METHOD AND APPARATUS FOR DETERMINING A VEHICLE EGO-POSITION

• US 20170016740A1
• Filed: 07/16/2015
• Published: 01/19/2017
• Est. Priority Date: 07/16/2015
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Herman, David A., MacNEILLE, Perry Robinson, MAKKE, Omar, CUI, Dehua, GUSIKHIN, Oleg Yurievitch, KOWALSKI, David Allen
• Granted Patent: US 11,125,566 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

A system includes a processor configured to receive image data gathered by a vehicle camera, relating to a fixed environmental feature. The processor is also configured to determine a vehicle position relative to the fixed environmental feature and determine a vehicle lane-level location on a digital map, based on the vehicle position relative to the fixed environmental feature.

Claims

1. A system comprising:

a processor configured to;

receive image data gathered by a vehicle camera, relating to a fixed environmental feature;

determine a real-world vehicle position relative to the fixed environmental feature; and

determine a vehicle lane-level road location on a digital map, including the environmental feature, based on the real-world vehicle position relative to the fixed environmental feature, transitioned on to the digital map.

2. The system of claim 1, wherein the processor is configured to determine a distance between a vehicle and the fixed environmental feature based at least in part on actual feature size compared to viewed feature size in the image data.

3. The system of claim 2, wherein the actual feature size is obtained from the digital map.

4. The system of claim 1, wherein the processor is configured to determine a distance between a vehicle and the fixed environmental feature based at least in part on angular resolution of the vehicle camera.

5. The system of claim 1, wherein the processor is configured to determine a distance between a vehicle and the fixed environmental feature based at least in part on actual size and location of elements of the fixed environmental feature, and a relative viewed-angle in the image data between these elements.

6. The system of claim 5, wherein the processor is configured to determine a vehicle lane-location on the digital map based on a comparison of different viewed-angles, one to the left and one to the right of a vehicle in the image data, between elements of the fixed environmental feature.

7. The system of claim 1, wherein the processor is further configured to extract lane-markings from the image data and utilize the lane markings to determine if a vehicle changes lanes following the determination of the lane-level location.

8. The system of claim 1, wherein the determination of the vehicle position relative to the vehicle feature includes determination of a distance between the vehicle and the feature, a vehicle orientation and an offset angle between a vehicle heading and the feature.

9. A computer-implemented method comprising:

determining geometric characteristics of a fixed geographic object in an image captured by a vehicle camera;

determining a real-world vehicle location, relative to the fixed geographic object, based on the geometric characteristics; and

determining a vehicle lane-level road location on a digital map, including the geographic object, based on the real-world vehicle location relative to the fixed geographic object, transitioned on to the digital map.

10. The method of claim 9, wherein the geometric characteristics include an angle between a vehicle heading and the fixed geographic object.

11. The method of claim 9, wherein the geometric characteristics include a distance to the fixed geographic object, based at least in part on the angle between the vehicle heading and the fixed geographic object.

12. The method of claim 9, wherein the geometric characteristics include an angle between two elements of the fixed geographic object, wherein the geographic location of each of the two elements is obtainable from a digital map.

13. The method of claim 9, wherein the geometric characteristics include a scale of the fixed geographic object, based on a known height of the fixed geographic object compared to a viewed height in the image.

14. The method of claim 13, wherein the geometric characteristics include a distance to the fixed geographic object, based at least in part on the scale of the fixed geographic object.

15. The method of claim 9, further comprising determining geometric characteristics of a plurality of fixed geographic objects, on either side of a vehicle location in an image, and determining the vehicle location based at least in part on a comparison of the determined geometric characteristics of the plurality of fixed geographic objects.

16. The method of claim 15, wherein the determining geometric characteristics includes determining a viewed-angle between a first and second object to the left of the vehicle location, and between a third and fourth object to the right of the vehicle location, the geographic location of all four objects obtainable from a digital map.

17. A system comprising:

a vehicle-embedded camera, configured to capture images relative to a vehicle location; and

a processor configured to;

identify fixed geographic objects in the captured images;

determine a real-world relative distance and angle from one or more of the fixed geographic objects to a vehicle location based on comparison of viewed geometric characteristics of the fixed geographic objects to actual geometric characteristics obtained from a digital map; and

determine a vehicle lane-level road location on the digital map based on the real-world relative distance and angle, transitioned on to the digital map.

18. The system of claim 17, wherein the processor is configured to identify lane markings in the captured image and to associate a line of lane markings to the left or right of the vehicle with a current vehicle lane, based on the lane-level location.

19. The system of claim 18, wherein the processor is configured to determine that the line of lane markings is passing under a vehicle in a series of images in a direction from a first vehicle side to a second vehicle side.

20. The system of claim 19, wherein the processor is configured to determine a new lane level location as one lane over from a previous lane level location, in the direction of the first vehicle side.