Method and system for measuring the speed of a vehicle

• US 8,964,031 B2
• Filed: 08/17/2010
• Issued: 02/24/2015
• Est. Priority Date: 08/17/2009
• Status: Active Grant

• Current Assignee: Neology Incorporated (OEP Technologie BV)
• Original Assignee: 3M Innovative Properties Company (3M Company)
• Inventors: Smith, Brian David Vincent, Clucas, Alan
• Primary Examiner(s): Dastouri, Mehrdad
• Assistant Examiner(s): DOBBS, KRISTIN SENSMEIER
• Application Number:
  US13/390,429
• Publication Number:
  US 20120206602A1
• Time in Patent Office: 1,652 Days
• US Class Current: 348/143
• 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 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G08G 1/052 with provision for determining speed or overspeed speed measuring in general G01P

Abstract

A system for measuring the speed of a vehicle includes: one or more cameras (200) for capturing images of vehicles (100) on a road (50); timing means for timing the capture of the images; a processor arranged to: identify in the captured images a feature (150) of the vehicle; calculate the size in pixels of the feature (150) of the vehicle in two or more of the captured images; and determine the speed of the vehicle (100) based at least in part on the calculated sizes and the times at which each image was captured.

Claims

1. A system for measuring the speed of a vehicle having a feature of known size, comprising:

one or more cameras for capturing images of vehicles on a road;

timing means for timing the capture of the images;

a processor arranged to operate in at least a calibration mode and a monitoring mode,

wherein;

(i) in the calibration mode the processor;

identifies in the captured images the feature of a vehicle;

calculates the size in pixels of the feature of the vehicle in two or more of the captured images;

receives as an input the vehicle'"'"'s geodesic distance along the road at the times of capture of the captured images; and

generates a look-up table or function correlating the calculated size of the feature to the vehicle'"'"'s geodesic distance along the road; and

(ii) in the monitoring mode the processor;

identifies in the captured images the feature of the vehicle;

calculates the size in pixels of the feature of the vehicle in two or more of the captured images;

determines the vehicle'"'"'s geodesic distance along the road in each image by using the calculated sizes as an input to the generated look-up table or function; and

determines the speed of the vehicle based on the determination of the vehicle'"'"'s geodesic distance along the road in each image and the times at which each image was captured.

2. A system as claimed in claim 1 wherein the processor is arranged to determine from at least one of the captured images a vertical position of the identified vehicle feature in the image and the speed of the vehicle is determined using the determined vertical position as an input to the look-up table or function.

3. A system as claimed in claim 1 wherein the processor is arranged to determine from at least one of the captured images a horizontal position of the identified vehicle feature in the image and the speed of the vehicle is determined using the determined horizontal position as an input to the look-up table or function.

4. A system as claimed in claim 1 which can measure the speed of a vehicle on a multi-lane road and in which the processor identifies which lane is occupied by the vehicle and the speed of the vehicle is determined from the captured images based upon the lane occupied by the vehicle.

5. A system as claimed in claim 1, comprising one camera which captures at least two images of the vehicle.

6. A system as claimed in claim 1, comprising more than one camera, each of which captures at least one image of the vehicle.

7. A system as claimed in claim 1, wherein:

in the calibration mode;

the one or more cameras capture(s) a plurality of images of a calibration vehicle which has distance of travel measuring means, the calibration vehicle comprising a part of the system when the system is operating in the calibration mode;

the plurality of images are captured for differing distances of the calibration vehicle from the camera(s);

the input means receives from the distance of travel measuring means inputs indicative of the geodesic distance along the road from the camera(s) to the calibration vehicle;

the processor identifies in the captured images a feature of the calibration vehicle;

the processor correlates each captured image with an indicated geodesic distance along the road;

the processor calculates the size in pixels of the feature of the vehicle in each captured image;

the processor generates a look-up table which stores the calculated sizes correlated to the indicated geodesic distances along the road, and

in the monitoring mode;

the one or more cameras capture(s) a plurality of images of a vehicle at a plurality of different known times;

the timing means records the times of the captured images;

the processor identifies in the captured images a feature of the vehicle;

the processor calculates the size in pixels of the feature of the vehicle in two or more of the captured images; and

the processor determines the speed of the vehicle from the two or more captured images using the calculated sizes to determine from the generated look-up table the geodesic distances along the road between the camera(s) and the vehicle, the processor calculating a distance of travel of the vehicle between the captured images and using the distance of travel and the times at which each image was captured to determine the speed of the vehicle.

8. A system as claimed in claim 1, wherein:

for the vehicle, a pair of images are captured; and

the speed of the vehicle is determined by;

calculating the geodesic distance travelled along the road by the vehicle in a known period of time by determining the vehicle'"'"'s geodesic distance along the road corresponding to the first captured image from the size in pixels of the feature in the first captured image, determining the vehicle'"'"'s geodesic distance along the road corresponding to the second captured image from the size in pixels of the feature in the second captured image and the recorded times of image capture, and thereby determining the speed of the vehicle.

