Method for detecting a roadway and corresponding detection systems

• US 9,555,812 B2
• Filed: 06/19/2015
• Issued: 01/31/2017
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Parchami, Marzieh Asadeh
• Primary Examiner(s): NGUYEN, TAN QUANG
• Application Number:
  US14/744,678
• Publication Number:
  US 20150367855A1
• Time in Patent Office: 592 Days
• Field of Search: 701/36, 701/1, 348/149
• US Class Current: 1/1
• CPC Class Codes: B60T 2210/12 Friction
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2520/26 Wheel slip
• CPC Class Codes: B60W 2552/05 Type of road, e.g. motorways, local streets, paved or unpaved roads
• CPC Class Codes: B60W 2552/40 Coefficient of friction
• CPC Class Codes: B60W 2720/26 Wheel slip
• CPC Class Codes: B60W 40/068 Road friction coefficient
• CPC Class Codes: G01N 2021/1765 Method using an image detector and processing of image signal
• CPC Class Codes: G01N 2021/551 Retroreflectance
• CPC Class Codes: G01N 21/55 Specular reflectivity
• CPC Class Codes: G01S 17/46 Indirect determination of position data
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• 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 is provided for detecting a roadway of a vehicle including at least the following steps: generating a light signal and emitting the light signal onto a lit area of the roadway, receiving retroreflected radiation of the lit area and generating an image signal, evaluating the image signal. For this purpose, it is provided that the light signal having light structures is generated, the image signal is evaluated as a two-dimensional light pattern, a detection of pattern characteristics corresponding to the light structures being carried out in the light pattern during the evaluation of the image signals, a signal strength of the image pattern being evaluated in a space-resolved manner and a reflecting behavior of the lit area being inferred therefrom, and a roadway surface being inferred from the reflecting behavior.

Claims

1. A method for detecting a roadway of a vehicle, comprising:

generating a light signal having light structures;

emitting the light signal onto the roadway;

receiving reflected radiation of the light signal off at least the roadway;

generating a light pattern as a function of the received reflected radiation;

evaluating the light pattern;

during the evaluating, detecting pattern characteristics of the light pattern that correspond to at least some of the light structures of the light signal;

analyzing a geometry of the detected pattern characteristics; and

inferring a surface of the roadway based at least on the analyzing.

2. The method as recited in claim 1, wherein the pattern characteristics are lines, and

wherein the lines are disposed at lengths and angles such that each line intersects with at least one other line.

3. The method of claim 2 wherein analyzing the geometry of the detected pattern characteristics comprises analyzing the lengths of the lines.

4. The method of claim 2 wherein analyzing the geometry of the detected pattern characteristics comprises analyzing the angles of the lines.

5. The method as recited in claim 1, wherein the light pattern is rotationally asymmetrical.

6. The method as recited in claim 1, wherein the light signal has a wavelength range below visible light.

7. The method as recited in claim 6, wherein the wavelength range is in a range of 780 nm to 820 nm.

8. The method as recited in claim 1, wherein the inferring is based at least on stored values of a radiometrical calibration from one of:

a signal strength of the detected pattern characteristics; and

a gray scale value of the light pattern.

9. The method as recited in claim 1, wherein the analyzing is based at least on one of:

stored values of a geometrical calibration; and

a stored pattern of the light pattern.

10. The method as recited in claim 1, further comprising ascertaining a probability from the light pattern whether a retroreflected light was emitted by one of:

the roadway; and

an obstacle.

11. The method as recited in claim 1, wherein the light pattern is classified in a space-resolved manner into at least one following class:

asphalt;

one of a film of water and a wetness from rain;

frozen water including one of frost, ice, and snow; and

one of gravel and dirt.

12. The method as recited in claim 11, wherein when the light pattern is classified as frozen water, a sub-classification into different subclasses takes place, into at least two of the following subclasses:

one of light frost and cloudy frost; and

one of black ice and freezing moisture.

13. The method as recited in claim 11, further comprising assigning one of friction coefficients and probability values of the friction coefficients to the classified light pattern.

14. The method of claim 1 wherein the pattern of the pattern characteristics is assigned to the vehicle.

15. The method of claim 1 further comprising:

analyzing a signal strength of the detected pattern characteristics.

16. The method of claim 1 further comprising:

analyzing a reflecting behavior of the detected pattern characteristics.

17. A detection system of a vehicle, comprising:

a pattern generator, which generates and emits a light signal having light structures onto a roadway of the vehicle;

a camera, which records radiation of the light signal that is reflected by at least the roadway, wherein;

the pattern generator includes an LED device and a projection lens, which emits the light signal, and

the projection lens has a diffractive optical element; and

a control device, wherein the control device generates a light pattern as a function of the recorded radiation, wherein the control device also evaluates the light pattern by detecting pattern characteristics in the light pattern that correspond to at least some of the light structures of the light signal, wherein the control device determines a geometry of the detected pattern characteristics, wherein the control device analyzes a signal strength of the detected pattern characteristics, and wherein the control device infers a surface of the roadway from at least the analyzing.

18. A method for dynamically controlling a vehicle as a function of a friction coefficient of a roadway upon which the vehicle is travelling, comprising:

generating a light signal having light structures;

emitting the light signal onto the roadway;

receiving reflected radiation of the light signal off at least the roadway;

generating a light pattern as a function of the received reflected radiation;

evaluating the light pattern;

during the evaluating, detecting pattern characteristics of the light pattern that correspond to at least some of the light structures of the light signal;

determining a geometry of the detected pattern characteristics;

analyzing a signal strength of the detected pattern characteristics;

inferring the friction coefficient of the roadway based at least on the analyzing; and

dynamically controlling the vehicle, by a vehicle dynamics control system, at least in response to the determined geometry and the inferred friction coefficient.

19. A vehicle system, comprising:

a detection system, including;

a pattern generator, which generates and emits a light signal having light structures onto a roadway of the vehicle;

a camera, which records radiation of the light signal that is reflected by at least the roadway, wherein;

the pattern generator includes an LED device and a projection lens, which emits the light signal, and

the projection lens has a diffractive optical element;

a control device, wherein the control device generates a light pattern as a function of the recorded radiation, wherein the control device also evaluates the light pattern by detecting pattern characteristics in the light pattern that correspond to at least some of the light structures of the light signal, wherein the control device determines a geometry of the detected pattern characteristics, wherein the control device analyzes a signal strength of the detected pattern characteristics, and wherein the control device infers a surface of the roadway from at least the analyzing; and

a vehicle dynamics control system, which dynamically controls the vehicle at least in response to the determined geometry and the inferred surface of the roadway.

20. The vehicle system as recited in claim 19, wherein the inferred surface of the roadway is a space-resolved classification of the roadway into values of one of iciness coefficients and friction coefficients.