Method and device for analyzing an image of an image recording device for a vehicle

• US 8,818,093 B2
• Filed: 02/10/2011
• Issued: 08/26/2014
• Est. Priority Date: 02/24/2010
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Ehlgen, Tobias, Seger, Ulrich, Ruhnau, Paul
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US13/579,885
• Publication Number:
  US 20130039576A1
• Time in Patent Office: 1,293 Days
• Field of Search: 382/100, 382/104, 382/168, 382/195, 382/199, 382/270, 382/271
• US Class Current: 382/168
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

In a method for analyzing an image of an image recording device for a vehicle, a piece of brightness information of the image is determined, taking an exposure characteristic of the image recording device into account, and a threshold value is set as a function of the piece of brightness information. An image structure of the image is furthermore determined, and a blindness value for the image is determined on the basis of the image structure, using the threshold value.

Claims

1. A method for analyzing image data of an image recorded by an image recording device for a vehicle, comprising:

receiving, with a processor, the image data of the image via an image interface from the image recording device;

determining, by the processor, a brightness information of the image on the basis of the image data, taking an exposure characteristic of the image recording device into account;

setting, by the processor, a threshold value as a function of the brightness information;

determining, by the processor, an image structure of at least one region of the image; and

determining, by the processor, a blindness value for the image by comparing the image structure and the threshold value.

2. The method as recited in claim 1, further comprising:

determining a relinearized histogram from the brightness information, wherein the setting of the threshold value is carried out as a function of the relinearized histogram.

3. The method as recited in claim 1, further comprising:

ascertaining a brightness change on the basis of a time progression of the brightness information, wherein the determination of the blindness value is carried out additionally on the basis of the brightness change.

4. The method as recited in claim 3, wherein multiple image structures are determined for multiple regions of the image, and wherein the image structures each represent one edge slope per region.

5. The method as recited in claim 3, wherein multiple image structures are determined for multiple regions of the image, and wherein each image structure represents an object shown in the image.

6. The method as recited in claim 3, further comprising:

receiving information concerning objects which are detected on the basis of the image data provided by the image recording device;

determining a number of objects contained in the image on the basis of the information concerning the objects; and

determining a visibility value for the image on the basis of the number of objects, using a visibility threshold value.

7. The method as recited in claim 6, wherein the visibility threshold value is set as a function of the brightness information.

8. The method as recited in claim 6, further comprising:

determining a blindness probability for the image on the basis of the blindness value and the visibility value.

9. The method as recited in claim 6, wherein an existing visibility value for the image is changed by a predetermined value as a function of a comparison between the number of objects in the image and the visibility threshold value.

10. The method as recited in claim 6, further comprising:

dividing the image into multiple regions, wherein a blindness value and a visibility value is determined for each of the regions.

11. The method as recited in claim 10, wherein a first item of blindness information is determined on the basis of blindness values of a first group of regions, and a second item of blindness information is determined on the basis of blindness values in a second group of regions.

12. A device for analyzing image data of an image recorded by an image recording device for a vehicle, comprising:

an interface receiving the image data of the image;

means for determining a brightness information of the image on the basis of the image data, taking an exposure characteristic of the image recording device into account;

means for setting a threshold value as a function of the brightness information;

means for determining an image structure of at least one region of the image; and

means for determining a blindness value for the image by comparing the image structure and the threshold value.

13. A non-transitory computer-readable data storage medium storing a computer program having program codes which, when executed on a computer, performs a method for analyzing image data of an image recorded by an image recording device for a vehicle, the method comprising:

receiving the image data of the image via an image interface from the image recording device;

determining a brightness information of the image on the basis of the image data, taking an exposure characteristic of the image recording device into account;

setting a threshold value as a function of the brightness information;

determining an image structure of at least one region of the image; and

determining a blindness value for the image by comparing the image structure and the threshold value.