System and method for detecting, tracking, and classifiying objects

• US 9,710,712 B2
• Filed: 06/11/2015
• Issued: 07/18/2017
• Est. Priority Date: 01/16/2015
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Fortress Corporation (Motorola Solutions, Inc.)
• Inventors: Madden, Don, Shayne, Ethan
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): SHIN, BRIAN D
• Application Number:
  US14/736,644
• Publication Number:
  US 20160210512A1
• Time in Patent Office: 768 Days
• Field of Search: None
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles
• CPC Class Codes: G08G 1/015 with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles

Abstract

The present disclosure provides for a method, device, and computer-readable storage medium for performing a method for discerning a vehicle at an access control point. The method including obtaining a video sequence of the access control point; detecting an object of interest from the video sequence; tracking the object from the video sequence to obtain tracked-object data; classifying the object to obtain classified-object data; determining that the object is a vehicle based on the classified-object data; and determining that the vehicle is present in a predetermined detection zone based on the tracked-object data.

Claims

1. A method for discerning a vehicle at an access control point, the method comprising:

obtaining a video sequence of the access control point from a first camera operable to capture video of the vehicle approaching a first outer gate;

detecting an object of interest from the video sequence;

tracking the object from the video sequence to obtain tracked-object data;

classifying the object to obtain classified-object data;

determining that the object is the vehicle based on the classified-object data;

determining if the vehicle is being tailgated based on the classified-object data;

determining that the vehicle is present in a predetermined detection zone of the access control point based on the tracked-object data; and

controlling activation of the first outer gate and a second inner gate at the access control point based on the determining if the vehicle is being tailgated.

2. The method of claim 1, wherein detecting the object of interest further comprises:

employing a stochastic background modeling technique or a segmentation technique to detect the object in the video sequence.

3. The method of claim 1, wherein tracking the object comprises:

employing a motion detection technique to track the object in the video sequence.

4. The method of claim 1, wherein the detecting the object of interest further comprises:

extracting background components from the video sequence.

5. The method of claim 1, wherein tracking the object comprises:

determining if a pixel in a frame of the video sequence represents an object that is moving based on a stochastic model of a background scene in the frame; and

clustering pixels in the frame that represent the object that is moving.

6. The method of claim 5, wherein tracking the object comprises:

identifying a position of the object in the frame of the video sequence;

identifying candidate objects in a next frame of the video sequence; and

comparing the object in the frame with candidate objects in the next frame to determine a next position of the object in the next frame.

7. The method of claim 1, wherein classifying the object comprises:

comparing the object with one or more vehicle classifications to determine a type of vehicle that is similar to the tracked object using a 3-D model based fitting technique.

8. The method of claim 7, wherein the one or more vehicle classifications are based on computer-assisted drawings of vehicle types.

9. The method of claim 7, wherein comparing the object comprises:

comparing the object based on fitting the object to a model of a vehicle having between 10-30 vertices and between 10-40 facets to approximate a mean shape of a computer-assisted drawing of the vehicle.

10. A device for discerning a vehicle at an access control point, the device comprising:

a memory containing instructions; and

at least one processor, operably connected to the memory, that executes the instructions to perform operations comprising;

obtaining a video sequence of the access control point from a first camera operable to capture video of the vehicle approaching a first outer gate;

detecting an object of interest from the video sequence;

tracking the object from the video sequence to obtain tracked-object data;

classifying the object to obtain classified-object data;

determining that the object is the vehicle based on the classified-object data;

determining if the vehicle is being tailgated based on the classified-object data;

determining that the vehicle is present in a predetermined detection zone of the access control point based on the tracked-object data; and

controlling activation of the first outer gate and a second inner gate at the access control point based on the determining if the vehicle is being tailgated.

11. The device of claim 10, wherein detecting the object of interest further comprises:

employing a stochastic background modeling technique or a segmentation technique to detect the object in the video sequence.

12. The device of claim 10, wherein tracking the object comprises:

employing a motion detection technique to track the object in the video sequence.

13. The device of claim 10, wherein the detecting the object of interest further comprises:

extracting background components from the video sequence.

14. The device of claim 10, wherein tracking the object comprises:

determining if a pixel in a frame of the video sequence represents an object that is moving based on a stochastic model of a background scene in the frame; and

clustering pixels in the frame that represent the object that is moving.

15. The device of claim 14, wherein tracking the object comprises:

identifying a position of the object in the frame of the video sequence;

identifying candidate objects in a next frame of the video sequence; and

comparing the object in the frame with candidate objects in the next frame to determine a next position of the object in the next frame.

16. The device of claim 10, wherein classifying the object comprises:

comparing the object with one or more vehicle classifications to determine a type of vehicle that is similar to the tracked object using a 3-D model based fitting technique.

17. The device of claim 16, wherein the one or more vehicle classifications are based on computer-assisted drawings of vehicle types.

18. The device of claim 16, wherein comparing the object comprises:

comparing the object based on fitting the object to a model of a vehicle having between 10-30 vertices and between 10-40 facets to approximate a mean shape of a computer-assisted drawing of the vehicle.

19. A non-transitory computer readable storage medium comprising instructions for causing one or more processors to perform a method for discerning a vehicle at an access control point, the method comprising:

obtaining a video sequence of the access control point from a first camera operable to capture video of the vehicle approaching a first outer gate;

detecting an object of interest from the video sequence;

tracking the object from the video sequence to obtain tracked-object data;

classifying the object to obtain classified-object data;

determining that the object is the vehicle based on the classified-object data;

determining if the vehicle is being tailgated based on the classified-object data;

determining that the vehicle is present in a predetermined detection zone of the access control point based on the tracked-object data; and

controlling activation of the first outer gate and a second inner gate at the access control point based on the determining if the vehicle is being tailgated.

20. The computer readable storage medium of claim 19, wherein detecting the object of interest further comprises:

employing a stochastic background modeling technique or a segmentation technique to detect the object in the video sequence.

21. The computer readable storage medium of claim 19, wherein tracking the object comprises:

employing a motion detection technique to track the object in the video sequence.

22. The computer readable storage medium of claim 19, wherein the detecting the object of interest further comprises:

extracting background components from the video sequence.

23. The computer readable storage medium of claim 19, wherein tracking the object comprises:

determining if a pixel in a frame of the video sequence represents an object that is moving based on a stochastic model of a background scene in the frame; and

clustering pixels in the frame that represent the object that is moving.

24. The computer readable storage medium of claim 19, wherein tracking the object comprises:

identifying a position of the object in the frame of the video sequence;

identifying candidate objects in a next frame of the video sequence; and

comparing the object in the frame with candidate objects in the next frame to determine a next position of the object in the next frame.

25. The computer readable storage medium of claim 19, wherein classifying the object comprises:

comparing the object with one or more vehicle classifications to determine a type of vehicle that is similar to the tracked object using a 3-D model based fitting technique.

26. The computer readable storage medium of claim 25, wherein the one or more vehicle classifications are based on computer-assisted drawings of vehicle types.

27. The computer readable storage medium of claim 25, wherein comparing the object comprises:

comparing the object based on fitting the object to a model of a vehicle having between 10-30 vertices and between 10-40 facets to approximate a mean shape of a computer-assisted drawing of the vehicle.