Detecting and recognizing traffic signs

• US 8,064,643 B2
• Filed: 12/06/2007
• Issued: 11/22/2011
• Est. Priority Date: 12/06/2006
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: Mobileye Technologies Limited (Intel Corporation)
• Inventors: Stein, Gideon P., Wolfovitz, Uri, Shachar, Ori, Taieb, Yoav
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US11/951,405
• Publication Number:
  US 20080137908A1
• Time in Patent Office: 1,447 Days
• Field of Search: 382/103, 382/104, 382/181, 382/107, 701/96
• US Class Current: 382/104
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G08G 1/0967 Systems involving transmission of highway information, e.g. weather, speed limits transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element

Abstract

A method for detecting and identifying a traffic sign in a computerized system mounted on a moving vehicle. The system includes a camera mounted on the moving vehicle. The camera captures in real time multiple image frames of the environment in the field of view of the camera and transfers the image frames to an image processor. The processor is programmed for performing the detection of the traffic sign and for performing another driver assistance function. The image frames are partitioned into the image processor into a first portion of the image frames for the detection of the traffic sign and into a second portion of the image frames for the other driver assistance function. Upon detecting an image suspected to be of the traffic sign in at least one of said image frames of the first portion, the image is tracked in at least one of the image frames of the second portion.

Claims

1. A method identifying a traffic sign using a computerized system mounted on a moving vehicle, the system including a camera mounted on the moving vehicle, wherein the camera captures in real time a plurality of image frames of the environment in the field of view of the camera and transfers the image frames to an image processor, the method comprising the steps of:

(a) programming the processor for performing the detecting of the traffic sign and for performing another driver assistance function;

(b) first partitioning a first portion of the image frames to the image processor for the detecting of the traffic sign and second partitioning a second portion of the image frames for said other driver assistance function; and

(c) upon detecting an image suspected to be of the traffic sign in at least one of said image frames of said first portion, tracking said image in at least one of said image frames of said second portion.

2. The method, according to claim 1, wherein said first partitioning includes first setting a camera parameter for the detecting of the traffic sign while capturing said image frames of said first portion, and wherein said second partitioning includes second setting said camera parameter for said other driver assistance function while capturing said image frames of said second portion, wherein said first setting and said second setting have different values for said camera parameter, whereby said tracking is performed without altering said values of said camera parameter.

3. The method, according to claim 1, wherein said other driver assistance function is provided by a forward collision warning system which measures from said second portion of the image frames a distance to a lead vehicle, wherein said image scales with said distance, further comprising the step of:

(d) flagging said image as irrelevant, by associating said image to be of an object attached to said lead vehicle.

4. The method, according to claim 1, wherein said other driver assistance function is provided by a lane departure warning system from which is determined the lane in which the moving vehicle is traveling, wherein said image is of a traffic sign associated with another lane of traffic other than said lane, further comprising the step of:

(d) flagging said image as irrelevant, by associating said image as an image of traffic sign for said other lane of traffic.

5. The method, according to claim 1, wherein said other driver assistance function is provided by an ego-motion system which estimates from said second portion of the image frames an ego-motion including a translation in the forward direction and rotation of the moving vehicle,

(e) performing said tracking while calibrating at least in part the effect of said ego-motion;

(f) flagging said image as irrelevant, if after said tracking and said calibrating, the motion of said image between said image frames of said second portion is inconsistent with a static traffic sign.

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

(e) classifying said image based on at least one of shape or color.

7. The method, according to claim 6, further comprising the step of, prior to said classifying:

(f) by using a group of known images of traffic signs, training a classifier for performing said classifying.

8. The method, according to claim 6, wherein said shape is a circle, and wherein said traffic sign is a circular traffic sign, further comprising the step of:

(e) based on an output of said classifier, deciding that said circular traffic sign is a speed limit circular traffic sign.

9. The method, according to claim 6, wherein said classifying said circular traffic sign as a speed limit traffic sign is performed by a non-binary classifier.

10. The method, according to claim 8, wherein the moving vehicle is equipped with a global positioning system which provides world coordinates to the moving vehicle, further comprising the step of:

(f) verifying at least one of said detecting, said classifying or said deciding based on said world coordinates.

11. The computerized system mounted on a moving vehicle, the system including a camera mounted on the moving vehicle, wherein the camera captures in real time a plurality of image frames of the environment in the field of view of the camera and transfers the image frames to an image processor, the computerized system used to perform the method steps of claim 1.

12. A method for identifying a traffic sign, using a computerized system mounted on a moving vehicle, the system including a camera mounted on the moving vehicle, wherein the camera captures in real time a plurality of image frames of the environment in the field of view of the camera and transfers the image frames to an image processor, the method comprising the steps of:

(a) programming the processor for performing the detecting of the traffic sign and for performing another driver assistance function;

(b) first partitioning a first portion of the image frames to the image processor for the detecting of the traffic sign and second partitioning a second portion of the image frames for said other driver assistance function, wherein said first partitioning includes first setting a camera parameter for the detecting of the traffic sign while capturing said image frames of said first portion, and wherein said second partitioning includes second setting said camera parameter for said other driver assistance function while capturing said image frames of said second portion; and

(c) upon detecting an image suspected to be of the traffic sign in at least one of said image frames of both said first and said second portions, tracking said image in at least one of said image frames from either said first or from said second portions, whereby said tracking is performed without altering said camera parameter by the driver assistance system which performs said other driver assistance function.

13. A method performed using a computerized system mounted on a moving vehicle, the system including a camera mounted on the moving vehicle, wherein the camera captures in real time a plurality of image frames of the environment in the field of view of the camera and transfers the image frames to an image processor, the method comprising the steps of:

programming the image processor for detecting a traffic sign and for performing another driver assistance function;

partitioning a subset of the image frames for said other driver assistance function; and

upon said detecting an image suspected to be of a traffic sign in at least one of said image frames not in said subset, classifying the image selectably either as a traffic sign or not as a traffic sign by using said subset of the image frames partitioned for said other driver assistance function.