System and method for detection of average speed of vehicles for traffic control

• US 8,301,363 B2
• Filed: 10/16/2007
• Issued: 10/30/2012
• Est. Priority Date: 11/10/2006
• Status: Active Grant

• Current Assignee: Eng Celeritas S.r.l.
• Original Assignee: Eng Celeritas S.r.l.
• Inventors: Grassi, Nicola
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): Marc-Coleman, Marthe
• Application Number:
  US12/312,239
• Publication Number:
  US 20110313644A1
• Time in Patent Office: 1,841 Days
• Field of Search: 701/119, 701/117, 382/100, 382/176, 382/198, 382103-107, 382/161, 382/169, 382/171, 382/172, 382/174, 382/200, 382/270, 382/292, 348/149, 348/135, 348/159, 348/236, 340/937
• US Class Current: 701/119
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: G08G 1/054 photographing overspeeding vehicles

Abstract

The invention relates to a method and a system for identifying moving objects by employing a tag, said tag comprising at least alphanumeric characters and said tag being extracted from pictures taken by cameras located in at least two different points within a certain distance comprising extracting alphanumeric characters of said tag from the pictures taken by at least two cameras; converting said alphanumeric characters into other new characters of another representation space; creating a string of said new characters for each of the tags extracted from the pictures taken by the cameras at different locations, said cameras being synchronized and said pictures taken by the cameras within a predetermined time interval; comparing the strings by associating a correlation score; inputting a threshold score; identifying the moving object if the correlation score is over the predetermined threshold score.

Claims

1. A method for identifying a moving object by employing a tag, said tag comprising at least alphanumeric characters and said tag being extracted from pictures taken by cameras located in at least two different points within a certain distance, said cameras being synchronized and said pictures taken by the cameras within a predetermined time interval;

said method comprises extracting alphanumeric characters of said tag from the pictures taken by at least two cameras, said alphanumeric characters forming elements of a first representation space;

the method being characterized in that it further comprises;

converting said alphanumeric characters of the first representation space into other new characters of a second representation space;

creating a string of said new characters for each of the tags extracted from the pictures taken by the cameras at different locations;

comparing the strings by associating a correlation score;

inputting a threshold score;

identifying the moving object if the correlation score is over the predetermined threshold score.

2. The method of claim 1 wherein the second representation space has a number of elements which is lower than the number of elements of the first representation space.

3. The method of claim 2 wherein said predetermined time interval is lower than a predetermined threshold Time_h and higher than a predetermined threshold Time_1, said threshold Time_h being the time needed for the moving object to cover said certain distance at a predefined speed limit and said threshold Time_1 being the time needed for the moving object to cover said certain distance at a speed at least two times higher than said predefined speed limit.

4. The method of claim 3 wherein the identified moving object is considered as a speeding object and the pictures are sent to the law enforcement authorities.

5. The method of claim 4 wherein different moving objects are classified so that it is possible to associate different speed limits to different class of moving objects, preferably cars or trucks.

6. The method of claim 2 wherein the pictures taken from the said cameras comprise only a partial tag.

7. The method of claim 2 wherein said picture taken by each camera can be a picture of the front or of the back of the moving object.

8. The method of claim 1 wherein the function that converts said at least alphanumeric characters into new characters of the second representation space is non bijective.

9. The method of claim 8 wherein said predetermined time interval is lower than a predetermined threshold Time_h and higher than predetermined threshold Time_1, said threshold Time_h being the time needed for the moving object to cover said certain distance at a predefined speed limit and said threshold Time_1 being the time needed for the moving object to cover said certain distance at a speed at least two times higher than said predefined speed limit.

10. The method of claim 8 wherein the pictures taken from the said cameras comprise only a partial tag.

11. The method of claim 8 wherein said picture taken by each camera can be a picture of the front or of the back of the moving object.

12. A system for identifying a moving object comprising at least a couple of peripheral units able to detect the transit of the moving objects, a central unit comprising a computing system, a screen, a communication system with the peripheral units a camera for acquiring data tags related to the moving object transit, said data tags comprising at least alphanumeric characters forming elements of a first representation space, wherein the peripheral units comprise cameras taking pictures and a synchronization system for synchronizing the pictures taken by the cameras with a corresponding string of new characters;

an electronic memory unit for temporarily storing said string of new characters and the picture, before the strings of new characters and the pictures being sent to the central unit and computing system;

characterized in that;

said computing system of said peripheral units convert said alphanumeric characters of the first representation space into new characters of a second representation space and create a string of said new characters for each of the tags extracted from the pictures taken by said peripheral units; and

said computing system of said central unit associate the picture of each peripheral unit with the string of said second representation space and carry out a scoring algorithm from said created strings of new characters to identify the moving object.

13. The system for identifying moving objects of claim 12 further comprising:

induction coils with signal processing interface,

photoelectric cells with signal processing interface,

magnetic micro loops with signal processing interface,

lasers with signal processing interface,

infrared sensors with signal processing interface,

camera equipped with motion detection technique directly onboard, or

camera with signal processing equipment able to apply a motion detection technique.

14. The system for identifying moving objects of claim 12 further comprising an illumination system (22) or an infrared system for operatively use in absence of natural lighting or artificial lighting of the road.

15. The system for identifying moving objects of claim 12 wherein the synchronization system (23), employs satellite services to synchronize the clocks of the peripheral units.

16. The system for identifying moving objects of claim 12 wherein the peripheral unit comprises at least one elaboration unit (27) enabled to classify vehicles so that it is possible to associate different speed limits to different class of vehicles.

17. The system for identifying moving objects of claim 12 wherein a display is provided for displaying on the screen the string associated to said tag of said moving object.

18. The system for identifying moving objects of claim 12 wherein said cameras can be set to take pictures of the front or of the back of the moving objects.

19. An article of manufacture comprising a non-transitory program storage medium readable by a computer the medium tangibly embodying one or more programs of instructions executable by the computer to perform a method for identifying a moving object by employing a tag, the method comprising the steps of:

converting alphanumeric characters of a first representation space into other new characters of a second representation space;

creating a string of said new characters for each tags extracted from pictures taken by cameras at different locations;

comparing the strings by associating a correlation score;

inputting a threshold score;

identifying the moving object if the correlation score is over a predetermined threshold score.