Apparatus and method for detecting precipitation for a motor vehicle

• US 10,106,126 B2
• Filed: 05/13/2015
• Issued: 10/23/2018
• Est. Priority Date: 05/15/2014
• Status: Active Grant

• Current Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Original Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Inventors: Kosubek, Christopher, Kroekel, Dieter, Meis, Urban
• Primary Examiner(s): Dastouri, Mehrdad
• Assistant Examiner(s): Cattungal, Rowina
• Application Number:
  US14/710,910
• Publication Number:
  US 20150332099A1
• Time in Patent Office: 1,259 Days
• CPC Class Codes: B60S 1/0844 including a camera
• CPC Class Codes: G01W 1/14 Rainfall or precipitation gauges measuring volume in general G01F
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

An apparatus and a method are for detecting precipitation on a windscreen of a motor vehicle. A camera device records a first image and thereafter a second image. A comparison device produces a first comparison image by comparing the first image with the second image. An image detection device identifies objects on the first comparison image, and determines motion of the objects, to detect whether there is precipitation on the windscreen.

Claims

1. An apparatus for detecting precipitation on a windscreen of a motor vehicle, the apparatus comprising:

a camera device configured to record a first image and thereafter a second image;

a comparison device configured to produce a first comparison image by comparing the first image with the second image; and

an image detection device configured to detect objects in the first comparison image, and to determine a respective apparent motion and a respective apparent motion direction of moving objects among the detected objects, and to classify some of the moving objects respectively as being either precipitation drops on the windscreen or non-precipitation objects in an outside environment of the motor vehicle based on consideration of at least the respective motion direction thereof;

wherein the moving objects include first moving objects of which the respective motion direction includes a lateral or horizontal motion component, and second moving objects of which the respective motion direction does not include a lateral or horizontal motion component, and

wherein the image detection device is further configured so that the classifying of the moving objects based on consideration of the respective motion direction thereof comprises ignoring or filtering-out the first moving objects and further classifying only the second moving objects as being either the precipitation drops or the non-precipitation objects.

2. The apparatus according to claim 1, wherein the comparison device is further configured to produce a difference image as the first comparison image.

3. The apparatus according to claim 1, wherein:

the camera device is further configured to record a third image following the second image;

the comparison device is further configured to produce a second comparison image by comparing the second image with the third image; and

the image detection device is further configured to determine the respective apparent motion and the respective apparent motion direction of the moving objects by comparing the first comparison image with the second comparison image.

4. The apparatus according to claim 1, wherein the image detection device is further configured to determine the respective apparent motion and the respective apparent motion direction of the moving objects by comparing the first image with the second image.

5. The apparatus according to claim 1, wherein the image detection device is further configured to classify the detected objects other than the moving objects in the first comparison image.

6. The apparatus according to claim 1, wherein the image detection device is further configured to classify the detected objects based on consideration of respective shapes of the detected objects.

7. The apparatus according to claim 1, wherein the image detection device is further configured to classify the detected objects based on consideration of respective local frequencies of the detected objects in the first comparison image.

8. The apparatus according to claim 1, wherein the camera device is further configured to record the images with a predefined depth of field, and the image detection device is further configured to classify the detected objects based on consideration of whether a respective one of the detected objects lies within or outside the predefined depth of field.

9. The apparatus according to claim 1, wherein the camera device is further configured to record the images without the apparatus applying any active lighting.

10. The apparatus according to claim 1, wherein the camera device is further configured to record the images and the image detection device is further configured to perform the classifying when the motor vehicle is stationary.

11. The apparatus according to claim 1, wherein the camera device is further configured to record the images and the image detection device is further configured to perform the classifying when the motor vehicle is moving with a vehicle motion, and to filter out motion components of the respective apparent motion of the moving objects caused by the vehicle motion before the classifying of the moving objects.

17. The apparatus according to claim 1, wherein the image detection device is configured to detect the detected objects in the first comparison image by detecting new objects that are present in the second image but are not present in the first image, whereby the new objects appear in the first comparison image.

12. A method of detecting precipitation on a windscreen of a motor vehicle, the method comprising the following steps performed with a driver assistance system of the vehicle:

with a camera of the driver assistance system recording a first image and thereafter a second image;

producing a comparison image from the first image and the second image;

identifying objects in the comparison image;

determining a respective apparent motion and a respective apparent motion direction of moving objects among the identified objects, wherein the moving objects include first moving objects of which the respective motion direction includes a lateral or horizontal motion component, and second moving objects of which the respective motion direction does not include a lateral or horizontal motion component; and

classifying some of the moving objects based on consideration of at least the motion direction thereof, comprising ignoring or filtering-out the first moving objects and then further classifying the second moving objects to determine whether the second moving objects represent environment objects in an outside environment in front of the motor vehicle or represent precipitation drops on the windscreen.

13. A method of detecting precipitation on a windscreen of a motor vehicle, the method comprising the following steps performed with a driver assistance system of the motor vehicle:

a) with a camera of the driver assistance system having a field of view directed through the windscreen and focused in an outside environment in front of the motor vehicle, recording a first image and thereafter a second image;

b) evaluating the images and detecting therein moving objects that have moved in the second image relative to the first image;

c) determining a respective motion direction of the moving objects;

d) among the moving objects, determining first moving objects of which the respective motion direction is horizontal and determining second moving objects of which the respective motion direction does not include a lateral or horizontal motion component; and

e) performing a rain detection procedure on the second moving objects, and ignoring or filtering-out the first moving objects from the rain detection procedure, wherein the rain detection procedure comprises classifying the second moving objects to determine whether the second moving objects represent physical objects in the outside environment in front of the motor vehicle or represent precipitation drops on the windscreen.

14. The method according to claim 13,

wherein the step d) further includes determining, among the moving objects, third moving objects of which the respective motion direction is a diagonal motion direction;

and

wherein the step e) further involves ignoring or filtering-out the third moving objects from the rain detection procedure.

15. The method according to claim 13, performed when the motor vehicle is stationary.

16. The method according to claim 13, performed when the motor vehicle is moving with a vehicle motion, wherein the method further comprises filtering-out motion components caused by the vehicle motion in the respective motion directions of the moving objects before performing the steps d) and e).