Method for detecting nocturnal fog and system for implementing the method

• US 20070031006A1
• Filed: 04/18/2006
• Published: 02/08/2007
• Est. Priority Date: 04/19/2005
• Status: Active Grant

• Current Assignee: Valeo Vision (Valeo SE)
• Original Assignee: Valeo Vision (Valeo SE)
• Inventors: Rebut, Julien, Bensrhair, Abdelaziz, Leleve, Joel
• Granted Patent: US 7,423,752 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: B60Q 1/1423 Automatic dimming circuits, i.e. switching between high beam and low beam due to change of ambient light or light level in road traffic
• CPC Class Codes: B60Q 1/20 Fog lights
• CPC Class Codes: G06T 2207/30248 Vehicle exterior or interior
• CPC Class Codes: G06T 7/66 of image moments or centre of gravity
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

The invention concerns a system and method for detecting, at night, the presence of an element such as fog interfering with the visibility of a road scene situated in front of a vehicle, comprising the following operations: acquiring an image of the road scene, extracting, from the image of the road scene, at least one light halo produced by a lighting device of the vehicle, approximating a form of this light halo by an elliptic curve, comparing the form of this light halo with the elliptic curve obtained in order to deduce therefrom the presence or absence of an element interfering with visibility.

Claims

1. A method for detecting, by night, the presence of an element such as fog interfering with the visibility of a road scene situated at the front of a vehicle, comprising the following operations:

acquiring an image of the road scene,

extracting, from the image of the road scene, at least one light halo produced by a lighting device of the vehicle,

approximating a form of said at least one light halo by an elliptic curve, and

comparing the form of said at least one light halo with the elliptic curve obtained in order to deduce therefrom the presence or absence of an element interfering with visibility.

2. The method according to claim 1, comprising, when the element interfering with visibility is present, an operation of determining the visibility distance according to parameters of the said elliptic curve.

3. The method according to claim 1, wherein the operating of extracting the light halo comprises a binarisation of said image and an extraction of a contour of the halo on the binarised image.

4. The method according to claim 3, wherein the operation of extracting said at least one light halo comprises a detection of an optimum binarisation threshold.

5. The method according to any one of claims 1, wherein the operation of approximating the said at least one light halo comprises a determination of the parameters of the elliptic curve.

6. The method according to claim 5, wherein the determination of the parameters comprises an estimation of a center of gravity of the elliptic curve.

7. The method according to claim 6, wherein said center of gravity of the elliptic curve is determined by detecting the points on the elliptic curve having the same gradient.

8. The method according to claim 6, wherein the center of gravity of the elliptic curve is determined by construction, from tangents to the said elliptic curve.

9. The method according to claim 3, wherein the comparison of the form of the said at least one light halo with the elliptic curve comprises a calculation of the approximation error between the elliptic curve and the contour of said at least one light halo of the binarised image.

10. The method according to claim 2, wherein the determination of the visibility distance comprises a determination of a vertical profile passing through the center of gravity of the elliptic curve and a reversal point on said elliptic curve.

11. The method according to claim 1, wherein said elliptic curve is obtained by the combination of two ellipses.

12. A system for detecting, at night, the presence of an element such as fog interfering with the visibility of a road scene situated in front of a vehicle, said system comprising:

a camera for acquiring images of the road scene;

image processing means for extracting at least one light halo from a captured image of the road scene for producing an approximation of a form of said at least one light halo by an elliptic curve and for comparing the form of said at least one light halo with said elliptic curve in order to deduce therefrom the presence or absence of the element interfering with visibility.

13. The system according to claim 12, comprising means for determining a visibility distance of the vehicle, when the element interfering with visibility has been detected.

14. The system according to claim 13, wherein it is connected to a device for controlling an alarm intended to indicate a speed of the vehicle unsuited to the said visibility distance.

15. The system according to claim 13, wherein it is connected to a device controlling at least one light source of the vehicle in order to adapt the light intensity of the said at least one light source to said visibility distance.

16. The system according to claim 13, wherein it is connected to a device for controlling of a speed of the vehicle in order to modify the said speed according to the visibility distance.

17. The system according to claim 12, wherein said system further comprises means for detecting a transition between day and night.

18. Road vehicle, comprising a system for detecting, at night, the presence of an element such as fog interfering with the visibility of the road scene according to claim 12.

19. A method for detecting an element interfering with the visibility of a road scene illuminated by at least one light of a vehicle:

capturing an image of the road scene;

extracting at least one light halo from said image; and

deducing the presence or absence of the element using said at least one light halo.

20. The method as recited in claim 19 wherein said method further comprises the steps of:

approximating a form of said at least one light halo;

using said approximation to perform said deducing step.

21. The method as recited in claim 20 wherein said method further comprises the step of:

approximating said form of said at least one light halo by applying an elliptic curve that approximates a contour of said at least one light halo.

22. The method as recited in claim 20 wherein said extracting step comprises the step of:

using a binarisation of said image to provide a binarised image;

extracting a contour of said at least one halo from said binarised image.

23. The method as recited in claim 21 wherein said approximating step further comprises the step of:

determining a plurality of parameters of said elliptic curve.

24. The method as recited in claim 23 wherein said plurality of parameters comprises an estimation of a center of gravity.

25. The method as recited in claim 21 wherein said elliptic curve is obtained by combination of two ellipses.