Method and device for detecting an interfering object in a camera image

• US 8,582,809 B2
• Filed: 06/22/2011
• Issued: 11/12/2013
• Est. Priority Date: 06/28/2010
• Status: Expired due to Fees

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Simon, Stephan, Halimeh, Jad
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US13/135,012
• Publication Number:
  US 20120008866A1
• Time in Patent Office: 874 Days
• Field of Search: 382/103, 382/107, 382/236, 382/190, 348/143, 348/154, 348/155, 348/169, 348/170, 348/171, 348/172, 348/208.1, 348/208.02, 348/208.16, 348/352, 348/208.2
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

A method for detecting an interfering object in a camera image of a camera image sequence includes: reading in a first pixel data value of a predetermined position in a first camera image obtained at a first point in time, a second pixel data value of the predetermined position in a second camera image obtained at a second point in time after the first point in time, and a third pixel data value of the predetermined position in a third camera image obtained at a third point in time after the second point in time; ascertaining a reference value on the basis of the second pixel data value and a comparison value on the basis of the first pixel data value and/or the third pixel data value; and detecting the interfering object at the predetermined position when the reference value is in a predefined relationship with the comparison value.

Claims

1. A method for detecting an interfering object in at least one camera image of a camera image sequence, comprising:

reading in a first pixel data value at a predetermined position in a first camera image obtained at a first point in time, a second pixel data value at the predetermined position in a second camera image obtained at a second point in time after the first point in time, and a third pixel data value at the predetermined position in a third camera image obtained at a third point in time after the second point in time;

ascertaining (i) a reference value on the basis of the second pixel data value and (ii) a comparison value on the basis of at least one of the first pixel data value and the third pixel data value; and

detecting the presence of the interfering object at the predetermined position if the reference value is in a predefined relationship with the comparison value.

2. The method as recited in claim 1, wherein the presence of the interfering object at the predetermined position is detected when the first pixel data value and the third pixel data value each have a value which is within a predefined, common tolerance range.

3. The method as recited in claim 1, wherein the presence of the interfering object at the predetermined position is detected when a first ratio of the reference value to the comparison value is within a predefined tolerance range for a second ratio of the reference value to a further comparison value determined on the basis of the third pixel data value.

4. The method as recited in claim 1, wherein the presence of the interfering object at the predetermined position is detected when the reference value differs from the comparison value by more than a predefined quantity.

5. The method as recited in claim 1, wherein in the detecting of the presence of the interfering object, one of a difference or a ratio of the reference value and the comparison value is calculated for the predetermined relationship.

6. The method as recited in claim 1, wherein in the detecting of the presence of the interfering object, a difference determined between the reference value and at least one of (i) the comparison value and (ii) a further comparison value determined on the basis of the third pixel data value, in order to discern a probability of the presence of the interfering object at the predetermined position on the basis of the difference.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position.

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

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence; and

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position, and

wherein the presence of the interfering object at the predetermined position is detected when the first pixel data value and the third pixel data value each have a value which is within a predefined, common tolerance range.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence; and

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position,

wherein the presence of the interfering object at the predetermined position is detected when the reference value differs from the comparison value by more than a predefined quantity, and

wherein in the detecting of the presence of the interfering object, one of a difference or a ratio of the reference value and the comparison value is calculated for the predetermined relationship.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence; and

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position,

wherein the presence of the interfering object at the predetermined position is detected when a first ratio of the reference value to the comparison value is within a predefined tolerance range for a second ratio of the reference value to a further comparison value determined on the basis of the third pixel data value.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence; and

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position,

wherein the presence of the interfering object at the predetermined position is detected when the reference value differs from the comparison value by more than a predefined quantity, and

wherein in the detecting of the presence of the interfering object, one of a difference or a ratio of the reference value and the comparison value is calculated for the predetermined relationship.

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

defining at least one one-dimensional structure in at least one camera image of the camera image sequence; and

detecting a snow density based on a ratio of (i) a number of predetermined positions at which interfering objects were detected, to (ii) a number of positions in a camera image;

wherein no interfering object is determined to be present at the predetermined position if the at least one one-dimensional structure was defined at the predetermined position,

wherein the presence of the interfering object at the predetermined position is detected when the reference value differs from the comparison value by more than a predefined quantity, and

wherein in the detecting of the presence of the interfering object, a difference determined between the reference value and at least one of (i) the comparison value and (ii) a further comparison value determined on the basis of the third pixel data value, to discern a probability of the presence of the interfering object at the predetermined position on the basis of the difference.

14. A method for eliminating an interfering object in a camera image sequence, comprising:

detecting an interfering object in at least one camera image of a camera image sequence by;

reading in a first pixel data value at a predetermined position in a first camera image obtained at a first point in time, a second pixel data value at the predetermined position in a second camera image obtained at a second point in time after the first point in time, and a third pixel data value at the predetermined position in a third camera image obtained at a third point in time after the second point in time;

ascertaining (i) a reference value on the basis of the second pixel data value and (ii) a comparison value on the basis of at least one of the first pixel data value and the third pixel data value; and

detecting the presence of the interfering object at the predetermined position if the reference value is in a predefined relationship with the comparison value; and

replacing the second pixel data value at the predetermined position in the second camera image with a pixel data value which is in a predetermined relationship with at least one of the first pixel data value and the third pixel data value.

15. A system for detecting an interfering object in at least one camera image of a camera image sequence, comprising:

a device configured to read in a first pixel data value at a predetermined position in a first camera image obtained at a first point in time, a second pixel data value at the predetermined position in a second camera image obtained at a second point in time after the first point in time, and a third pixel data value at the predetermined position in a third camera image obtained at a third point in time after the second point in time;

a device configured to ascertain (i) a reference value on the basis of the second pixel data value and (ii) a comparison value on the basis of at least one of the first pixel data value and the third pixel data value; and

a device configured to detect the presence of the interfering object at the predetermined position if the reference value is in a predefined relationship with the comparison value.

16. A non-transitory computer-readable data storage device storing a computer program having program codes which, when executed on a computer, perform a method for detecting an interfering object in at least one camera image of a camera image sequence, the method comprising:

reading in a first pixel data value at a predetermined position in a first camera image obtained at a first point in time, a second pixel data value at the predetermined position in a second camera image obtained at a second point in time after the first point in time, and a third pixel data value at the predetermined position in a third camera image obtained at a third point in time after the second point in time;

ascertaining (i) a reference value on the basis of the second pixel data value and (ii) a comparison value on the basis of at least one of the first pixel data value and the third pixel data value; and

detecting the presence of the interfering object at the predetermined position if the reference value is in a predefined relationship with the comparison value.