VIDEO-BASED SYSTEM FOR AUTOMATED DETECTION OF DOUBLE PARKING VIOLATIONS

• US 20150206014A1
• Filed: 01/22/2014
• Published: 07/23/2015
• Est. Priority Date: 01/22/2014
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Wu, Wencheng, Bernal, Edgar A., Wang, Yao Rong, Fan, Zhigang, Loce, Robert P.
• Granted Patent: US 11,244,171 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: G06V 10/23 based on positionally close patterns or neighbourhood relationships
• 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 20/586 of parking space
• CPC Class Codes: G08G 1/147 where the parking area is within an open public zone, e.g. city centre
• CPC Class Codes: G08G 1/168 Driving aids for parking, e.g. acoustic or visual feedback on parking space
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A method for detecting a double-parked vehicle includes identifying a parking region in video data received from an image capture device monitoring the parking region. The method includes defining an enforcement region at least partially surrounding the parking region. The method includes detecting a stationary vehicle in the enforcement region. The method includes determining the occurrence of an event relative to the stationary vehicle. In response to the determined occurrence of the event, the method includes classifying the stationary vehicle as being one of double parked and not double parked.

Claims

1. A method for detecting a double-parked vehicle, the method comprising:

identifying a parking region in video data received from an image capture device monitoring the parking region;

defining an enforcement region at least partially surrounding the parking region;

detecting a stationary candidate double-parked vehicle in the enforcement region;

determining the occurrence of an event relative to the stationary candidate double-parked vehicle;

in response to the determined occurrence of the event, classifying the stationary candidate double-parked vehicle as being one of double parked and not double parked.

2. The method of claim 1, wherein the determining the occurrence of the event includes:

determining whether hazard lights are operating on the stationary candidate double-parked vehicle; and

,

in response to the hazard lights operating on the stationary candidate double-parked vehicle, classifying the stationary candidate double-parked vehicle as being double parked.

3. The method of claim 2, wherein the determining whether the hazard lights are operating includes:

identifying a hazard light region in the sequence of frames surrounding one of a front light and rear light; and

,

determining pixel colors in the hazard light region in the sequence of frames.

4. The method of claim 1, wherein the determining the occurrence of the event further includes:

determining whether the stationary candidate double-parked vehicle qualifies for an exception.

5. The method of claim 4, wherein the exception is determined to have occurred if the stationary candidate double-parked vehicle is one of an emergency vehicle and a commercial vehicle.

6. The method of claim 1, wherein the determining the occurrence of the event includes:

determining whether an object is located in front of the stationary candidate double-parked vehicle; and

,

in response to a distance between the object and the stationary candidate double-parked vehicle being below a threshold, classifying the stationary candidate double-parked vehicle as not being double parked.

7. The method of claim 6, wherein the determining the occurrence of the event further includes:

in response to the distance between the object and the stationary candidate double-parked vehicle being equal to or above the threshold, determining if the object is a stop light;

determining pixel colors in the stop light region in the sequence of frames; and

,

in response to the pixel colors being green, classifying the stationary candidate double-parked vehicle as being double parked

8. The method of claim 1, wherein the determining the occurrence of the event includes:

detecting a second vehicle in the sequence of frames;

determining a trajectory of the second vehicle across a number of frames;

determining whether the trajectory moves around the stationary candidate double-parked vehicle; and

,

in response the trajectory moving around the stationary candidate double-parked vehicle, classifying the stationary candidate double-parked vehicle as being double parked.

9. The method of claim 1, wherein the determining the occurrence of the event includes:

detecting a second stationary vehicle in the parking region located within proximity to the stationary candidate double-parked vehicle in the enforcement region.

10. The method of claim 1, wherein the detecting the vehicle is performed using one of background estimation and subtraction, tracking, temporal difference, optical flow, and an initialization process.

11. The method of claim 1, wherein the detecting the vehicle includes:

determining a number of frames the detected vehicle is located in a same position;

comparing the number of frames to a threshold; and

,

in response to the number of frames meeting or exceeding the threshold, classifying the detected vehicle as the stationary candidate double-parked vehicle.

