Navigation system and method of determining a vehicle position

• US 9,797,733 B2
• Filed: 04/10/2013
• Issued: 10/24/2017
• Est. Priority Date: 04/10/2013
• Status: Active Grant

• Current Assignee: Harman Becker Automotive Systems GmbH (Samsung Group)
• Original Assignee: Harman Becker Automotive Systems GmbH (Samsung Group)
• Inventors: Strassenburg-Kleciak, Marek
• Primary Examiner(s): Holloway, Jason
• Application Number:
  US14/650,562
• Publication Number:
  US 20160097644A1
• Time in Patent Office: 1,658 Days
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01C 21/3658 Lane guidance
• CPC Class Codes: G01C 21/3811 Point data, e.g. Point of Interest [POI]
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• 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

Navigation system and method of determining a vehicle position A navigation system comprises an image sensor configured to capture image data. A map database comprises street lighting data which includes, for a plurality of street lights (41), position data indicating a position (31) at which a street light (41) is installed and height data indicating a height (34) at which a light source (42) of the street light (41) is located. A processing device is configured to refine a position estimate by analyzing the image data using the street lighting data.

Claims

1. A navigation system, comprising:

an image sensor configured to capture image data;

a map database comprising street lighting data that includes, for a plurality of street lights, position data indicating a position at which a street light is installed and height data indicating a height at which a light source of the street light is located; and

a processing device coupled to the map database and the image sensor, the processing device configured to;

identify a portion of the image data located above a horizon line;

refine a position estimate by analyzing the portion of the image data in view of the street lighting data;

compute a light pattern above the horizon line based on the street lighting data; and

compare the computed light pattern with the portion of the image data located above the horizon line,

wherein computing the light pattern comprises computing the light pattern as a function of a point of view and varying the point of view based on a comparison of the computed light pattern and the portion of the image data located above the horizon line to refine the position estimate.

2. The navigation system of claim 1, wherein the processing device is configured to vary the point of view to increase an image similarity measure of the computed light pattern and the portion of the image data located above the horizon line.

3. The navigation system of claim 1, wherein the processing device is configured to limit an object recognition procedure to the portion of the image data located above the horizon line to refine the position estimate.

4. The navigation system of claim 1, wherein the street lighting data comprises type data indicating a light pattern shape emitted by the street light.

5. The navigation system of claim 4, wherein the type data comprises an indicator that is selected from a group comprising an indicator for a sphere-shaped light emission pattern, an indicator for a downwardly directed light emission pattern, an indicator for an upwardly directed light emission pattern, and an indicator for a laterally directed light emission pattern.

6. The navigation system of claim 1, wherein the street lighting data comprises, for at least a sub-set of the plurality of street lights, offset data indicating an offset between the light source and a base of the street light.

7. The navigation system of claim 1, further comprising a position sensor configured to determine the position estimate, wherein the processing device is coupled to the position sensor and configured to refine the position estimate based on the image data and a portion of the street lighting data that is selected based on the position estimate.

8. The navigation system of claim 1, wherein the processing device is configured to control a driver assistance function as a function of the refined position estimate.

9. The navigation system of claim 8, wherein the processing device is configured to determine on which lane of a road a vehicle is located by analyzing the image data in view of the street lighting data and to control the driver assistance function as a function of the determined lane.

10. A vehicle, comprising:

a navigation system that includes;

an image sensor configured to capture image data,

a map database comprising street lighting data that includes, for a plurality of street lights, position data indicating a position at which a street light is installed and height data indicating a height at which a light source of the street light is located, and

a processing device coupled to the map database and the image sensor, the processing device configured to;

identify a portion of the image data located above a horizon line;

refine a position estimate by analyzing the portion of the image data in view of the street lighting data;

compute a light pattern above the horizon line based on the street lighting data; and

compare the computed light pattern with the portion of the image data located above the horizon line,

wherein computing the light pattern comprises computing the light pattern as a function of a point of view and varying the point of view based on a comparison of the computed light pattern and the portion of the image data located above the horizon line to refine the position estimate.

11. A method of determining a vehicle position, comprising:

capturing image data via an image sensor installed in a vehicle;

retrieving street lighting data from a map database, wherein the street lighting data includes, for a plurality of street lights, position data indicating a position at which a street light is installed, and height data indicating a height at which a light source of the street light is located;

identifying a portion of the image data located above a horizon line;

refining a position estimate by analyzing the portion of the image data in view of the street lighting data;

computing a light pattern above the horizon line based on the street lighting data; and

compare the computed light pattern with the portion of the image data located above the horizon line, wherein computing the light pattern comprises computing the light pattern as a function of a point of view and varying the point of view based on a comparison of the computed light pattern and the portion of the image data located above the horizon line to refine the position estimate.

12. The method of claim 11, wherein varying the point of view comprises increasing an image similarity measure of the computed light pattern and the portion of the image data located above the horizon line.

13. The method of claim 11, wherein the street lighting data includes type data indicating a light pattern shape emitted by the street light.

14. The method of claim 13, wherein the type data includes an indicator selected from a group comprising an indicator for a sphere-shaped light emission pattern, an indicator for a downwardly directed light emission pattern, an indicator for an upwardly directed light emission pattern, and an indicator for a laterally directed light emission pattern.