Method and system for vandalism and/or loitering detection using video

• US 9,802,571 B2
• Filed: 10/01/2014
• Issued: 10/31/2017
• Est. Priority Date: 10/01/2014
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Inventors: Shreve, Matthew Adam, Wang, Yao Rong, Loce, Robert P., Furst, Michael R.
• Primary Examiner(s): Rao, Andy
• Application Number:
  US14/503,957
• Publication Number:
  US 20160096506A1
• Time in Patent Office: 1,126 Days
• Field of Search: 348 11-118, 348148, 348149
• CPC Class Codes: B60R 25/102 a signal being sent to a remote location, e.g. a radio signal being transmitted to a police station, a security company or the owner
• 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: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Abstract

This disclosure provides a method and system to detect a predefined activity, e.g., vandalism, loitering, trespass, etc., associated with a parked vehicle. According to an exemplary embodiment, a method includes capturing video of a parking area and processing the video to detect vandalism and/or loitering with respect to a region of interest associated with the parked vehicle.

Claims

1. A computer-implemented method of detecting a predefined human activity in a region of interest (ROI) associated with a parked vehicle registered with a vehicle monitoring service, the method comprising:

the vehicle monitoring service capturing a video stream of a parking area including the parked vehicle registered with the vehicle monitoring service;

the vehicle monitoring service identifying the parked vehicle in the video stream;

the vehicle monitoring service processing the video to detect the predefined human activity with respect to the ROI associated with the parked vehicle registered with the vehicle monitoring service, the predefined human activity including a person detected within the ROI and behaving in a predefined manner associated with vandalism and vandalism is detected by the vehicle monitoring service performing a method comprising;

detecting the parked vehicle

defining the ROI to include a region surrounding the detected parked vehicle

detecting a person within the ROI; and

determining the person tracked within the ROI has contacted the parked vehicle if an image representation of the person tracked intersects with an image representation of the parked vehicle by a threshold; and

the vehicle monitoring service communicating an alert to a user associated with the parked vehicle if the predefined human activity is detected.

2. The method of detecting a predefined human activity according to claim 1, wherein the parked vehicle is one of an automobile, motorcycle, motorized scooter, truck, van, golf-cart, ATV, and a bicycle.

3. The method of detecting a predefined human activity according to claim 1, wherein the parked vehicle is pre-registered with the vehicle monitoring service.

4. The method of detecting a predefined human activity according to claim 3, wherein the parked vehicle is registered using one of a computing device, a phone, and verbally communicating with an operator of the parking area.

5. The method of detecting a predefined human activity according to claim 4, further comprising:

the user transmitting a response to the vehicle monitoring service indicating if the detected human activity is authorized by the user.

6. The method of detecting a predefined human activity according to claim 1, wherein the predefined human activity is associated with one or more of loitering, vandalism, vehicle trespass, theft of an article from the vehicle and lying in wait.

7. The computer-implemented method of detecting a predefined human activity according to claim 1, wherein the predefined human activity is associated with loitering and loitering is detected by the vehicle monitoring service performing a method comprising:

detecting the parked vehicle;

defining the ROI to include a region surrounding the detected parked vehicle;

detecting a person within the ROI and initializing a timer; and

determining the detected person is loitering if the timer exceeds a temporal threshold.

8. A system for detecting a predefined human activity in a region of interest (ROI) associated with a parked vehicle pre-registered with a vehicle monitoring service comprising:

a detection device including memory which stores instructions for performing the method of claim 1 and a processor in communication with the memory for executing instructions.

