METHOD FOR PREDICTING LANE LINE AND LANE DEPARTURE WARNING SYSTEM USING THE SAME

• US 20090058622A1
• Filed: 01/25/2008
• Published: 03/05/2009
• Est. Priority Date: 08/30/2007
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: LIAO, YUNG-SHENG, HSIEH, HSI-WEN, LIN, CHE-CHUNG, LIN, CHI-WEI, HUANG, DAU-CHEN
• Granted Patent: US 8,687,063 B2
• Time in Patent Office: Days
• US Class Current: 340/435
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• 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

A method for predicting lane line is provided in the present invention, in which the method is capable of predicting and reconstructing the unidentified lane line according to a predetermined geometry relationship based on the recognized lane line data previously while one side of lane line is unable to be identified. In one embodiment, a lane predicting relationship formula is formed by describing the geometry relationship between the two identified lines defined the lane. When the one side of line of the lane is unable to be identified, a new predicted line can be reconstructed for representing the unidentified line of lane according to the lane predicting relationship curve. In another embodiment, a lane departure warning system utilizing the foregoing method is provided for monitoring vehicle moving status and alerting the driver so as to enhance the vehicle safety.

Claims

1. A method for predicting lane line, comprising the steps of:

providing two lane predicting relationship curves;

imaging lane lines of a lane and measuring a characteristic value of an identifiable lane line of the lane lines when there is only one lane line of the imaged lane lines that is identifiable; and

reconstructing an unidentifiable lane line to complete the lane image by applying the measured characteristic value into the two lane predicting relationship curves.

2. The method of claim 1, wherein the characteristic value is to a distance measured between the identifiable lane line and a virtual center line of the lane.

3. The method of claim 1, wherein the two lane predicting relationship curves is determined by the process comprising the steps of:

providing a plurality of lane line images of a lane;

acquiring a plural sets of distance information while each set includes a distance measured between a left lane line and a virtual center line of the lane, a distance measured between a right lane line and the virtual center line of the lane; and

performing a numerical analysis upon the plural sets of distance information for obtaining the two lane predicting relationship curves.

4. The method of claim 1, wherein the two lane predicting relationship curves is determined by the process comprising the steps of:

determining the types of the two lane predicting relationship curves;

imaging at least two lane images with a complete left lane line and a complete right lane line;

acquiring two consecutive sets of distance information while each distance set includes a distance measured between the left lane line and a virtual center line of the lane, a distance measured between the right lane line and the virtual center line of the lane; and

performing a numerical analysis upon the two sets of distance information to obtain parameters of the two lane predicting relationship curves.

5. The method of claim 1, further comprise a step for displaying the reconstructed lane line.

6. The method of claim 1, further comprises a step of:

making an evaluation to determining whether the status of the lane remain unchanged; and

dynamically updating the lane predicting relationship curves when the status of the lane is changed.

7. The method of claim 6, wherein the updating of the lane predicting relationship curves further comprises the steps of:

acquiring a plural sets of distance information from a plurality of newly fetched lane images, while each set includes a distance measured between a left lane line and a virtual center line of the lane, a distance measured between a right lane line and the virtual center line of the lane; and

performing a numerical analysis to obtain updated types of the lane predicting relationship curves and the parameters thereof;

8. The method of claim 6, wherein the updating of the lane predicting relationship curves further comprises the steps of:

acquiring a plural sets of distance information from a plurality of newly fetched lane images, while each set includes a distance measured between a left lane line and a virtual center line of the lane, a distance measured between a right lane line and the virtual center line of the lane; and

performing one process selected from the group consisting of;

performing a numerical analysis to obtain new lane predicting relationship curves and the parameters thereof; and

basing on the previously obtained types of the two lane predicting relationship curves to perform a numerical analysis so as to obtain parameters to be used as basis for dynamically updating the lane predicting relationship curves.

9. A lane departure warning system, comprising:

at least a front imaging unit, for imaging an image of lane lines of a lane on which a vehicle travels;

a vehicle status detecting unit, for detecting a status of the vehicle and thus generating a detection signal;

an image processing/controlling module, capable of performing an operation based upon the image of lane line and the detection signal so as to generate an alarm signal;

a displaying unit, coupled to the image processing/controlling module for receiving signals from the image processing/controlling module and thus displaying an image of lane line according; and

an alerting unit, coupled to the image processing/controlling module for receiving the alarm signal and thus generating an alarm;

wherein the image processing/controlling module is configured to reconstruct an unidentifiable lane line to complete the lane image according to a lane predicting relationship curve when there is only one lane line of the lane line image that is identifiable.

10. The system of claim 9, wherein the front imaging unit is substantially a camcorder.

11. The system of claim 10, wherein the camcorder is a device selected from the group consisting of a charge-coupled device (CCD), and a complementary metal-oxide semiconductor (CMOS).

12. The system of claim 9, wherein the front imaging unit is substantially an infrared imaging unit.

13. The system of claim 9, wherein the alarm generated by the alerting unit for alerting is a response selected from the group consisting of a sound, a light, a vibration.

14. The system of claim 9, further comprising:

a control unit, provided to be used by a user as a control interface for disarming the alarm and adjusting system parameters.

15. The system of claim 9, wherein the image processing/controlling module further comprises:

an image fetching/decoding unit, coupled to the front imaging unit for converting the lane line image into a digital image data;

a digital signal processing/controlling unit, for analyzing the digital image data received from the image fetching/decoding unit; and

an image encoding/outputting unit, coupled to the digital signal processing/controlling unit and the displaying unit for enabling the same to receive a control signal from the digital signal processing/controlling unit while using the control signal for image encoding and thus outputting an output image data to the displaying unit.

16. The system of claim 9, wherein the image processing/controlling module further comprises:

an image random access memory, for storing the digital image data and a processed image data, being the image data processed and outputted from the digital signal processing/controlling unit, in a manner that it is used for providing the digital image data to the digital signal processing/controlling unit and the process image data to the image encoding/outputting unit; and

a non-volatile programmable memory, for registering the analysis result of lane line information received from the digital signal processing/controlling unit.

17. The system of claim 15, wherein the digital signal processing/controlling unit is configured to transmit a lane line recognition data and an abnormal driving data to the displaying unit.

18. The system of claim 17, wherein the lane line recognition data includes data of vehicle departure, turning orientation and lane curvature.

19. The system of claim 9, wherein the image processing/controlling module is capable of dynamically updating the lane predicting relationship curves.

20. The system of claim 9, wherein the vehicle status is a measurement selected from the group consisting speed, brake signal, turning signal and the combination thereof.