Method and device for recognizing obstruction of view in image sensor systems

• US 7,609,857 B2
• Filed: 11/22/2002
• Issued: 10/27/2009
• Est. Priority Date: 01/17/2002
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Franz, Matthias
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): ZARKA, DAVID PETER
• Application Number:
  US10/501,253
• Publication Number:
  US 20050254688A1
• Time in Patent Office: 2,531 Days
• Field of Search: 382/104
• US Class Current: 382/104
• CPC Class Codes: B60S 1/0822 characterized by the arrangement or type of detection means
• CPC Class Codes: B60S 1/0844 including a camera
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• 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 7/0004 Industrial image inspection
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

A method and a device for recognizing visual obstructions in image sensor systems are provided. A signal is produced, based on the analysis of the recorded image from the image sensor, which indicates the presence and, optionally, the type, of the visual obstruction on a windshield, for example.

Claims

1. A method for recognizing a visual obstruction using an image sensor associated with a vehicle, comprising:

recording an image by the image sensor, wherein the image sensor is focused on an external region beyond the vehicle such that a visual obstruction on the vehicle is imaged;

analyzing the image recorded by the image sensor, wherein at least one of a presence and a type of a visual obstruction is determined by the analysis of the image, wherein the analysis includes measuring a blurriness of at least a portion of the image;

producing a signal which indicates one of the presence and the type of the visual obstruction; and

controlling downstream systems based on the signal;

wherein an analysis of at least one image recorded after an initial wiping operation on a windshield of a motor vehicle is used to determine whether to initiate a next wiping operation, and

wherein the determination regarding the next wiping operation is based on blurriness of a first image that was recorded immediately after the initial wiping operation in comparison to blurriness of an image recorded subsequent to the first image.

2. The method of claim 1, wherein the at least one of the presence and the type of the visual obstruction is determined by measuring a relative blurriness of different parts of the image.

3. The method of claim 1, wherein the blurriness is measured based on one of a contrast spectrum of the image, a Fourier spectrum, and a autocorrelation function of the image.

4. The method of claim 1, wherein the at least one of the presence and the type of visual obstruction is determined based on a measured distribution of the blurriness by comparison with reference distributions.

5. The method of claim 1, further comprising:

turning on a windshield light if a scene has a contrast below a predetermined threshold.

6. A device for identifying a visual obstruction, comprising:

an image sensor for recording an image, wherein the image sensor is focused on an external region beyond the vehicle such that a visual obstruction on the vehicle is imaged; and

an evaluation unit for analyzing the image recorded by the image sensor;

wherein the evaluation unit outputs a signal that indicates at least one of a presence and a type of the visual obstruction based on the analysis of the image, wherein the analysis includes measuring a blurriness of at least a portion of the image; and

wherein the signal is used to control downstream systems, and

wherein the determination regarding the next wiping operation is based on blurriness of a first image that was recorded immediately after the initial wiping operation in comparison to blurriness of an image recorded subsequent to the first image.

7. The device of claim 6, wherein the downstream systems include at least one of windshield wipers, windshield heating systems, and windshield washer systems.

8. The device of claim 6, wherein the at least one of the presence and the type of the visual obstruction is determined by measuring a relative blurriness of different parts of the image.

9. The device of claim 6, wherein the blurriness is measured based on one of a contrast spectrum of the image, a Fourier spectrum, and a autocorrelation function of the image.

10. The device of claim 6, wherein the at least one of the presence and the type of visual obstruction is determined based on a measured distribution of the blurriness by comparison with reference distributions.

11. The device of claim 6, wherein an analysis of at least one image recorded after an initial wiping operation on a windshield of a motor vehicle is used to determine whether to initiate a next wiping operation.

12. The device of claim 6, further comprising:

an arrangement to turn on a windshield light if a scene has a contrast below a predetermined threshold.

13. A device for identifying a visual obstruction, comprising:

an image sensor for recording an image, wherein the image sensor is focused on an external region beyond the vehicle such that a visual obstruction on the vehicle is imaged; and

an evaluation unit for analyzing the image recorded by the image sensor;

wherein;

the evaluation unit outputs a signal that indicates at least one of a presence and a type of the visual obstruction based on the analysis of the image, wherein the analysis includes measuring a blurriness of at least a portion of the image,

the signal is used to control downstream systems,

the downstream systems include at least one of windshield wipers, windshield heating systems, and windshield washer systems,

the blurriness is measured based on one of a contrast spectrum of the image, a Fourier spectrum, and a autocorrelation function of the image, and

an analysis of at least one image recorded after an initial wiping operation on a windshield of a motor vehicle is used to determine whether to initiate a next wiping operation, and wherein the determination regarding the next wiping operation is based on blurriness of a first image that was recorded immediately after the initial wiping operation in comparison to blurriness of an image recorded subsequent to the first image.

14. The device of claim 13, wherein the at least one of the presence and the type of the visual obstruction is determined by measuring a relative blurriness of different parts of the image.

15. The device of claim 13, wherein the at least one of the presence and the type of visual obstruction is determined based on a measured distribution of the blurriness by comparison with reference distributions.

16. The device of claim 13, further comprising:

an arrangement to turn on a windshield light if a scene has a contrast below a predetermined threshold.

17. A method for recognizing a visual obstruction using an image sensor associated with a vehicle, comprising:

recording an image by the image sensor, wherein the image sensor is focused on an external region beyond the vehicle such that a visual obstruction on the vehicle is imaged;

analyzing the image recorded by the image sensor, wherein at least one of a presence and a type of a visual obstruction is determined by the analysis of the image, wherein the analysis includes measuring a blurriness of at least a portion of the image;

producing a signal which indicates one of the presence and the type of the visual obstruction; and

controlling downstream systems based on the signal;

wherein;

the downstream systems include at least one of windshield wipers, windshield heating systems, and windshield washer systems,

the blurriness is measured based on one of a contrast spectrum of the image, a Fourier spectrum, and a autocorrelation function of the image, and

wherein an analysis of at least one image recorded after an initial wiping operation on a windshield of a motor vehicle is used to determine whether to initiate a next wiping operation, and wherein the determination regarding the next wiping operation is based on blurriness of a first image that was recorded immediately after the initial wiping operation in comparison to blurriness of an image recorded subsequent to the first image.

18. The method of claim 17, wherein the at least one of the presence and the type of the visual obstruction is determined by measuring a relative blurriness of different parts of the image.

19. The method of claim 17, wherein the at least one of the presence and the type of visual obstruction is determined based on a measured distribution of the blurriness by comparison with reference distributions.

20. The method of claim 17, further comprising:

turning on a windshield light if a scene has a contrast below a predetermined threshold.