9. A parked vehicle monitoring system for detecting a predefined human activity in a region of interest (ROI) associated with a parked vehicle registered with the vehicle monitoring system;

one or more image capturing devices configured to capture a video stream of a parking area including the parked vehicle registered with the vehicle monitoring system;

an image processing module configured to process the video to detect the predefined human activity with respect to the ROI associated with the parked vehicle registered with the vehicle monitoring system, the predefined human activity including a person detected within the ROI and behaving in a predetermined manner associated with vandalism and vandalism is detected by the vehicle monitoring service performing a method comprising;

detecting the parked vehicle;

defining the ROI to include a region surrounding the detected parked vehicle;

detecting a person within the ROI;

tracking the person detected within the ROI; and

determining the person tracked within the ROI has contacted the parked vehicle if an image representation of the person tracked intersects with an image representation of the parked vehicle by a threshold; and

a communications module configured to communicate an alert to a user associated with the parked vehicle.

10. The parked vehicle monitoring system according to claim 9, wherein the vehicle is one of an automobile, motorcycle, motorized scooter, truck, van, golf cart, ATV, and a bicycle.

11. The parked vehicle monitoring system according to claim 9, wherein the parked vehicle is pre-registered with the vehicle monitoring system.

12. The parked vehicle monitoring system according to claim 9, wherein the parked vehicle is registered using one of a computing device, a phone, and verbally communicating with an operator of the parking area.

13. The parked vehicle monitoring system according to claim 9, further comprising:

the user transmitting a response to the vehicle monitoring system indicating if the detected human activity is authorized by the user.

14. The parked vehicle monitoring system according to claim 9, wherein the predefined human activity is associated with one or more of loitering, vandalism, vehicle trespass, theft of an article from the vehicle and lying in wait.

15. The parked vehicle monitoring system according to claim 9, wherein the predefined human activity is associated with loitering and loitering is detected by the vehicle monitoring service performing a method comprising:

detecting the parked vehicle;

defining the ROI to include a region surrounding the detected parked vehicle;

detecting a person within the ROI and initializing a timer; and

determining the detected person is loitering if the timer exceeds a temporal threshold.

16. A computer-implemented method of detecting a predefined human activity in a region of interest (ROI) associated with a parked vehicle registered with a vehicle monitoring service, the method comprising:

the vehicle monitoring service capturing a video stream of a parking area including the parked vehicle registered with the vehicle monitoring service;

the vehicle monitoring service identifying the parked vehicle in the video stream;

the vehicle monitoring service processing the video to detect the predefined human activity with respect to the region of interest (ROI) associated with the parked vehicle registered with the vehicle monitoring service, the predefined human activity including a person detected within the ROI and behaving in a predefined manner associated with vandalism and vandalism is detected by the vehicle monitoring service performing a method comprising;

detecting the parked vehicle;

defining the ROI to include a pixel region surrounding the detected parked vehicle;

detecting a person within the ROI

tracking one or more pixel positions of the person detected within the ROI; and

determining the person tracked with the ROI has contacted the parked vehicle if one or more pixel representations of the person are closer than a threshold distance from a reference line associated with the parked vehicle; and

the vehicle monitoring service communicating an alert to a user associated with the parked vehicle if the predefined human activity is detected.

17. A parked vehicle monitoring system for detecting a predefined human activity in a region of interest (ROI) associated with a parked vehicle registered with the vehicle monitoring system;

one or more image capturing devices configured to capture a video stream of a parking area including the parked vehicle registered with the vehicle monitoring system;

an image processing module configured to process the video to detect the predefined human activity with respect to the ROI associated with the parked vehicle registered with the vehicle monitoring system, the predefined human activity including a person detected within the ROI and behaving in a predetermined manner associated with vandalism and vandalism is detected by the vehicle monitoring service performing a method of comprising;

detecting the parked vehicle;

defining the ROI to include a pixel region surrounding the detected parked vehicle;

detecting a person within the ROI;

tracking one or more pixel positions of the person detected within the ROI; and

determining the person tracked with the ROI has contacted the parked vehicle if one or more pixel representations of the person are closer than a threshold distance from a reference line associated with the parked vehicle; and

a communications module configured to communicate an alert to a user associated with the parked vehicle.