Method for object size calibration to aid vehicle detection for video-based on-street parking technology

Patent metadata

Field	Value
Publication number	US-9449236-B2
Application number	US-201314070812-A
Country	US
Kind code	B2
Filing date	Nov 4, 2013
Priority date	Nov 4, 2013
Publication date	Sep 20, 2016
Grant date	Sep 20, 2016

Abstract

A method for determining parking availability includes receiving video data from a sequence of frames taken from an image capture device monitoring a parking area. The method includes detecting at least one object located in the parking area. The method includes determining boundaries of the parking area. The boundaries include at least an inner boundary relative to the image capture device and an outer boundary relative to the image capture device. The outer boundary is substantially parallel to the inner boundary. The method further includes computing a length of at least one of the object and a space between objects using an object pixel for each of the inner and outer boundaries. Using the computed length, The method includes determining a parking availability in the parking area. The method includes outputting a notice of the parking availability to a user.

First claim

What is claimed is:

1. A method for determining parking availability, the method comprising:
receiving video data from a sequence of frames taken from an associated image capture device monitoring a parking area;
detecting at least one object located in the parking area;
determining boundaries of the parking area, the boundaries including at least an inner boundary relative to the associated image capture device and an outer boundary relative to the associated image capture device, the outer boundary being substantially parallel to the inner boundary;
identifying a leftmost object pixel and one of a rightmost object pixel and rightmost second object pixel on or closest to each of the inner and outer boundaries;
computing a length of at least one of the object and a space between objects using the identified pixels and first and second LUTs corresponding to the inner and outer boundaries;
using the computed length, determining a parking availability in the parking area; and,
outputting a notice of the parking availability to a user.

2. The method of claim 1 , wherein the parking area includes an on-street parking lane and the inner and outer boundaries extend along the parking lane.

3. The method of claim 1 further comprising:
before detecting the at least one object, receive video data capturing equally spaced apart markings defining actual boundaries in the parking area, the markings including a first set of inner marks and a second set of outer marks located along opposite edges defining the parking area, the first and second sets of marks being oriented in a substantial parallel relationship;
capturing the parking area with the markings using the associated image capture device;
mapping coordinates of each marking onto the image plane;
associating a pixel value with the each marking;
generating the first LUT corresponding to the pixels associated with the first set of inner marks and the second LUT corresponding to the pixels associated with the second set of the outer marks, the first and second LUTs assigning each pixel to an assigned value such that a spaced apart pair of pixels is known to be of certain distance along the actual boundaries; and,
removing the markings in the parking area before receiving the video data.

4. The method of claim 1 , wherein the detecting the at least one object includes:
classifying pixels in each frame as belonging to one of a background image and a foreground image using background estimation;
generating a binary image using the classified pixels; and,
for a current frame, associating each binary image on the image plane with an object.

5. The method of claim 4 , wherein the computing the length includes:
identifying leftmost pixels of the object on the image plane on or closest to each of the outer and inner boundaries and rightmost pixels of the object on the image plane closest to each of the outer and inner boundaries;
receiving the first LUT corresponding to the inner boundary and the second LUT corresponding to the outer boundary, the first and second LUTs mapping the identified pixels to an assigned value; and,
computing a length of the object with the equation:
L object =min(LUT inner ( P r ),LUT outer ( P r ))−max(LUT inner ( P l ),LUT outer ( P l )),

where P r is the rightmost pixel identified in the binary image, and P l is the leftmost pixel identified in the binary image.

6. The method of claim 5 wherein the determining the parking availability includes:
determining a remaining length of space available in the parking using the computed length of the object;
comparing the remaining length to a threshold; and,
in response to the remaining length being greater than the threshold, classifying the parking area as having available space.

7. The method of claim 4 , wherein the computing the length includes:
identifying rightmost pixels of a first object located closest to the associated image capture device on the image plane on or closest to each of the inner and outer boundaries;
identifying leftmost pixels of a second object located next to the first object and farther away from the associated image capture device on the image plane on or closest to each of the inner and outer boundaries; and,
calculating the length of a space between the objects based on the identified pixels.

8. The method of claim 7 , wherein the calculating the length of the space between two objects includes:
receiving the first LUT corresponding to the inner boundary and the second LUT corresponding to the outer boundary, the first and second LUTs mapping pixel values with actual coordinates; and,
computing the length of the space with the equation:
L space =min(LUT inner ( P r ),LUT outer ( P r ))−max(LUT inner ( P l ),LUT outer ( P l )),

where P r is the rightmost pixel identified in the binary image, and P l is the leftmost pixel identified in the binary image.

9. The method of claim 1 , wherein the determining a parking availability includes:
comparing the length between the two objects to a threshold associated with one of a vehicle class and select length;
in response to the length being greater than the threshold, classifying the space as an available parking space for the one of the vehicle class and select length.

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

11. A system for determining parking availability, the system comprising:
a parking space determination device, the parking space determination device including:
a video buffer module operable to receive video data from a sequence of frames capturing a parking area;
a vehicle detection module operable to detect at least one object located in the parking area;
a length calculation module operable to:
determine boundaries of the parking area, the boundaries including at least an inner boundary relative to an associated image capture device and an outer boundary relative to the associated image capture device, the outer boundary being substantially parallel to the inner boundary,
identify a leftmost object pixel and one of a rightmost object pixel and rightmost second object pixel on or closest to each of the inner and outer boundaries, and
compute a length of at least one of the object and a space between objects using the identified pixels and first and second LUTs corresponding the inner and outer boundaries;
a parking determination module operable to determine a parking availability in the parking area using the computed length;
a communication interface operable to transmit a notice of the parking availability to a user; and,

a processor operable to execute the modules.

12. The system of claim 11 , wherein the parking area includes an on-street parking lane and the inner and outer boundaries extend along the parking lane.

13. The system of claim 11 further comprising a calibration module operable to:
before detecting the at least one object, receive video data capturing equally spaced apart markings defining actual boundaries in the parking area, the markings including a first set of inner marks and a second set of outer marks located along opposite edges defining the parking area, the first and second sets of marks being oriented in a substantial parallel relationship;
map coordinates of each marking onto the image plane;
associate a pixel value with the each marking;
generate the first LUT corresponding to the pixels associated with the first set of inner marks and the second LUT corresponding to the pixels associated with the second set of the outer marks, the first and second L

Assignees

• Xerox Corp

Inventors

• Wang Yao Rong
• Bulan Orhan
• Ding Hengzhou
• Pennington Graham S

Classifications

• G08G1/168 Primary

  Driving aids for parking, e.g. acoustic or visual feedback on parking space · CPC title

• G06K9/00812 Primary

  Physics · mapped topic

• G06K9/00771

  Physics · mapped topic

• G08G1/141

  with means giving the indication of available parking spaces · CPC title

• G06V20/586 Primary

  of parking space · CPC title