Vehicle lane position detection system

• US 5,351,044 A
• Filed: 08/12/1992
• Issued: 09/27/1994
• Est. Priority Date: 08/12/1992
• Status: Expired due to Term

• Current Assignee: Bendix Commercial Vehicle Systems LLC (Estate of Heinz Hermann Thiele)
• Original Assignee: Rockwell International Corporation
• Inventors: Haendel, Richard S., Mathur, Bimal P., Wang, H. Taichi
• Primary Examiner(s): Crosland, Donnie L.
• Application Number:
  US07/928,819
• Time in Patent Office: 776 Days
• Field of Search: 340/901, 340/937, 340/903-905, 340/942, 340/436, 340/437, 340/555, 340/556, 340/687, 358/108, 358/110, 358/125, 358/213.15, 358/213.27, 382/30, 382/67, 382/48, 382/65, 382/34, 382/35, 348/135, 348/143, 348/148, 348/149
• US Class Current: 340/901
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

A low cost, real time vehicle lane position detection system is provided for determining and maintaining the position of the vehicle on a highway. The system comprises an image sensor mounted on the front of an automotive vehicle and an integrated processor for performing real-time lane mark detection. The sensor/processor system identifies highway lane marks on the detector image plane by using a nonlinear resistive network for detecting outliers. A line detection algorithm, such as the Hough transform, is used to determine the lane marks from the outliers on the image plane. Because the expected lane position can be determined in advance, an added degree of signal-to-noise discrimination is achieved by providing feedback to the processor for outlier detection. The position of the vehicle in the lane is determined and tracked from the position of the detected lane marks on the image plane given the sensor position and optical geometry.

Claims

1. A highway lane position detecting system for an automotive vehicle, comprising:

a sensor array comprising a plurality of sensor elements mounted on the vehicle for generating an image of the highway lane ahead of the vehicle, said image comprising data values input from said plurality of sensor elements;

a resistive network comprising a plurality of nodes connected to said sensor array for receiving said input data values and providing smoothed data values on said nodes;

a plurality of data paths, each of said data paths including a data path switch connecting one of said sensor elements to a corresponding network node;

means connected to each of said data paths for opening said data path switch when the difference between said sensor input data value and said smoothed data value on said corresponding node exceeds a predetermined value;

a microprocessor connected to said resistive network for determining position of said open switches in said image; and

said microprocessor using said open switch positions in said image for computing and outputting data in real time indicating position of the vehicle in the highway lane.

2. The system of claim 1, wherein each of said switch opening means comprises a comparator, said comparator connected to receive data values from said sensor element and said corresponding network node.

3. A method of determining position of an automotive vehicle in a highway lane, comprising the steps of:

mounting a sensor array comprising a plurality of sensor elements on the vehicle;

generating an image of the highway lane ahead of the vehicle, said image comprising data values input from said plurality of sensor elements;

providing a resistive network having a plurality of nodes;

connecting each of said sensor elements to a corresponding node of said resistive network with a data path having a data path switch;

smoothing said input data values to provide smoothed data values on said nodes of said resistive network;

opening said data path switch in each of said data paths where the difference between said sensor input data value and said smoothed data value on said corresponding node exceeds a predetermined value;

determining position of said open switches in said image; and

computing and outputting data in real time indicating position of the vehicle in the highway lane based on said open switch positions in said image.

4. The method of claim 3, further comprising the step of connecting a comparator to receive and compare data values from said sensor element and said corresponding network node and to open said data path switch.

5. The method of claim 3, wherein the step of computing and outputting data further comprises the step of performing a Hough transform.

6. The method of claim 5, wherein the step of computing and outputting data further comprises the step of providing feedback from said Hough transform for adjusting said predetermined value for opening said switches.

7. The method of claim 3, further comprising the step of tracking position of the vehicle in the highway lane.

8. The method of claim 7, further comprising the steps of monitoring and controlling position of the vehicle in the highway lane.

9. A method of determining position of an automotive vehicle in a highway lane, comprising the steps of:

mounting a sensor array comprising a plurality of sensor elements on the vehicle;

generating an image of the lane ahead of the vehicle from said sensor array, said image comprising data values input from said plurality of sensor elements;

connecting a resistive network to said sensor array with a plurality of data path switches, said resistive network comprising a plurality of nodes, each of said nodes connected to a corresponding one of said sensor elements by one of said data path switches;

smoothing said input data values to provide smoothed data values on said nodes;

opening corresponding ones of said data path switches when the difference between said smoothed data value on said node and said corresponding sensor input data value exceeds a predetermined value;

performing a transform to determine highway lane marks from the positions of said open data path switches in said image;

determining position of said highway lane marks in said image; and

computing and outputting data in real time indicating position of the vehicle in the highway lane based on said highway lane mark position in said image.

10. The method of claim 9, wherein the step of performing a transform comprises the step of performing a Hough transform.

11. The method of claim 10, wherein the step of determining position of said highway lane marks in said image further comprises the step of providing feedback from said Hough transform for adjusting said predetermined value for opening said data path switches.

12. The method of claim 11, further comprising the step of tracking position of the vehicle in the highway lane.

13. The method of claim 12, further comprising the steps of monitoring and controlling position of the vehicle in the highway lane.