Video-based system and method for parking occupancy detection

Patent metadata

Field	Value
Publication number	US-9672434-B2
Application number	US-201514805608-A
Country	US
Kind code	B2
Filing date	Jul 22, 2015
Priority date	Jul 22, 2015
Publication date	Jun 6, 2017
Grant date	Jun 6, 2017

Abstract

A spatiotemporal system and method for parking occupancy detection. The system can generally include suitable image acquisition, processing, transmission and data storage devices configured to carry out the method which includes generating and processing spatiotemporal images to detect the presence of an object in a region of interest, such as a vehicle in a parking stall.

First claim

What is claimed is:

1. A computer implemented method for detecting vehicle occupancy of a plurality of parking spaces comprising:
acquiring a sequence of images of the plurality of parking spaces;
extracting at least one vector of data from the same location in each of the images;
generating a plurality of spatiotemporal images, each spatiotemporal image comprised of vectors of data extracted from the same location in each of the sequence of images; and
analyzing the plurality of spatiotemporal images to obtain vehicle occupancy data of each of the plurality of parking spaces;
wherein the analyzing includes calculating a color difference of respective at least one pixels in at least two of the spatiotemporal images, determining the maximum absolute difference per pixel between at least two spatiotemporal images and comparing the difference to a threshold to obtain occupancy data, or subtracting a first spatiotemporal image from a second spatiotemporal image and comparing the difference to a threshold to obtain occupancy data.

2. The computer implemented method of claim 1 , wherein the extracting at least one vector of data from the same location in each of the images further comprises extracting at least three vectors of data from substantially different portions of each respective image.

3. The computer implemented method of claim 2 , further comprising defining the three vectors of data to be three color data components, transforming the three color data components to a device independent color space, and analyzing non-lightness components of the transformed data to determine vehicle occupancy of the plurality of parking spaces.

4. The computer implemented method of claim 2 , further comprising defining the three vectors of data to be respective red, green, and blue color data components, transforming the color data components to a hue-saturation color space, and analyzing the hue-saturation components of the transformed data to determine vehicle occupancy of the plurality of parking spaces.

5. The computer implemented method of claim 1 , further comprising performing temporal noise reduction on the at least one of the plurality of spatiotemporal images prior to the analyzing.

6. The computer implemented method of claim 5 , further comprising performing spatial noise reduction on the at least one of the plurality of spatiotemporal images prior to the analyzing.

7. The computer implemented method of claim 1 , wherein the analyzing includes comparing a saturation value of at least one pixel of the spatiotemporal image to a threshold value and, if above the threshold, generating an output indicative of occupancy of the space corresponding to the at least one pixel.

8. The computer implemented method of claim 1 , wherein the analyzing includes detecting horizontal intensity changes in at least one of the plurality of spatiotemporal images.

9. The computer implemented method of claim 1 , wherein a time interval between individual images of the sequence of images is variable.

10. A system for video-based detection occupancy of a space, the system comprising a memory in communication with a processor configured to:
acquire a sequence of images of the space;
extract at least one vector of data from the same location in each of the images;
generate a plurality of spatiotemporal images, each spatiotemporal image comprised of vectors of data extracted from the same location in each of the sequence of image; and
analyze the plurality of spatiotemporal images to obtain occupancy data of the space;
wherein the processor is further configured to analyze the plurality of spatiotemporal images by calculating a color difference of respective at least one pixels in at least two of the spatiotemporal images, determining the maximum absolute difference per pixel between at least two spatiotemporal images and comparing the difference to a threshold to obtain occupancy data, or subtracting a first spatiotemporal image from a second spatiotemporal image and comparing the difference to a threshold to obtain occupancy data.

11. The system of claim 10 , wherein the processor is further configured to extract at least three vectors of data from substantially different portions of each respective image.

12. The system of claim 11 , wherein the processor is further configured to define the at least three vectors of data to be three color data components, transform the three color data components to a device independent color space, and analyze non-lightness components of the transformed color data components to determine vehicle occupancy of the plurality of parking spaces.

13. The system of claim 11 , wherein the processor is further configured to define the at least three vectors of data to be respective red, green, and blue color data components, transform the color data components to a hue-saturation color space, and analyze the hue-saturation components of the transformed color data components to determine vehicle occupancy of the plurality of parking spaces.

14. The system of claim 10 , wherein the processor is further configured to perform temporal noise reduction on at least one of the plurality of spatiotemporal images prior to the analyzing.

15. The system of claim 10 , wherein the processor is further configured to perform spatial noise reduction on at least one of the plurality of spatiotemporal images prior to the analyzing.

16. The system of claim 10 , wherein the analyzing includes comparing a saturation value of at least one pixel of at least one of the spatiotemporal images to a threshold value and, if above the threshold, generating an output indicative of occupancy of the space corresponding to the at least one pixel.

17. The system of claim 10 , wherein the analyzing includes detecting horizontal intensity changes in at least one of the plurality of spatiotemporal images.

Assignees

• Xerox Corp
• Conduent Business Services Llc

Inventors

• Wu Hao
• Loce Robert P
• Wang Yao Rong

Classifications

• G06V20/47 Primary

  Detecting features for summarising video content · CPC title

• G06V20/586

  of parking space · CPC title

• G06K9/00812 Primary

  Physics · mapped topic

• G06K9/4652

  Physics · mapped topic

• G06T5/00

  Image enhancement or restoration · CPC title