Video-based system and method for detecting exclusion zone infractions

• US 8,666,117 B2
• Filed: 04/06/2012
• Issued: 03/04/2014
• Est. Priority Date: 04/06/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Bulan, Orhan, Wang, Yao Rong, Loce, Robert P., Bernal, Edgar A., Fan, Zhigang, Pennington, Graham S., Cummins, David P.
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US13/441,253
• Publication Number:
  US 20130266185A1
• Time in Patent Office: 697 Days
• Field of Search: 382/100, 382103-107, 382/155, 382/162, 382/168, 382/173, 382/181, 382/199, 382/209, 382/232, 382/254, 382/274, 382/276, 382286-294, 382/305, 382/312, 340/932.2, 340/937, 340/903, 348/169, 348/148
• US Class Current: 382/104
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A method for determining a parking violation includes receiving video data as a sequence of frames provided by a camera. The method includes defining a location of an exclusion zone in the video data. The method includes detecting a vehicle located in the defined exclusion zone. The detecting includes determining a background in an initial frame of the video data and determining a background in a select frame by applying a predetermined updating process. The detecting includes subtracting the background of the select frame from the initial frame to obtain an image difference. The detecting includes classifying the pixels in the image difference as foreground or background pixels and classifying the pixels in the foreground image as vehicle or non-vehicle pixels. The method includes determining a duration that the detected vehicle is in the exclusion zone based on a number of the sequence of frames including the detected vehicle.

Claims

1. A method for determining a parking violation, the method comprising:

receiving video data as a sequence of frames provided by an associated image capture device;

defining a location of an exclusion zone in the video data;

detecting a vehicle located in the defined exclusion zone;

determining a duration that the detected vehicle is in the exclusion zone based on a number of the sequence of frames including the detected vehicle;

comparing the duration to a threshold; and

,

in response to the duration meeting the threshold, indicating a parking violation,

wherein the threshold is dependent on a type of exclusion zone being monitored.

2. The method of claim 1, where in the detecting of a vehicle includes:

determining a background in an initial frame of the video data;

determining a background in a select frame by applying a predetermined updating process;

subtracting the background of the select frame from the select frame to obtain an image difference;

classifying the pixels in the image difference as foreground or background pixels; and

,

classifying the pixels in the foreground as vehicle or non-vehicle pixels.

3. The method of claim 2, wherein the determining the background in the select frame includes:

applying a predetermined updating factor p in an algorithm for each pixel in the select frame, wherein the updating factor p varies depending on a classification of a pixel belonging to the foreground or the background pixels in the current frame.

4. The method of claim 2, wherein the determining the background in the select frame includes:

computing a function B_t+1=ρ

*F_t+1+(1−

ρ

)*B_t, wherein B_t is the background at time t, F_t+1 is a frame at time t+1, and p is an image updating factor for a pixel, wherein the updating factor p is selected from a group consisting;

a “

0”

value for pixels belonging to a vehicle;

a “

1”

value for pixels belonging to a location previously occupied by a vehicle in a corresponding location of the initial frame; and

,

a value 0≦

p≦

1 for all other pixels.

5. The method of claim 2, where the classifying the pixels in the foreground includes:

applying a threshold to the image difference;

in response to the image difference meeting the threshold, classifying the pixel as belonging to a foreground.

6. The method of claim 2, wherein the detecting the vehicle further includes:

applying morphological operations to the foreground image; and

,

in response to the morphological operations, classifying the pixel as belonging to a vehicle.

7. The method of claim 1, wherein the defining the location of the exclusion zone includes:

receiving input designating the exclusion zone in the video data with a boundary.

8. The method of claim 1, wherein the defining the location of the exclusion zone includes:

generating a model associating a three-dimensional location in an actual area of the exclusion zone to a two-dimensional pixel coordinate (x, y) in the video data; and

,

defining a location of the exclusion zone by mapping actual physical coordinates to pixel coordinates in the video data.

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

using the background estimate, computing a number of frames in the sequence of frames that the vehicle is stationary; and

,

converting the number of frames to a time duration.

10. The method of claim 9, wherein the computing the number of frames includes:

determining a first frame having an updating factor p being equal to “

0”

for a select pixel (i,j) belonging to the vehicle at a select location;

determining the number of frames following the first frame having the updating factor being equal to “

0”

for pixels located at corresponding locations to the first frame; and

,

associating the first frame as a start time and the number of frames as a current time.

11. The method of claim 1 further comprising:

comparing the duration to a threshold;

in response to the duration meeting the threshold, determining if a parking condition is met; and

,

in response to the parking condition being met, indicating that a parking violation is detected.

12. The method of claim 1 further comprising:

communicating the parking violation to a user device.

13. A computer program product comprising tangible media which encodes instructions for performing the method of claim 1.

14. A system for determining parking availability comprising:

a parking violation determination device comprising memory which stores instructions for performing the method of claim 1 and a processor, in communication with the memory for executing the instructions.

15. A system for determining a parking violation, the system comprising a parking violation determination device in communication with an associated image capture device adapted to monitor an exclusion zone over a duration of time, the parking violation determination device including:

a video capture module adapted to receive video data from the associated image capture device and corresponding to a sequence of frames each capturing the exclusion zone;

an exclusion zone detection module adapted to define a location of the exclusion zone in the video data;

a vehicle detection module adapted to detect a vehicle located in the defined exclusion zone;

a duration determination module adapted to;

determine a duration that a vehicle is in the exclusion zone based on a number of the sequence of frames including the vehicle pixels,

compare the duration to a threshold, and

in response to the duration meeting the threshold, indicate a parking violation; and

,

a processor adapted to implement the modules.

16. The system according to claim 15, wherein the vehicle detection module is further adapted to:

determine a background in an initial frame of the video data;

determine a background in a select frame by applying a predetermined updating process;

subtract the background of the select frame from the background of the initial frame to obtain an image difference;

classify pixels in the image difference as belonging to one of foreground and background pixels; and

,

classify the pixels in the foreground image as one of vehicle and non-vehicle pixels.

17. The system of claim 16, wherein the background estimation module is further adapted to:

apply a predetermined updating factor p in an algorithm computed for each pixel in the select frame, wherein the updating factor p varies depending on a classification of a pixel belonging to the foreground or the background pixels in a current frame.

18. The system of claim 16, wherein the vehicle detection module is adapted:

compute the function B_t+1=ρ

*F_t+1+(1−

ρ

)*B_t, wherein B_t is the background at time t, F_t+1 is a frame at time t+1, and p is an image updating factor for a pixel, wherein the updating factor p is selected from a group consisting;

a “

0”

value if a vehicle is detected at the pixel location;

a “

1”

value if another object is detected at a pixel location previously occupied by a vehicle; and

,

a value 0≦

p≦

1 for all other pixels.

19. The system of claim 16, wherein the duration determination module is further adapted to:

determine a first frame having the updating factor p being equal to “

0”

for a select pixel (i,j) belonging to the vehicle at a select location;

determine a number of frames following the first frame having the updating factor being equal to “

0”

for pixels located at corresponding locations to the first frame; and

,

convert the number of frames to the duration.

20. The system of claim 15, wherein the vehicle detection module is adapted to:

apply the image difference to a threshold; and

,

in response to the image difference meeting the threshold, classify the pixel as belonging to a vehicle,

wherein the threshold is dependent on a type of exclusion zone being monitored.