Video-based method for detecting parking boundary violations

• US 8,744,132 B2
• Filed: 05/01/2012
• Issued: 06/03/2014
• Est. Priority Date: 04/06/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Orhan Bulan
• Inventors: Bulan, Orhan, Bernal, Edgar A., Loce, Robert P., Wang, Yao Rong, Fan, Zhigang
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US13/461,266
• Publication Number:
  US 20130266188A1
• Time in Patent Office: 763 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, 348/169, 348/148, 340/932.2, 340/937, 340/432
• US Class Current: 382/104
• 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 and a system for determining a parking boundary violation includes receiving video data from a sequence of frames taken from an image capture device monitoring a parking area including at least a single parking space. A boundary is determined for defining at least one parking space in the parking area. A vehicle is detected in the parking area. A determination is made whether the detected vehicle is violating a parking regulation based on a position and size of the vehicle within the boundary.

Claims

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

receiving video data from a sequence of frames taken from an associated image capture device monitoring a parking area including at least a single parking space;

determining a boundary defining at least one parking space in the parking area;

detecting a presence of a vehicle in the parking area;

determining an area that the detected vehicle reaches beyond the boundary of the at least one parking space;

comparing the area to a predetermined threshold; and

,

in response to the area meeting or exceeding the predetermined threshold, indicating that the detected vehicle is in violation of the parking regulation.

2. The method of claim 1 further comprising:

classifying the detected vehicle as one of satisfying and not satisfying an exception to the parking regulation.

3. The method of claim 2, wherein the classifying includes:

determining an attribute of the detected vehicle;

comparing the attribute to a predetermined threshold;

in response to the attribute meeting and exceeding the threshold, classifying the detected vehicle as satisfying the exception; and

,

in response to the attribute not meeting and exceeding the threshold, classifying the detected vehicle as not satisfying the exception.

4. The method of claim 2, wherein the classifying includes:

extracting at least one feature describing the detected vehicle;

inputting the at least one feature into a classifier previously trained using labeled sample features;

in response to the at least one feature matching the sample labeled features, classifying the detected vehicle based on the label.

5. The method of claim 1, wherein the determining whether the detected vehicle is violating the parking regulation includes:

in response to the area not meeting or exceeding the predetermined threshold, proceeding to process a subsequent frame in the sequence.

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

determining whether a current frame is an initial frame of the sequence;

in response to the current frame being the initial frame, initializing a background image; and

in response to the current frame not being the initial frame, updating a background in the current frame by applying a predetermined updating factor p in an algorithm used to determine the background, wherein the updating factor p varies for each pixel in the current frame and depends on a classification of the pixel as belonging to one of a foreground image and a background construct.

7. The method of claim 6, wherein the algorithm includes a function

B_t+1=p*F_t+1+(1−

p)*B_t,

wherein B_t is the background at time t, F_t+1 is a frame at time t+1, and p is the updating factor for the pixel, wherein the updating factor 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.

8. The method of claim 1 further comprising:

computing an absolute difference in an intensity between pixels located in a current frame and pixels at corresponding locations in one of a background image initialized in an initial frame and a background of a preceding frame;

determining if the difference meets or exceeds a threshold; and

,

classifying the pixels in the select frame based on the difference and the threshold.

9. The method of claim 8, wherein the classifying the pixels includes:

in response to the threshold not being met or exceeded, classifying a pixel as belonging to the background construct;

in response to a threshold being met or exceeded, classifying the pixel as belonging to the foreground image.

10. The method of claim 8 further comprising:

providing an image using the classified pixels, the providing including;

assigning different values to the pixels corresponding to locations classified as belonging to background, and foreground; and

,

processing the image for determining whether the detected vehicle is violating the parking regulation.

11. The method of claim 1 further comprising:

in response to determining that the detected vehicle is violating the parking regulation, providing notice of the violation to a user device.

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

13. A system for determining parking availability comprising:

a parking boundary 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.

14. A system for determining a parking boundary violation, the system comprising:

a parking boundary violation determination device, the determination device including;

a video buffer module adapted for receiving video data from a sequence of frames taken from an associated image capture device monitoring a parking area including at least a single parking space;

a boundary violation detection module adapted for determining a boundary defining at least one parking space in the parking area;

a stationary vehicle detection module adapted for detecting a presence of a vehicle in the parking area;

a boundary violation detection module adapted to;

determine an area that the detected vehicle reaches beyond the boundary of the at least one parking space,

compare the area to a predetermined threshold, and

in response to the area meeting or exceeding the predetermined threshold, indicate that the detected vehicle is in violation of the parking regulation; and

,

a processor adapted to implement the modules.

15. The system according to claim 14 further comprising a vehicle classification module adapted for classifying the detected vehicle as one of satisfying and not satisfying an exception to the parking regulation.

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

determine an attribute of the detected vehicle;

compare the attribute to a predetermined threshold;

in response to the attribute meeting and exceeding the threshold, classify the detected vehicle as satisfying the exception; and

,

in response to the attribute not meeting and exceeding the threshold, classify the detected vehicle as not satisfying the exception.

17. The system according to claim 15, wherein the vehicle classification module is adapted to:

extract at least one feature describing the detected vehicle;

input the at least one feature into a classifier previously trained using sample

labeled features;

in response to the at least one feature matching the sample labeled features, classify the detected vehicle based on the label.

18. The system according to claim 14, wherein the boundary violation detection module is adapted to:

in response to the area not meeting or exceeding the predetermined threshold, proceed to process a subsequent frame in the sequence.

19. The system according to claim 14, wherein the stationary vehicle detection module is adapted to:

determine whether a current frame is an initial frame of the sequence;

in response to the current frame being the initial frame, initialize a background image; and

in response to the current frame not being the initial frame, update a background in the current frame by applying a predetermined updating factor p in an algorithm used to determine the background, wherein the updating factor p varies for each pixel in the current frame and depends on a classification of the pixel as belonging to one of a foreground image and a background construct.

20. The system according to claim 19, wherein the algorithm includes a function,

B_t+1=p*F_t+1+(1−

p)*B_t,

wherein B_t is the background at time t, F_t+1 is a frame at time t+1, and p is the updating factor for the pixel, wherein the updating factor 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.