Determination of position from images and associated camera positions

Patent metadata

Field	Value
Publication number	US-10311297-B2
Application number	US-201715434740-A
Country	US
Kind code	B2
Filing date	Feb 16, 2017
Priority date	Sep 28, 2012
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

An apparatus includes an interface configured to receive image data and position data. The image data is associated with a plurality of images of a scene including an object. The position data is associated with positions of a camera that captured the plurality of images. The apparatus further includes a processor configured to identify a corresponding camera position for a first image of the plurality of images and to output an indication of a global position of the object based on first image data corresponding to the first image and based on the corresponding camera position.

First claim

What is claimed is:

1. An apparatus comprising:
an interface configured to receive image data and position data, the image data associated with a plurality of images of a scene including an object, the position data associated with positions of a camera that captured the plurality of images; and
a processor configured to:
identify a camera position corresponding to a first image of the plurality of images;
identify a relative position of the object relative to the camera, the relative position identified based on first image data corresponding to the first image, second image data corresponding to a second image of the plurality of images, and the camera position; and
output an indication of a global position of the object based on the position data and the relative position of the object.

2. The apparatus of claim 1 , wherein the global position of the object is determined without using orientation measurement values corresponding to orientations of the camera during capture of the plurality of images.

3. The apparatus of claim 1 , wherein a first image of the plurality of images has an overlapping field of view with the second image, the overlapping field of view including the object.

4. The apparatus of claim 1 , wherein the positions of the camera correspond to a flight path of an aircraft that includes the camera, and wherein the flight path comprises a curved path with respect to a physical location of the object.

5. The apparatus of claim 1 , wherein, for each image of the plurality of images, the image data includes a corresponding time stamp that indicates a time at which the image was captured.

6. The apparatus of claim 1 , wherein the position data comprises global position data corresponding to the positions of the camera during capture of the plurality of images.

7. The apparatus of claim 1 , wherein, for a position of the camera at a time in which the camera captured the first image, the position data indicates a latitude, longitude, altitude, or a combination thereof.

8. The apparatus of claim 1 , wherein the interface is further configured to receive second image data and second position data, the second image data associated with a second plurality of images of the scene, the second position data associated with positions of a second camera that captured the second plurality of images.

9. The apparatus of claim 8 , wherein the position data corresponds to a first flight path and the second position data corresponds to a second flight path.

10. The apparatus of claim 1 , further comprising:
a memory coupled to the processor and configured to store the image data and the position data; and
a user interface configured to receive an input that identifies the object in a particular image of the plurality of images.

11. The apparatus of claim 1 , further comprising a display device coupled to the processor, wherein the indication of a global position of the object is presented via the display device.

12. A method comprising:
receiving image data associated with a plurality of images of a scene including an object;
receiving position data associated with positions of a camera that captured the plurality of images;
identifying a camera position that corresponds to a first image of the plurality of images, the camera position corresponding to a time the camera captured the first image;
identifying a relative position of the object relative to the camera, the relative position identified based on first image data corresponding to the first image, second image data corresponding to a second image of the plurality of images, and the camera position; and
outputting an indication of a global position of the object based on the position data and the relative position of the object.

13. The method of claim 12 , further comprising receiving a user input designating a target image point in at least one of the images, the target image point corresponding to the object.

14. The method of claim 12 , wherein the position data comprises global position system (GPS) data and time information.

15. The method of claim 12 , further comprising:
detecting a first set of features based on the first image data;
generating a first set of descriptors for the first image based on the first set of features;
detecting a second set of features based on second image data, the second image data corresponding to the second image;
generating a second set of descriptors for the second image based on the second set of features; and
matching the first set of descriptions associated with the first image to the second set of descriptors associated with the second image.

16. The method of claim 15 , wherein a first feature of the first set of features comprises a corner feature.

17. The method of claim 15 , wherein identifying the camera position includes determining an estimated orientation of the camera, the estimated orientation determined independent of measured orientation data and determined based on an optical axis of the camera being aligned with a common object point, the common object point depicted in each image.

18. A system comprising:
a camera configured to generate image data associated with a plurality of images of a scene including an object;
a position receiver configured to generate position data associated with positions of the camera during image capture operations; and
a processor configured to:
identify a camera position corresponding to a first image of the plurality of images;
identify a relative position of the object relative to the camera, the relative position identified based on first image data corresponding to the first image, second image data corresponding to a second image of the plurality of images, and the camera position; and
output an indication of a global position of the object based on the position data and the relative position of the object.

19. The system of claim 18 , further comprising an aircraft that includes the camera and the position receiver.

20. The system of claim 18 , further comprising a clock configured to generate a clock signal, wherein each image of the plurality of images is associated with a corresponding timestamp generated based on the clock signal, and the position data includes, for each position of the positions of the camera, a corresponding time indicator determined based on the clock signal.

Assignees

• 2D3 Ltd
• Boeing Co

Inventors

• Greveson Eric
• Srinivasan James
• Morris Julian

Classifications

• G06T7/73 Primary

  using feature-based methods · CPC title

• G06V30/422

  Technical drawings; Geographical maps · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T2207/10032

  Satellite or aerial image; Remote sensing · CPC title