Method and system for integrating multiple camera images to track a vehicle

• US 9,761,135 B2
• Filed: 08/14/2012
• Issued: 09/12/2017
• Est. Priority Date: 05/15/2012
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chen, Yi-Yuan, Chen, Jian-Ren, Chang, Leii H., Hung, Shang-Chih
• Primary Examiner(s): Lee, Michael
• Assistant Examiner(s): Khalid, Omer
• Application Number:
  US13/585,795
• Publication Number:
  US 20130307979A1
• Time in Patent Office: 1,855 Days
• Field of Search: 348143, 348148, 348153, 348159, 382103, 382104, 382105
• CPC Class Codes: B60R 25/305 using a camera
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules

Abstract

A method and a system for integrating multiple camera images to track a vehicle are provided. In the method, a security request of a vehicle to be tracked is received from a user, in which the security request comprises registration information and position information of the vehicle. Next, images captured by multiple cameras in a specific range around a location of the position information are retrieved. The retrieved images are analyzed according to the registration information, so as to recognize the images comprising the vehicle. Finally, a message is issued when the images comprising the vehicle are recognized.

Claims

1. A method for integrating multiple camera images to track a vehicle, adapted to a server having a request processing unit, an image capturing unit, an image processing unit, and an analyzing unit, for tracking the vehicle by using images captured by a plurality of cameras, the method comprising:

receiving a request to track the vehicle by the request processing unit, wherein the request comprises a registration information and a position information of the vehicle;

retrieving a plurality of images captured by the plurality of cameras in a specific range around a location of the position information by the image capturing unit;

analyzing the retrieved images according to the registration information by the analyzing unit, so as to recognize the images comprising the vehicle, comprising;

performing an image processing on the images captured by each of the cameras by the image processing unit, so as to recognize at least one license plate from the images;

comparing the recognized at least one license plate with the license plate corresponding to the registration information by the image processing unit, so as to find out images having the license plate matched to serve as the images comprising the vehicle;

estimating a recognition frequency threshold value indicating a minimum quantity of cameras that recognize the license plate by the analyzing unit according to at least one historical statistic value, wherein each historical statistic value comprises a license plate recognition accuracy of recognizing the license plate by n cameras, wherein n is a positive integer;

calculating a quantity of cameras which capture the images comprising the vehicle by the analyzing unit; and

issuing a message by the request processing unit when the calculated quantity of cameras is equal to or greater than the recognition frequency threshold value,

wherein an expected value of expecting a same license plate to be recognized in the images captured by the cameras is set by the analyzing unit, and the recognition frequency threshold value is estimated according to the set expected value and the at least one historical statistic value by the analyzing unit.

2. The method for integrating multiple camera images to track a vehicle as claimed in claim 1, wherein before the step of receiving the request of the vehicle, the method further comprises:

activating a function and setting the position information of the vehicle by a user device; and

incorporating the position information and the registration information of the vehicle into the request and transmitting the request to the server by the user device.

3. The method for integrating multiple camera images to track a vehicle as claimed in claim 2, wherein the step of activating the function and setting the position information of the vehicle by the user device comprises:

positioning the vehicle to obtain the position information by the user device.

4. The method for integrating multiple camera images to track a vehicle as claimed in claim 2, wherein the step of activating the function and setting the position information of the vehicle by the user device further comprises:

setting an alert rule and the registration information, wherein the server issues the message according to the alert rule and the registration information when the images comprising the vehicle are recognized.

5. The method for integrating multiple camera images to track a vehicle as claimed in claim 4, wherein the alert rule comprises time, location, frequency, distance or time interval for detecting the vehicle.

6. The method for integrating multiple camera images to track a vehicle as claimed in claim 1, wherein the image processing comprises moving object detection, license plate detection, or plate number recognition, or a combination thereof.

7. The method for integrating multiple camera images to track a vehicle as claimed in claim 1, wherein the step of analyzing the retrieved images according to the registration information, so as to recognize the images comprising the vehicle further comprises:

dynamically adjusting the recognition frequency threshold value by referring to a vehicle information, wherein the vehicle information comprises time, distance, or speed of driving, or a combination thereof.

8. The method for integrating multiple camera images to track a vehicle as claimed in claim 1, wherein when the images comprising the vehicle are recognized, the method further comprises:

according to a location of the camera corresponding to the images comprising the vehicle, capturing images captured by other cameras in the specific range around the location of the camera, so as to recognize the vehicle.

9. The method for integrating multiple camera images to track a vehicle as claimed in claim 1, wherein the message comprises the recognized images comprising the vehicle, or the locations and times of the cameras capturing the images, or a combination thereof.

10. The method for integrating multiple camera images to track a vehicle as claimed in claim 9, wherein the step of issuing the message comprises:

transmitting the message to a user device; and

according to a location of the camera capturing the images recorded in the message, displaying a map around the location on the user device, and labeling the recognized images comprising the vehicle on the map.

11. A system for integrating multiple camera images to track a vehicle, comprising:

a request processing unit, configured to receive a request of a vehicle, wherein the request comprises a registration information and a position information of the vehicle;

a data storage unit, configured to store the registration information and the position information of the vehicle;

an image capturing unit, configured to retrieve a plurality of images captured by a plurality of cameras in a specific range around a location of the position information;

an image processing unit, configured to perform an image processing on the images; and

an analyzing unit, configured to analyze the retrieved images according to the registration information, so as to recognize the images comprising the vehicle, wherein

the request processing unit issues a message when the images comprising the vehicle are recognized,

wherein the image processing unit performs an image processing on the images captured by each of the cameras, so as to recognize at least one license plate from the images, and compares the recognized at least one license plate with the license plate corresponding to the registration information, so as to find images having the license plate matched to serve as the images comprising the vehicle,

wherein the analyzing unit further estimates a recognition frequency threshold value indicating a minimum quantity of cameras that recognize the license plate according to at least one historical statistic value, calculates a quantity of cameras which capture the images comprising the vehicle, and compares the quantity of cameras with the recognition frequency threshold value, wherein the request processing unit issues the message when the calculated quantity of cameras is equal to or greater than the recognition frequency threshold value,

wherein each historical statistic value comprises a license plate recognition accuracy of recognizing the license plate by n cameras, wherein n is a positive integer,

wherein an expected value of expecting a same license plate to be recognized in the images captured by the cameras is set by the analyzing unit, and the recognition frequency threshold value is estimated according to the set expected value and the at least one historical statistic value by the analyzing unit.

12. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the request processing unit further provides a user device for setting the position information of the vehicle.

13. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the request processing unit further provides a user device for setting an alert rule and the registration information, wherein the server issues the message according to the alert rule and the registration information when the images comprising the vehicle are recognized.

14. The system for integrating multiple camera images to track a vehicle as claimed in claim 13, wherein the alert rule comprises time, location, frequency, distance or time interval for detecting the vehicle.

15. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the image processing comprises moving object detection, license plate detection, or plate number recognition, or a combination thereof.

16. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the analyzing unit further dynamically adjusts the recognition frequency threshold value by referring to a vehicle information, wherein the vehicle information comprises time, distance, or speed of driving, or a combination thereof.

17. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the request processing unit further captures images captured by other cameras in the specific range around the location of the camera according to a location of the camera corresponding to the images comprising the vehicle, so as to recognize the vehicle.

18. The system for integrating multiple camera images to track a vehicle as claimed in claim 11, wherein the message comprises the recognized images comprising the vehicle, or the locations and time of the cameras capturing the images, or a combination thereof.