Method and device for detecting objects in the dark using a vehicle camera and a vehicle lighting system

1. A method for detecting objects in the dark, the method comprising:

a) capturing, by a vehicle camera, a first image when a vehicle lighting is switched off;

b) capturing, by the vehicle camera, a second image when the vehicle lighting is switched on;

c) determining, by a vehicle processor, movement of the vehicle between capturing the first image and capturing the second image;

d) predicting, by the vehicle processor, a position of an object in the second image based on a position of the object in the first image and the movement of the vehicle;

e) generating, by the vehicle processor, a differential image of the second and first images based on the predicted position of the object in the second image; and

f) distinguishing, by the vehicle processor, between lighting devices and reflective objects based on the differential image.

2. The method according to claim 1 , wherein stationary reflective objects are detected using the differential images by multiple performance of the steps a) to f).

3. The method according to claim 2 , wherein the course of the road lying ahead is estimated from the position and type of detected stationary reflective objects.

4. The method according to claim 1 , further comprising estimating whether reflective objects can represent road users or obstacles without an independent light source.

5. The method according to claim 4 , wherein non-stationary reflective objects are detected as road users.

6. The method according to claim 1 , wherein the color of the reflective objects is determined and taken into account for detection.

7. The method according to claim 1 , wherein an ego-motion of the vehicle is taken into account when generating the differential image by predicting the position of areas of light in the second image based on the position of said areas of light in the first image.

8. The method according to claim 1 , wherein a movement of areas of light is determined from a sequence of first images and said movement is taken into account when generating the differential image from another first image and a subsequent second image.

9. The method according to claim 1 , wherein the vehicle camera is an all-round view camera system.

10. A device for detecting objects in the dark using a vehicle camera and a vehicle lighting control unit comprising:

a vehicle camera, configured for:

a) capturing a first image when a vehicle lighting is switched off;

b) capturing a second image when the vehicle lighting is switched on;

c) determining movement of the vehicle between capturing the first image and capturing the second image;

d) predicting a position of an object in the second image based on a position of the object in the first image and the movement of the vehicle; and

an image processor, configured for:

a) generating a differential image of the second and first images based on the predicted position of the object in the second image; and

b) distinguishing between lighting devices and reflective objects based on the differential image.

11. The method according to claim 2 , further comprising estimating whether reflective objects can represent road users or obstacles without an independent light source.

12. The method according to claim 3 , further comprising estimating whether reflective objects can represent road users or obstacles without an independent light source.