9. A system as claimed in claim 1, wherein:

the system is configured to operate in at least a calibration mode and a monitoring mode; and

in the calibration mode;

the one or more cameras capture(s) a plurality of images of a calibration vehicle which has distance of travel measuring means, the calibration vehicle comprising a part of the system when the system is operating in the calibration mode;

the plurality of images are captured for differing geodesic distances along the road of the calibration vehicle from the camera(s);

the input means receives from the distance of travel measuring means inputs indicative of the geodesic distance along the road from the camera(s) to the calibration vehicle;

the processor identifies in the captured images a feature of the calibration vehicle;

the processor correlates each captured image with an indicated geodesic distance along the road;

the processor calculates the vertical position and/or horizontal position of the feature of the vehicle in each captured image;

the processor calculates the size in pixels of the feature of the vehicle in each captured image;

the processor generates a look-up table which stores the calculated the vertical positions and/or horizontal positions and the calculated sizes correlated to the indicated geodesic distances along the road, and

in the monitoring mode;

the one or more cameras capture(s) a plurality of images of a vehicle at a plurality of different known times;

the timing means records the times of the captured images;

the processor identifies in the captured images a feature of the vehicle;

the processor calculates the vertical positions and/or horizontal positions of the feature of the vehicle in two or more of the captured images;

the processor calculates the size in pixels of the feature of the vehicle in the two or more of the captured images; and

the processor determines the speed of the vehicle from the two or more captured images using the calculated vertical positions and/or the calculated horizontal positions and the calculated sizes to determine from the generated look-up table the geodesic distances along the road between the camera(s) and the vehicle, the processor calculating a distance of travel of the vehicle between the captured images and using the distance of travel and the times at which each image was captured to determine the speed of the vehicle.

10. A system as claimed in claim 1, wherein the identified feature is a license plate of the vehicle.

11. A system as claimed in claim 10, wherein the calculated size in pixels of the license plate is the width in pixels of the license plate.

12. A system as claimed in claim 10, wherein the calculated size in pixels of the license plate is the length in pixels of a diagonal of the license plate.

13. A system as claimed in claim 10, wherein the calculated size in pixels of the license plate is the area in pixels of the license plate.

14. A system as claimed in claim 1 comprising a single camera.

15. A system as claimed in claim 7 comprising at least two cameras, wherein in the monitoring mode one or more of the at least two images is captured by the first camera and one or more other(s) of the at least two images is captured by the second camera.

16. A traffic monitoring system comprising:

a system for measuring the speed of a vehicle according to claim 1, wherein the feature of the vehicle is a license plate;

a license plate detector for detecting the license plate of a vehicle in the captured images; and

an automatic license plate recognition system which reads characters in the license plate detected in each image.

17. A traffic monitoring system as claimed in claim 16, wherein the processor determines an aspect ratio of the detailed license plate and the step of determining the speed of the vehicle is also based in part on the determined aspect ratio.

18. A method of measuring the speed of a vehicle having a feature of known size, comprising:

capturing a plurality of images of the vehicle;

timing the capturing of the plurality of images;

in a calibration mode;

identifying in the captured images the feature of the vehicle;

calculating the size in pixels of the feature of the vehicle in two or more of the captured images; and

generating a look-up table or function that correlates the calculated size of the feature to the vehicle'"'"'s geodesic distance along the road to determine the vehicle'"'"'s position on the road from each image; and

in a monitoring mode;

identifying in the captured images the feature of the vehicle;

calculating the size in pixels of the feature of the vehicle in two or more of the captured images;

using the look-up table or function that correlates the calculated size of the feature to the vehicle'"'"'s geodesic distance along the road to determine the vehicle'"'"'s position on the road from each image; and

determining the speed of the vehicle using the determination of the vehicle'"'"'s geodesic distance on the road from each image and the times at which each image was captured.

19. The method of claim 18, wherein:

for the vehicle, a pair of images are captured; and

the speed of the vehicle is determined by;

calculating the distance travelled by the vehicle in a known period of time based on the size in pixels of the feature in the first captured image and the size in pixels of the feature in the second captured image, and thereby determining the speed of the vehicle.

20. The method of claim 19, wherein the known period of time is the period between the first image capture and the second image capture.

21. The method of claim 18, wherein the feature is a license plate of the vehicle.

22. The method of claim 21, wherein the calculated size in pixels of the license plate is the width in pixels of the license plate.

23. The method of claim 21, wherein the calculated size in pixels of the license plate is the length in pixels of a diagonal of the license plate.

24. The method of claim 21, wherein the calculated size in pixels of the license plate is the area in pixels of the license plate.

25. The method of claim 18, wherein the determination of the speed of the vehicle is also based on the vertical position in pixels of the feature in each image.

26. The method of claim 18, wherein the determination of the speed of the vehicle is also based on the horizontal position in pixels of the feature in each image.

27. The method of claim 18, wherein the first of the at least two images and the second of the at least two images are captured with the same camera.

28. The method of claim 18, wherein all images are captured with the same camera.

29. The method of claim 18, wherein the first of the at least two images and another of the at least two images are captured with different cameras.