Method for identification of traffic lane boundary

• US 20100161204A1
• Filed: 12/23/2008
• Published: 06/24/2010
• Est. Priority Date: 12/23/2008
• Status: Active Grant

• Current Assignee: National Chiao Tung University (Government of The Republic of China)
• Original Assignee: National Chiao Tung University (Government of The Republic of China)
• Inventors: Huang, Heng, Jou, Yow-Jen, Cho, Hsun-Jung, Tseng, Ming-Te, Chen, Yu-Kuang, Li, Rih-Jin, Lan, Chien-Lun, Hsu, Chia-Chun
• Granted Patent: US 8,116,968 B2
• Time in Patent Office: Days
• US Class Current: 701/117
• CPC Class Codes: G01S 13/91 for traffic control G01S13/93 takes precedence
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G08G 1/015 with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
• CPC Class Codes: G08G 1/048 with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector

Abstract

The invention provides a method for identification of traffic lane boundary. Firstly the microwave signal is received, and the noise reduction is treated for the microwave signal. Then the frequency domain information is employed to calculate the legal set of closed interval, in order to form the frequency span information. Finally, the probability density function model is employed to calculate the frequency span information in order to identify the traffic lane boundary.

Claims

1. A method for identification of traffic lane boundary, comprising:

receiving a microwave signal;

conducting a noise reduction, filtering an unnecessary frequency domain information from the microwave signal;

employing a frequency domain information to calculate a legal set of a closed interval to form a frequency span information; and

employing a probability density model to calculate the frequency span information in order to identify the traffic lane boundary.

2. The method according to claim 1, wherein the steps for employing the frequency domain information to calculate the legal set of closed interval, comprising:

calculating the closed interval formed by the frequency domain information; and

checking whether the distance between two closed intervals is smaller than a setting threshold value.

3. The method according to claim 2, wherein checking whether the distance between two closed intervals is smaller than a setting threshold value, if it is not, the two closed intervals are as different closed intervals.

4. The method according to claim 2, wherein checking whether the distance between two closed intervals is smaller than a setting threshold value, if it is, the two closed intervals are merged to a larger closed interval.

5. The method according to claim 1, wherein the legal set of the closed interval comprises checking a span of the closed interval meets a maximum threshold and minimum threshold of traffic lane width.

6. The method according to claim 5, wherein the minimum threshold is an acceptable minimum frequency span information.

7. The method according to claim 5, wherein the maximum threshold is a traffic lane width.

8. The method according to claim 1, wherein employing the frequency domain information to calculate the legal set of the closed interval, comprising:

carrying on a treatment of conflict information in order to adjust the frequency span information.

9. The method according to claim 8, wherein carrying on the treatment of conflict information, comprising:

comparing a boundary information of the closed interval to obtain a conflict information.

10. The method according to claim 8, wherein treatment of conflict information, comprising:

C_i=min{L[i], R[i]}, where C_i represents the conflict information, L[i], R[i] are formed by accumulated frequency span information.

11. The method according to claim 1, wherein the probability density function model is Gaussian Mixture Model.

12. The method according to claim 1, wherein the Gaussian Mixture Model is:

$p<br><br>\left(x|\mathrm{\Theta <br><br>},E_k\right)=\underset{m=1}{\overset{M}{\sum <br><br>}}<br><br>{\mathrm{\alpha <br><br>}}_m<br><br>g\left(x;<br><br>{\mathrm{\mu <br><br>}}_m,\underset{m}{\sum <br><br>}<br><br>,E_k\right),$

wherein α

₁ to α

_m represent non-negative weight, sum is 1, μ

_m is mean value, and σ

_m is Gaussian parameter of M_th.

13. A method for identification of traffic lane boundary, comprising:

forming a frequency span information;

carrying on a treatment of conflict information to adjust the frequency span information; and

employing a probability density function model to calculate the frequency span information in order to identify traffic lane boundary.

14. The method according to claim 13, wherein forming the frequency span information, further comprising:

conducting a noise reduction for a microwave signal, filtering out a unnecessary frequency domain information;

employing a frequency domain information to calculate a legal set of a closed interval;

setting a maximum width for the closed interval to form a frequency span information; and

setting a minimum acceptable width for the closed interval to form the frequency span information.