TIRE DETECTION FOR ACCURATE VEHICLE SPEED ESTIMATION

• US 20130294643A1
• Filed: 05/03/2012
• Published: 11/07/2013
• Est. Priority Date: 05/03/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Fan, Zhigang, Wu, Wencheng
• Granted Patent: US 9,052,329 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G01P 3/38 using photographic means
• CPC Class Codes: G01P 3/68 using optical means, i.e. using infrared, visible, or ultraviolet light G01P3/80 takes precedence ; by reflection of waves G01S17/58
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

In some aspects of the present application, a computer-implemented method for determining the speed of a motor vehicle in a vehicle speed detection system is disclosed. The method can include receiving a plurality of images of a motor vehicle traveling on a road, each of the images being separated in time by a known interval; determining, for each of at least two of the images, a point of contact where a same tire of the vehicle contacts a surface of the road based, in part, on one or more identified features of the vehicle in one or more of the plurality of images; and using the points of contact and the time interval separations to calculate a speed at which the vehicle is traveling on the road.

Claims

1. A computer-implemented method for determining the speed of a motor vehicle in a vehicle speed detection system, the method comprising:

receiving a plurality of images of a motor vehicle traveling on a road, each of the images being separated in time by a known interval;

determining, for each of at least two of the images, a point of contact where a same tire of the vehicle contacts a surface of the road based, in part, on one or more identified features of the vehicle in one or more of the plurality of images; and

using the points of contact and the time interval separations to calculate a speed at which the vehicle is traveling on the road.

2. The method according to claim 1, wherein determining the point of contact comprises:

determining a first two-dimensional estimated position at a first time at which a tire of the vehicle contacts a surface upon which it is situated in a first frame of a video image taken with a camera;

calculating a first three-dimensional position at the first time based on the two-dimensional position using a geometry of the camera with respect to the vehicle;

determining a second two-dimensional estimated position at a second time at which the tire of the vehicle contacts the surface in a second frame of the video image;

calculating a second three-dimensional position at the second time based on the second two-dimensional position using the geometry of the camera with respect to the vehicle; and

determining the estimated speed at which the vehicle is traveling using the first and the second three-dimensional positions and a time difference between which the first and the second two-dimensional positions were estimated.

3. The method according to claim 2, further comprising determining a first edge, a second edge, or both the first edge and the second edge of the tire to determine the first two-dimensional estimated position.

4. The method according to claim 2, further comprising determining a position of a license plate, a light fixture, or both the license plate and the light fixture of the vehicle.

5. The method according to claim 4, wherein the first two-dimensional estimated position is determined based, at least in part, on the position of the license plate, the light fixture, or both the license plate and the light fixture of the vehicle.

6. The method according to claim 1, wherein the camera is operable to detect radiation in a near infrared portion of the spectrum.

7. The method according to claim 1, wherein the images comprise any of:

still images captured at known time intervals, and video images captured at a known frame rate.

8. The method according to claim 1, further comprising calibrating the camera such that pixel locations of the captured images are known relative to real world coordinates.

9. The method according to claim 1, further comprising:

analyzing more than two images of the vehicle using contact points determined for each of a plurality of images over a plurality of time intervals; and

determining at least one of a mean speed, a median speed, a maximum speed and a minimum speed, for the vehicle from the analysis of more than two images.

10. The method according to claim 1, further comprising determining a time-varying speed for the vehicle using at least some of the images.

11. A system for determining the speed of a motor vehicle in a vehicle speed detection system, the system comprising:

an imaging system; and

a processor in communication with said video camera system and a memory, said processor executing machine readable instructions for performing;

receiving images captured using the imaging system, each of the images being separated in time by a known interval;

determining, for each of at least two of the images, a point of contact where a same tire of the vehicle contacts a surface of the road;

using the points of contact and the time interval separations to calculate a speed at which the vehicle is traveling on the road.

12. The system of claim 11, wherein the images comprise any of still images captured at known time intervals, and video images captured at a known frame rate.

13. The system of claim 11, further comprising calibrating the camera such that pixel locations of the captured images are known relative to real world coordinates.

14. The system of claim 11, further comprising:

analyzing more than two images of the vehicle using contact points determined for each of a plurality of images over a plurality of time intervals; and

determining at least one of a mean speed, a median speed, a maximum speed and a minimum speed, for the vehicle from the analysis of more than two images.

15. The system of claim 11, further comprising determining a time-varying speed for the vehicle using at least some of the images.

16. A computer implemented method for determining the speed of a motor vehicle in a vehicle speed detection system, the method comprising:

receiving a plurality of images of a moving vehicle, the images captured at known time intervals with each of the images being separated in time by a known interval, said images having been captured using an imaging system;

determining, for each of at least two of the images, a point of contact where a same tire of the vehicle contacts a surface of the road;

using the points of contact and the time interval separations to calculate a speed at which the vehicle is traveling on the road.

17. The computer implemented method of claim 16, further comprising calibrating the camera such that pixel locations of the captured images are known relative to real world coordinates.

18. The computer implemented method of claim 16, further comprising:

calculating a plurality of speeds for the vehicle using contact points determined for each of a plurality of images over a plurality of time intervals; and

determining an average speed for the vehicle from the plurality of speeds.

19. The computer implemented method of claim 16, further comprising determining a time-varying speed for the vehicle using at least a portion of the plurality of images.