IMAGE ACQUISITION AND PROCESSING SYSTEM FOR VEHICLE EQUIPMENT CONTROL

• US 20120072080A1
• Filed: 10/17/2011
• Published: 03/22/2012
• Est. Priority Date: 11/18/2004
• Status: Active Grant

• Current Assignee: Gentex Corporation
• Original Assignee: Gentex Corporation
• Inventors: JEROMIN, OLIVER, CURRIE, STEVEN, BUSH, GREGORY S., WALSTRA, ERIC J., STAM, JOSEPH S., CORNELL, TIMOTHY S.
• Granted Patent: US 8,924,078 B2
• Time in Patent Office: Days
• US Class Current: 701/49
• CPC Class Codes: B60Q 1/143 combined with another condition, e.g. using vehicle recognition from camera images or activation of wipers
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

An image acquisition and processing system includes an image sensor and one or more processors that are configured to receive at least a portion of at least one image from the image sensor. The dynamic aim of the image sensor is configured as a function of at least one feature extracted from at least a portion of an image. To accomplish the task, the system utilizes a series of adaptive thresholds used in parallel comparators to determine whether or not a pixel in a given image scene falls on the edge of a given lane line on a road. The location of the lane lines are then used to determine the scene vanishing point, which ideally will be co-located at the optical scene center. If they are not in agreement, the pixel data set being processed can be adjusted to accommodate for any disagreement.

Claims

1. A vehicular imaging system comprising:

at least one image sensor;

at least one processor configured to receive at least a portion of at least one image from the at least one image sensor such that a dynamic aim of the at least one image sensor is configured as a function of a lane marker detected from at least one threshold in the at least one image; and

wherein the at least one processor is further configured to generate at least one vehicle equipment control signal as a function of the lane marker.

2. A vehicular imaging system as in claim 1, wherein the at least one threshold is an intensity threshold.

3. A vehicular imaging system as in claim 1, wherein the at least one threshold is a gradient threshold.

4. A vehicular imaging system as in claim 1, wherein pixels in the at least one image are compared to the thresholds for determining lane line edge location.

5. A vehicular imaging system as in claim 1, wherein the at least one processor is a field programmable gate array (FPGA) for calculating a gradient approximation of at least one pixel in the at least one image and comparing the at least one pixel and the gradient approximation to the at least one threshold.

6. A vehicular imaging system as in claim 1, wherein lane line points used in determining a lane marker are processed using a linear model for determining a vanishing point in an image.

7. A vehicular imaging system as in claim 1, wherein the thresholds adaptively change based on environmental lighting conditions.

8. A vehicular imaging system as in claim 1, wherein the threshold is adaptively changed based on road surface conditions.

9. A vehicular imaging system as in claim 1, wherein a left portion of the at least one image and the right portion of the at least one image are separately processed.

10. A vehicular imaging system as in claim 1, wherein the dynamic aim of the at least one image sensor is configured such that an adaptive lane edge detection is used for establishing a position of a center of a road captured in the at least one image.

11. A vehicular imaging system as in claim 1, wherein the system is one from the group of:

a headlight control system, a lane departure warning system (LDW), an object detection system and a blind zone detection system.

12. A vehicular vision system, comprising:

at least one image sensor;

at least one processor configured to receive at least a portion of at least one image from the at least one image sensor such that a dynamic aim of the at least one image sensor is adjusted as a function of at least one object detected by the at least one image sensor; and

wherein the object is at least one lane marker detected by comparing at least one pixel from the at least one image sensor to a plurality of adaptive thresholds.

13. A vehicular vision system as in claim 12, wherein the plurality of adaptive thresholds are based upon intensity and gradient of the at least one pixel from the at least one image sensor.

14. A vehicular vision system as in claim 12, wherein the at least one processor is a field programmable gate array (FPGA) for calculating a gradient approximation of at least one pixel in the at least one image and comparing the at least one pixel and the gradient approximation to the plurality of adaptive thresholds.

15. A vehicular vision system as in claim 12, wherein lane line points used in determining the at least one lane marker are processed using a linear model for determining a vanishing point in the at least one image.

16. A vehicular vision system as in claim 12, wherein the adaptive thresholds are changed based on at least one of current lighting conditions and current road conditions.

17. A vehicular vision system as in claim 12, wherein a left portion of the at least one image and the right portion of the at least one image are processed separately for determining lane edge location.

18. A vehicular vision system as in claim 12, wherein the dynamic aim of the at least one image sensor is configured such that an adaptive lane edge detection is used for establishing a position of a center of a road captured in the at least one image.

19. A vehicular vision system as in claim 12, wherein the system is one from the group of:

a headlight control system, a lane departure warning system (LDW), an object detection system and a blind zone detection system.

20. A method for detecting a road lane location in a vehicular imaging system comprising the steps of:

providing a plurality of pixels for an image using at least one image sensor;

configuring at least one processor to receive at least a portion of at least one image from the at least one image sensor;

comparing at least one pixel from the plurality of pixels to at least one threshold;

storing the pixel location of the portion of the at least one image if the at least one pixel meets the at least one threshold;

identifying a lane marker based on a plurality of grouped lane locations; and

dynamically aiming the at least one image sensor as a function of the identified lane marker.

21. A method for detecting a road lane location as in claim 20, further comprising the step of:

utilizing at least one of an intensity threshold and a gradient threshold in the at least one threshold.

22. A method for detecting a road lane location as in claim 20, further comprising the steps of:

utilizing a field programmable gate array (FPGA) as the processor for calculating a gradient approximation of at least one pixel in the at least one image; and

comparing the at least one pixel and the gradient approximation to the at least one threshold.

23. A method for detecting a road lane location as in claim 20, further comprising the step of:

fitting the grouped lane points to a linear model; and

determining a vanishing point in the at least one image.

24. A method for detecting a road lane location as in claim 20, further comprising the step of:

changing the adaptive thresholds based upon at least one of changing lighting conditions and changing road surface conditions.

25. A method for detecting a road lane location as in claim 20, further comprising the step of:

separately processing a left portion of the at least one image and a right portion of the at least one image.

26. A method for detecting a road lane location as in claim 20, further comparing the step of:

dynamically aiming the at least one image using an adaptive lane edge detection for establishing a position of a center of a road captured in the at least one image.

27. A method for detecting a road lane location as in claim 20, further comprising the step of:

using the method for detecting road lane location is one from the group of;

a headlight vision control system, a lane departure warning system (LDW), an object detection system and a blind zone detection system.