Determining geographic position information from a single image

• US 8,854,453 B2
• Filed: 06/23/2009
• Issued: 10/07/2014
• Est. Priority Date: 06/23/2009
• Status: Active Grant

• Current Assignee: HERE Global B.V. (HERE Holding Corporation)
• Original Assignee: HERE Global B.V. (HERE Holding Corporation)
• Inventors: Chen, Xin, Yang, Xiangheng, Hui, Roger B., Alwar, Narayanan
• Primary Examiner(s): Kim, Hee-Yong
• Application Number:
  US12/489,737
• Publication Number:
  US 20100321489A1
• Time in Patent Office: 1,932 Days
• Field of Search: 348/116
• US Class Current: 348/118
• CPC Class Codes: G01C 11/02 Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
• CPC Class Codes: G01C 21/32 Structuring or formatting of map data
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves

Abstract

Systems, devices, features, and methods for determining geographic position information from an image are disclosed. For example, one method for determining the geographic position information is used to develop a navigation database. The method comprises capturing a plurality of images of geographic features by a camera mounted on a vehicle or a pedestrian. A single image from the plurality of images is identified or selected. A real-world ground distance between a reference ground point in the single image and a ground point corresponding to an object in the single image is determined based on determined calibration values corresponding to the camera. Real-world geographic position information, such as a latitude coordinate and a longitude coordinate, of the ground point corresponding to the object in the single image is determined based on the determined real-world ground distance.

Claims

1. A method of determining real-world geographic position information of an object from an image, wherein the image is collected to develop a navigation database, the method comprising:

capturing a plurality of images of geographic features, the plurality of images captured by a camera mounted on a vehicle;

identifying a single image from the plurality of images;

calculating a vanishing point in the single image as an intersection of lines in the single image;

determining a real-world ground distance between a reference ground point in the single image and a ground point corresponding to an object in the single image, wherein determination of the real-world ground distance is based on the vanishing point in the single image and calibration values corresponding to the camera, wherein no images other than the single image are used in determining the real-world ground distance; and

determining real-world geographic position information of the ground point corresponding to the object in the single image based on the determined real-world ground distance, the determined real-world geographic position information including a latitude coordinate and a longitude coordinate.

2. The method of claim 1, wherein the reference ground point represented in the single image corresponds to a point with a predetermined constant position relative to the vehicle.

3. The method of claim 2, wherein a center point at the bottom edge of the single image corresponds to the reference ground point.

4. The method of claim 1, wherein the object comprises a road sign or a road marking.

5. The method of claim 1, further comprising:

determining an altitude coordinate corresponding to the object based on the single image.

6. The method of claim 5, wherein determining the altitude coordinate includes incrementally comparing a height in a three-dimensional ground coordinate system to the single image.

7. The method of claim 1, wherein the determined calibration values include a focal length of the camera and a camera roll angle.

8. The method of claim 1, further comprising:

storing the determined real-world geographic position information in the navigation database.

9. The method of claim 1, wherein the determined calibration values are based on a projection of a three-dimensional ground coordinate system from an image plane.

10. The method of claim 1, wherein determining the real-world ground distance comprises entering the determined calibration values into mathematical models representing the reference ground point and the ground point corresponding to an object in a three-dimensional ground coordinate system, the three-dimensional ground coordinate system generated as a function of an image plane.

11. The method of claim 1, wherein determining the real-world geographic position information of the ground point corresponding to the object comprises using the determined real-world ground distance with a bearing of the object to calculate the latitude coordinate and the longitude coordinate.

12. A method of determining a geographic location in an image, the method comprising:

determining calibration values relating to a camera, wherein the camera captures an image at the determined calibration values;

calculating a vanishing point in the image;

identifying a reference point in the image, the reference point corresponding to a predetermined position relative to the camera;

identifying a selected point in the image, the selected point corresponding to a real-world location represented in the image;

determining a real-world distance between the reference point and the selected point represented in the image, wherein the determination of the real-world distance is based on the calibration values and the vanishing point in the image; and

determining real-world geographic coordinates corresponding to the selected point based on the determined real-world distance,

wherein the real-world distance is determined using no images other than the image corresponding to the vanishing point, the reference point and the selected point.

13. The method of claim 12, wherein the selected point corresponds to a road feature in the image.

14. The method of claim 12, wherein the determined calibration values include an intrinsic value of the camera and an extrinsic value of the camera.

15. The method of claim 12, wherein the real-world geographic coordinates are determined based on the determined real-world distance and a bearing corresponding to the selected point in the image.

16. The method of claim 12, wherein the camera is mounted on a vehicle that collects images to develop a master navigation database.

17. A non-transitory computer-readable medium configured to store a computer program that performs a method of determining a real-world geographic position from a single image, the method comprising:

identifying a calibration value associated with a camera, the identified calibration value including a determined extrinsic value of the camera at a the time an image was captured;

computing a vanishing point in the image as an intersection point between two parallel lines in the image;

computing a reference ground point based on an intrinsic parameter of the camera at the time the image was captured and at least the vanishing point in the image;

determining a real-world distance between a desired ground point represented in the image and the reference ground point in the image using the identified calibration value and the single image; and

calculating a latitude coordinate and a longitude coordinate associated with the desired ground point as a function of the determined real-world distance.

18. The non-transitory computer-readable medium of claim 17, wherein the determined extrinsic value comprises a camera roll angle.

19. The non-transitory computer-readable medium of claim 17, wherein the intrinsic parameter of the camera includes a focal length.

20. A device for determining a real-world geographic position from a single image, the device comprising:

a user interface configured to display images captured by a camera;

a processor in communication with the user interface and configured to calculate a vanishing point in an image; and

a memory in communication with the processor, the memory configured to store data of the images and data of predetermined calibration values of the camera,

wherein the image is displayed on the user interface, wherein the processor is configured to determine a real-world distance between a reference point corresponding to a known ground location and a selected target point corresponding to another ground location in the displayed image based on the predetermined calibration values and the calculated vanishing point in the image, and wherein the processor is further configured to determine real-world geographic coordinates of the selected target point in the image based on the real-world distance.