METHOD AND DEVICE FOR DETECTING OBJECTS IN THE SURROUNDINGS OF A VEHICLE

• US 20140098997A1
• Filed: 05/21/2012
• Published: 04/10/2014
• Est. Priority Date: 06/07/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Faber, Petko, Schwarzenberg, Gregor
• Granted Patent: US 10,552,688 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• 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 1/143 combined with another condition, e.g. using vehicle recognition from camera images or activation of wipers
• CPC Class Codes: B60Q 2300/112 Vehicle speed
• CPC Class Codes: B60Q 2300/3321 Detection of streetlights
• CPC Class Codes: B60Q 2300/41 preceding vehicle
• CPC Class Codes: B60Q 2300/42 oncoming vehicle
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: H04N 23/743 Bracketing, i.e. taking a series of images with varying exposure conditions
• CPC Class Codes: H04N 23/745 Detection of flicker frequency or suppression of flicker wherein the flicker is caused by illumination, e.g. due to fluorescent tube illumination or pulsed LED illumination

Abstract

A method for detecting objects in the surroundings of a vehicle. The method includes reading in a first image, of a vehicle camera, which represents the surroundings taken using a first exposure time and reading in a second image of the vehicle camera, which was taken after the first image and using a second exposure time, the second exposure time differing from the first exposure time, and extracting an image detail from the second image, the image detail representing a smaller area of the surroundings than the first image. During the extracting, a position of the image detail in the second image is determined based on at least one parameter which represents information on travel of the vehicle and/or a position of an infrastructure measure in front of the vehicle and/or which is independent of a moving object that was detected in a preceding step in the image detail.

Claims

1-12. -12. (canceled)

13. A method for detecting objects in surroundings of a vehicle, comprising:

reading in a first image of a vehicle camera, which represents the surroundings of the vehicle and which was taken using a first exposure time, and reading in a second image of the vehicle camera, which was taken after the first image and using a second exposure time, the second exposure time differing from the first exposure time;

extracting an image detail from the second image of the vehicle camera, the image detail representing a smaller area of the surroundings of the vehicle than the first image, during the extracting, a position of the image detail in the second image being at least one of;

i) determined based on at least one parameter which represents information on travel of the vehicle, ii) a position of an infrastructure measure in front of the vehicle, and iii) independent of a moving object that was detected in a preceding step in the image detail; and

applying a first object detection algorithm to the first image to detect at least one object in the first image and applying a second object detection algorithm to the image detail to detect at least one further object in the image detail.

14. The method as recited in claim 13, wherein, in the extracting step, the image detail is extracted using position information, wherein the position information is changed in response to information which represents travel of the vehicle.

15. The method as recited in claim 13, wherein, in the reading in step, an image is read in as the first image which has a shorter exposure time than the image that is read in as the second image.

16. The method as recited in claim 13, wherein, in the applying step, the first object detection algorithm is used on the entire first image.

17. The method as recited in claim 13, wherein, in the extracting step, an image detail of the second image is extracted, in which objects are imaged in the image of the vehicle camera, which are situated at a predetermined minimum distance ahead of the vehicle.

18. The method as recited in claim 13, wherein, in the applying step, the first object detection algorithm is used for the detection of objects of a first object type, and the second object detection algorithm is used for detecting objects of a second object type, which differs from the first object type.

19. The method as recited in claim 13, wherein, in the applying step, the first object detection algorithm detects an object in the first image while using a comparison of a brightness at a position in the first image to a brightness at a corresponding position in the image detail.

20. The method as recited in claim 13, wherein in the applying step, the second object detection algorithm detects an object in the image detail while using a comparison of a brightness at a position in the image detail, to a brightness at a corresponding position in the first image.

21. The method as recited in claim 19, wherein, in the applying step, an object is detected as a pulsating light source by the first object detection algorithm, if the brightness at the position in the first image is within a tolerance range equal to the brightness at the corresponding position in the image detail.

22. The method as recited in claim 19, wherein, in the applying step, an object is detected as a light source that is constantly emitting light by the first object detection algorithm, if the brightness at the position in the first image differs by more than a predetermined threshold value from the brightness at the corresponding position in the image detail.

23. The method as recited in claim 20, wherein, in the applying step, an object is detected as a pulsating light source by the second object detection algorithm, if the brightness at the position in the image detail is within a tolerance range equal to the brightness at the corresponding position in the first image.

24. The method as recited in claim 20, wherein, in the applying step, an object is detected as a light source that is constantly emitting light by the second object detection algorithm if the brightness at the position in the image detail differs by more than a predetermined threshold value from the brightness at the corresponding position in the first image.

25. A method for regulating a roadway illumination in front of a vehicle, comprising:

reading in a first image of a vehicle camera, which represents the surroundings of the vehicle and which was taken using a first exposure time, and reading in a second image of the vehicle camera, which was taken after the first image and using a second exposure time, the second exposure time differing from the first exposure time;

extracting an image detail from the second image of the vehicle camera, the image detail representing a smaller area of the surroundings of the vehicle than the first image, during the extracting, a position of the image detail in the second image being at least one of;

i) determined based on at least one parameter which represents information on the travel of the vehicle, ii) a position of an infrastructure measure in front of the vehicle, and iii) independent of a moving object that was detected in a preceding step in the image detail;

applying a first object detection algorithm to the first image to detect at least one object in the first image and applying a second object detection algorithm to the image detail to detect at least one further object in the image detail; and

actuating a modification of light radiation of a headlight of the vehicle, at least one of in response to at least one object detected by the first object detection algorithm, and in response to at least one object detected by the second object detection algorithm.

26. The method as recited in claim 25, wherein, in the actuating step, the modifying of the light radiation takes place independently of an infrastructure device at the roadway edge detected by one of the first or the second object detection algorithms.

27. A device to detect objects in surroundings of a vehicle, the device configured to read in a first image of a vehicle camera, which represents the surroundings of the vehicle and which was taken using a first exposure time, read in a second image of the vehicle camera, which was taken after the first image and using a second exposure time, the second exposure time differing from the first exposure time, and extract an image detail from the second image of the vehicle camera, the image detail representing a smaller area of the surroundings of the vehicle than the first image, during the extracting, a position of the image detail in the second image being at least one of:

i) determined based on at least one parameter which represents information on the travel of the vehicle, ii) a position of an infrastructure measure in front of the vehicle, and iii) independent of a moving object that was detected in a measure in front of the vehicle, and iii) independent of a moving object that was detected in a preceding step in the image detail, and to apply a first object detection algorithm to the first image to detect at least one object in the first image and applying a second object detection algorithm to the image detail to detect at least one further object in the image detail.

28. A computer readable storage medium storing program code for detecting objects in surrounds of a vehicle, the program code, when executed by a processor, causing the processor to perform the steps of:

reading in a first image of a vehicle camera, which represents the surroundings of the vehicle and which was taken using a first exposure time, and reading in a second image of the vehicle camera, which was taken after the first image and using a second exposure time, the second exposure time differing from the first exposure time;

extracting an image detail from the second image of the vehicle camera, the image detail representing a smaller area of the surroundings of the vehicle than the first image, during the extracting, a position of the image detail in the second image being at least one of;

i) determined based on at least one parameter which represents information on the travel of the vehicle, ii) a position of an infrastructure measure in front of the vehicle, and iii) independent of a moving object that was detected in a preceding step in the image detail; and

applying a first object detection algorithm to the first image to detect at least one object in the first image and applying a second object detection algorithm to the image detail to detect at least one further object in the image detail.