Method for estimating a roadway course and method for controlling a light emission of at least one headlight of a vehicle

• US 9,376,052 B2
• Filed: 07/03/2012
• Issued: 06/28/2016
• Est. Priority Date: 08/23/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Faber, Petko, Foltin, Johannes, Schwarzenberg, Gregor
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): GOLDMAN, RICHARD A
• Application Number:
  US14/240,472
• Publication Number:
  US 20140249715A1
• Time in Patent Office: 1,456 Days
• Field of Search: 382/104, 382/103, 382/190, 382/195, 382/199, 701/301, 701/1, 701/23, 701/28, 701/27, 701/300, 701/523
• US Class Current: 1/1
• CPC Class Codes: B60Q 1/085 due to special conditions, e.g. adverse weather, type of road, badly illuminated road signs or potential dangers B60Q1/10, B60Q1/12, B60Q1/1423 take precedence
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• 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 method for estimating a roadway course in a roadway section ahead of a vehicle in the direction of travel is provided. The method includes recognizing at least one reflective or self-luminous object in an image of the roadway section. The method also includes ascertaining a position of the at least one object based on the image of the roadway section. The method also includes estimating the roadway course using the ascertained position of the at least one object.

Claims

1. A method for estimating a roadway course in a roadway section ahead of a vehicle as the vehicle is moving in the direction of travel, the method comprising:

recognizing, by a computer processor, at least one reflective or self-luminous object in an image of the roadway section;

ascertaining, by a computer processor, a change over time of a position of the at least one object based on the image of the roadway section, the ascertaining including evaluating a trace of a movement of the at least one object in the image taken by a camera according to a long-term exposure; and

estimating, by a computer processor, the roadway course using the ascertained position of the at least one object.

2. The method of claim 1, wherein a plurality of reflective or self-luminous objects in the image of the roadway section is recognized in the recognizing operation, positions of the plurality of objects are ascertained, based on the image of the roadway section, in the ascertaining, and the roadway course is estimated, using the ascertained positions of the plurality of objects.

3. The method of claim 1, wherein the at least one object in a plurality of images of the roadway section is recognized in the recognizing operation, a change over time of a position of the at least one object is ascertained, based on the plurality of images of the roadway section, in the ascertaining, and the roadway course is estimated, using the ascertained change over time of the position of the at least one object, in the estimating.

4. The method of claim 1, further comprising:

combining the estimated roadway course with at least one of travel data and position data of the vehicle to generate a plausibility-checked roadway course.

5. The method of claim 1, further comprising:

combining the estimated roadway course with a detected course of a lane marking of the roadway section to generate a plausibility-checked roadway course.

6. The method of claim 1, further comprising:

determining an object type of the at least one object using at least one of the at least one recognized object and the ascertained position of the at least one object based on the image of the roadway section, the roadway course being additionally estimated using the determined object type in the estimating.

7. A method for controlling a light emission of at least one headlight of a vehicle as the vehicle moves along the direction of travel, the method comprising:

estimating, by a computer processor, a roadway course in a roadway section ahead of the vehicle in the direction of travel by performing the following;

recognizing, by a computer processor, at least one reflective or self-luminous object in an image of the roadway section;

ascertaining, by a computer processor, a change over time of a position of the at least one object based on the image of the roadway section, the ascertaining including evaluating a trace of a movement of the at least one object in the image taken by a camera according to a long-term exposure; and

estimating, by a computer processor, the roadway course using the ascertained position of the at least one object; and

generating, by a computer processor, an actuating signal for controlling the light emission of the at least one headlight, using the estimated roadway course.

8. A device for estimating a roadway course in a roadway section ahead of a vehicle in the direction of travel, comprising:

a recognizing arrangement to recognize at least one reflective or self-luminous object in an image of the roadway section;

an ascertaining arrangement to ascertain a change over time of a position of the at least one object based on the image of the roadway section, the ascertaining including evaluating a trace of a movement of the at least one object in the image taken by a camera according to a long-term exposure; and

an estimating arrangement to estimate the roadway course using the ascertained position of the at least one object.

9. A non-transitory computer readable medium having a computer program, which is executable by a processor, comprising:

a program code arrangement having program code for estimating a roadway course in a roadway section ahead of a vehicle as the vehicle is moving in the direction of travel, by performing the following;

recognizing at least one reflective or self-luminous object in an image of the roadway section;

ascertaining a change over time of a position of the at least one object based on the image of the roadway section, the ascertaining including evaluating a trace of a movement of the at least one object in the image taken by a camera according to a long-term exposure; and

estimating the roadway course using the ascertained position of the at least one object.