Method and device for detecting obstruction in image sensor systems

• US 7,218,757 B2
• Filed: 01/16/2003
• Issued: 05/15/2007
• 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): Wu; Jingge
• Assistant Examiner(s): Lu; Tom Y.
• Application Number:
  US10/346,789
• Publication Number:
  US 20030165268A1
• Time in Patent Office: 1,580 Days
• Field of Search: 382103-104, 382141-149, 382/154
• US Class Current: 382/104
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: H04N 13/194 Transmission of image signals
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 13/246 Calibration of cameras
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals

Abstract

A method and a device for the detection of obstruction in image sensor systems made up of at least two image sensors, which record essentially the same scene. If at least one image feature of the respective images differs unacceptably between the respective images, a signal is generated indicating the obstruction.

Claims

1. A method for the detection of an obstruction in an image sensor system, comprising:

providing at least two image sensors, the at least two image sensors recording essentially the same scene; and

generating a signal indicating an obstruction of only one of the image sensors if images generated by the two image sensors deviate unacceptably from one another in at least one feature.

2. The method according to claim 1, wherein the feature is a list of detected objects.

3. The method according to claim 1, wherein the feature is gray-scale values of individual pixels of each of the images.

4. The method according to claim 3, further comprising ascertaining image differences from the gray-scale values of the images by determining one of (a) pixel differences and (b) a correlation of the images.

5. The method according to claim 1, wherein the at least one feature includes image features represented as feature vectors which are compared to one another.

6. The method according to claim 1, further comprising:

ascertaining a measure of a difference of the two images from the at least one feature ascertained; and

comparing the measure of the difference to a predefined threshold, an obstruction being detected when the threshold is exceeded.

7. The method according to claim 1, further comprising detecting an unacceptable difference in the at least one feature if one existing difference changes in an abrupt manner.

8. A method for the detection of an obstruction in an image sensor system, comprising:

providing at least two image sensors, the at least two image sensors recording essentially the same scene; and

generating a signal indicating an obstruction of at least one of the image sensors if images generated by the image sensors deviate unacceptably from one another in at least one feature, wherein the feature is a histogram of gray-scale values of each of the images.

9. A device for the detection of an obstruction in an image sensor system having at least two image sensors which record essentially the same scene, the device comprising:

an evaluation unit for evaluating images generated by the image sensors and for generating a signal indicating an obstruction of only one of the image sensors if at least one feature deviates unacceptably in the images of the two image sensors.

10. The device according to claim 9, wherein the image sensor system is a stereo camera system in a motor vehicle.