Method for recognizing a covered state of a camera, camera system and motor

Patent metadata

Field	Value
Publication number	US-2016284076-A1
Application number	US-201415035988-A
Country	US
Kind code	A1
Filing date	Nov 6, 2014
Priority date	Nov 12, 2013
Publication date	Sep 29, 2016
Grant date	—

Abstract

The invention relates to a method for recognizing a covered state of a camera ( 4 ) of a motor vehicle ( 1 ) by providing an image of an environmental region of the motor vehicle ( 1 ) by means of the camera ( 4 ), determining respective brightness values of pixels within at least one image region of the image, determining a number of pixels within the at least one image region, which satisfy a preset criterion with respect to the brightness values, and checking whether the camera ( 4 ) is covered or not covered depending on the number.

First claim

1 . A method for recognizing a covered state of a camera of a motor vehicle by:
providing an image of an environmental region of a motor vehicle captured by a camera, determining respective brightness values (B) of pixels within at least one image region of the image,
determining a number (N1, N2) of pixels within the at least one image region, which satisfy a preset criterion with respect to the brightness values (B), and
checking whether the camera is covered or not covered depending on the number (N1, N2).

2 . The method according to claim 1 , characterized in that
at least two criteria are used for the brightness values (B) and to each criterion, the number (N1, N2) of pixels is determined, the brightness values (B) of which satisfy the respective criterion, wherein a different cause for the covered state is associated with each criterion.

3 . The method according to claim 2 , characterized in that
a first state is associated with a first criterion, in which the camera is at least partially covered by an opaque object, and/or a second state is associated with a second criterion, in which it is assumed that the camera is at least partially covered by a transparent object.

4 . The method according to claim 1 , characterized in that
a brightness average value (BE) within the image region is determined from the brightness values (B) of the pixels, and according to a first criterion, a first number (N1) of pixels within the image region is determined, the brightness value (B) of which is greater at least by a predetermined limit value (BV) than the brightness average value (BE), wherein it is checked whether the camera is covered or not covered depending in the first number (N1).

5 . The method Method-according to claim 4 , characterized in that
the covered state of the camera is assumed if the first number (N1) is smaller than a preset threshold value (A1).

6 . The method according to claim 5 , characterized in that
the image is divided in a plurality of image regions and to each image region, the first number (N1) of pixels is respectively determined, the brightness value (B) of which is greater by at least the predetermined limit value (BV) than the brightness average value (BE) within the respective image region, wherein those image regions, in which the first number (N1) is smaller than the preset threshold value (A1), are combined to an overall region, and the covered state of the camera is only assumed if the overall region is greater than a preset threshold.

7 . The method according to claim 1 , characterized in that
according to a second criterion, a second number (N2) of pixels within the image region is determined, the brightness value (B) of which corresponds to a maximum possible brightness value due to saturation, wherein it is checked whether the camera is covered or not covered depending on the second number (N2).

8 . The method according to claim 7 , characterized in that
the covered state of the camera is assumed if the second number (N2) is greater than a preset threshold value (A2).

9 . The method according to claim 8 , characterized in that
after detection, the covered state the camera is only again assumed as not covered if the second number (N2) remains smaller than the threshold value (A2) over a predetermined sequence (V) of images.

10 . The method according to claim 1 , characterized in that
if the covered state is not detected based on the number (N1, N2) of pixels, the image is filtered by a high-pass filter (HPF) and it is checked whether the camera is covered or not covered based on the filtered image.

11 . A camera system for a motor vehicle comprising:
at least one camera configured to provide an image of an environmental region of a motor vehicle, and a computing device configured to: determine respective brightness values (B) of pixels within at least one image region of the image, determine a number (N1, N2) of pixels within the at least one image region, which satisfy a preset criterion with respect to the brightness values (B), and check whether the camera is covered or not covered depending on the number (N1, N2).

12 . A combination of a motor vehicle with a camera system comprising:
a motor vehicle, at least one camera configured to provide an image of an environmental region of the motor vehicle, and a computing device configured to:
determine respective brightness values (B) of pixels within at least one image region of the image,
determine a number (N1, N2) of pixels within the at least one image region, which satisfy a preset criterion with respect to the brightness values (B), and
check whether the camera is covered or not covered depending on the number (N1, N2).

Assignees

• Application Solutions (Electronics And Vision) Ltd
• Connaught Electronics Ltd

Inventors

• Voros Robert
• Hughes Ciaran
• Yadav Dev

Classifications

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• H04N17/002

  for television cameras · CPC title

• G06T2207/30168

  Image quality inspection · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• H04N7/18

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title