of claim 1, wherein performing motion analysis upon information from a video camera comprises analyzing position changes of key features between two images in a video sequence using vehicle and camera information.

3. The method of claim 1, wherein performing motion analysis upon information from a video camera comprises analyzing position changes of key features between two images in a video sequence, and using vehicle attitude, camera focal length, and camera pointing angle to determine distance, heading, and altitude.

4. The method of claim 1, wherein performing motion analysis upon information from a video camera comprises:

identifying a set of feature points in a video image;

determining motion of the feature points by how they are mapped from a first image to a second image; and

using motion of the feature points to determine motion of a vehicle.

5. The method as recited in claim 4, wherein identifying a set of feature points in a video image comprises identifying points where a sum of image gradients in both horizontal and vertical directions exceeds a threshold.

6. The method as recited in claim 4, wherein identifying a set of feature points in a video image comprises dividing the image into a plurality of cells and identifying a feature point in each cell.

7. The method as recited in claim 4, wherein identifying a set of feature points in a video image comprises dividing the image into a grid of approximately 10 by approximately 15 cells and identifying a plurality of points from a corresponding plurality different cells.

8. The method as recited in claim 4, wherein identifying a set of feature points in a video image comprises dividing the image into a plurality of cells and identifying a point from each cell.

9. The method as recited in claim 4, wherein identifying a set of feature points in a video image comprises dividing the image into a plurality of cells and identifying a point from each cell, the point being that point that has the highest gradient within the each cell when that gradient exceeds a threshold.

10. The method as recited in claim 4, wherein determining how the feature points are mapped from a first image to a second image comprises using an optical flow algorithm.

11. The method as recited in claim 4, wherein determining how the feature points are mapped from a first image to a second image comprises using an L-K optical flow algorithm with a multi-resolution pyramid.

12. The method as recited in claim 4, further comprising identifying feature points that are moving with respect to a background of first video image by determining expected positions of the feature points on a second video image based upon position of the feature points in the first video image and based upon predetermined motion of the vehicle.

13. The method of claim 1, further comprising periodically determining position fixes.

14. The method of claim 1, further comprising periodically determining position fixes by comparing images of objects on the ground to objects of stored images, wherein positions of the objects of the stored images known.

15. A method of navigation, the method comprising:

performing motion analysis upon information from a video camera; and

wherein all of the motion analysis is performed via a processor that is collocated with respect to the video camera.

16. A method of navigation, the method comprising:

performing motion analysis upon information from a video camera; and

wherein at least a portion of the motion analysis is performed via a processor that is located remotely with respect to the video camera.