12. The method of claim 1 further comprising:

in response to the stationary candidate double-parked vehicle being classified as double parked, associating the stationary candidate double-parked vehicle as being a double parked vehicle and providing the user with a notification as output.

13. The method of claim 1, wherein the determining the occurrence of the event includes:

considering multiple events for confirming whether the stationary candidate double-parked vehicle is double parked.

19. The system of claim 13, wherein the vehicle classification module is further operative to:

determine whether an object is located in front of the stationary candidate double-parked vehicle; and

,

in response to a distance between the object and the stationary candidate double-parked vehicle being below a threshold, classify the stationary candidate double-parked vehicle as not being double parked.

20. The system of claim 19, wherein the vehicle classification module is further operative to:

in response to the distance between the object and the stationary candidate double-parked vehicle being equal to or above the threshold, determine if the object is a stop light;

determine pixel colors in the stop light region in the sequence of frames; and

,

in response to the pixel colors being green, classify the stationary candidate double-parked vehicle as being double parked

22. The system of claim 13, wherein the vehicle detection module detects the stationary candidate double-parked vehicle using background estimation and subtraction, temporal difference, optical flow, and an initialization process.

23. The system of claim 13, wherein the vehicle detection module is operative to:

determine a number of frames the stationary candidate double-parked vehicle is located in a same position;

compare the number of frames to a threshold; and

,

in response to the number of frames meeting or exceeding the threshold, classify the detected vehicle as being the stationary candidate double-parked vehicle.

14. A system for detecting a double-parked vehicle, the system comprising:

a double parking confirmation device including a memory for storing modules, including;

a region determination module operative to identify a parking region and an enforcement region at least partially surrounding the parking region in a sequence of frames received from an image capture device monitoring the parking region;

a vehicle detection module operative to detect a stationary candidate double-parked vehicle in the enforcement region;

a vehicle classification module operative to;

determine an occurrence of an event relative to the stationary candidate double-parked vehicle, and

in response to the determined occurrence of the event, classify the stationary candidate double-parked vehicle as being one of double parked and not double parked; and

,

a processor in communication with the memory and being operative to execute the modules.

15. The system of claim 14, wherein the vehicle classification module is further operative to:

determine whether hazard lights are operating on the stationary candidate double-parked vehicle;

in response to the hazard lights operating on the stationary candidate double-parked vehicle, classify the stationary candidate double-parked vehicle as being double parked.

16. The system of claim 15, wherein the vehicle classification module is further operative to:

identify a hazard light region in the sequence of frames surrounding one of a front light and rear light;

determine pixel colors in the hazard light region in the sequence of frames;

in response to changes in the pixel colors between frames, classify the stationary candidate double-parked vehicle as operating its hazard lights.

17. The system of claim 14, wherein the determining the occurrence of the event further includes:

determine whether the stationary candidate double-parked vehicle qualifies for an exception.

18. The system of claim 17, wherein the exception is determined to have occurred if the stationary candidate double-parked vehicle is one of an emergency vehicle and a commercial vehicle.

21. The system of claim 14, wherein the vehicle classification module is further operative to:

detect a second vehicle in the sequence of frames;

determine a trajectory of the second vehicle across a number of frames;

determine whether the trajectory moves around the stationary candidate double-parked vehicle; and

,

in response the trajectory moving around the stationary candidate double-parked vehicle, classify the stationary candidate double-parked vehicle as being double parked.

24. The system of claim 14, further comprising a notification module adapted to:

in response to the stationary candidate double-parked vehicle being classified as double parked, associate the stationary candidate double-parked vehicle as being a double parked vehicle and provide the user with a notification as output.

25. The system of claim 14, wherein the vehicle classification module is further operative to:

consider multiple events for confirming whether the stationary candidate double-parked vehicle is double parked.

26. The system of claim 14 further comprising an output device for providing the classification to a user.