Video/vision based access control method and system for parking occupancy determination, which is robust against camera shake

• US 9,736,374 B2
• Filed: 09/19/2013
• Issued: 08/15/2017
• Est. Priority Date: 09/19/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Inventors: Wu, Wencheng
• Primary Examiner(s): Patel, Jay
• Assistant Examiner(s): Haghani, Shadan E
• Application Number:
  US14/031,128
• Publication Number:
  US 20150077559A1
• Time in Patent Office: 1,426 Days
• 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: H04N 23/683 performed by a processor, e.g. controlling the readout of an image memory

Abstract

Methods and systems for parking lot occupancy determination. Video of an entrance to a parking lot (or other facility) can be acquired utilizing one or more video cameras focusing on a pre-defined vision-based region of interest and a pre-defined video-based region of interest. The video can be video processed via a classifier that is pre-trained to take into account potential camera shake disturbances to generate video output data thereof. The video output data can then be trajectory smoothed. The video output data (following trajectory smoothing) can then be analyzed for parking lot occupancy data such that the impact of camera shake with respect to the video camera(s) is minimized to determine parking lot occupancy.

Claims

1. A method for parking occupancy determination, said method comprising:

acquiring video of an entrance to a parking lot utilizing at least one video camera focusing on a computer vision-based region of interest for vehicle validation and a video-based region of interest for motion detecting and tracking;

video processing said video via at least one classifier trained with data collected from said parking lot and to take into account potential camera shake disturbances to generate video output data thereof, wherein said at least one classifier comprises at least one computer vision-based image content classifier;

analyzing said video output data for parking lot occupancy data, wherein an impact of camera shake with respect to said at least one video camera is minimized to determine parking lot occupancy;

determining an access type with respect to said parking lot based on said parking lot occupancy data, after analyzing said video output data for said parking lot occupancy data;

configuring said at least one classifier to comprise said computer vision-based image content classifier that performs image content classification for the computer vision-based region of interest and assists in object tracking with respect to said video-based region of interest;

applying distortions that simulate camera shake effects with respect to at least one image frame;

cropping said at least one image frame at an original region of interest after said applying said distortions that simulate said camera shake effects with respect to said at least one image frame;

incorporating said potential camera shake disturbances into training of said at least one classifier used for computer vision-based processing for said computer vision-based region of interest for vehicle validation and used for trajectory smoothing said video output data to remove an impact of high-frequency components during said camera shake disturbances;

measuring changes in a field of view of said video using template matching between templates derived from at least one original scene and at least one current scene with motion removed; and

employing said changes measured in said field of view to adjust data indicative of at least one region of interest for computer vision-based processing thereof if said changes measured are above a pre-determined threshold so that an impact of said changes with respect so said field of view to performance is minimized and determine said parking lot occupancy.

2. The method of claim 1 wherein said video processing said video further comprises video processing said video via a data-processing system comprising a server.

3. The method of claim 2 further comprising:

tracking at least one vehicle within said video of said entrance to said parking lot utilizing said at least one classifier.

4. The method of claim 2 further comprising:

tracking at least one vehicle within said video of said entrance to said parking lot utilizing said at least one classifier; and

wherein video processing said video via said at least one classifier further comprises;

video processing said video at said video-based region of interest for motion detecting and tracking, if motion is detected within said computer vision-based region of interest for vehicle validation.

5. The method of claim 1 wherein said video processing said video further comprises video processing said video via a data-processing system comprising a smartphone or a tablet computing device.

6. The method of claim 1 further comprising tracking at least one vehicle within said video of said entrance to said parking lot utilizing said at least one classifier.

7. The method of claim 6 wherein video processing said video via said at least one classifier further comprises:

video processing said video at said video-based region of interest for motion detecting and tracking, if motion is detected within said computer vision-based region of interest for vehicle validation.

8. The method of claim 7 further comprising analyzing said video for a vehicle trajectory of said at least one vehicle to provide an indication of whether or not said at least one vehicle is entering or exiting said parking lot.

9. The method of claim 7 further comprising training said at least one classifier based on pulled samples indicative of camera shake in scope to include said potential camera shake disturbances into said at least one classifier.

10. The method of claim 9 further comprising:

randomly moving, rotating, scaling, and warping said computer vision-based region of interest for vehicle validation; and

cropping said training samples to capture samples indicative of said camera shake.

11. The method of claim 10 further comprising manipulating distortion parameters to generate a plurality of varying levels of simulated camera shake samples for use as said training samples.

12. A system for parking occupancy determination, said system comprising:

a processor; and

a computer-usable medium embodying computer program code, said computer-usable medium capable of communicating with the processor, said computer program code comprising instructions executable by said processor and configured for;

acquiring video of an entrance to a parking lot utilizing at least one video camera focusing on a computer vision-based region of interest for vehicle validation and a video-based region of interest for motion detecting and tracking;

video processing said video via at least one classifier trained with data collected from said parking lot and to take into account potential camera shake disturbances to generate video output data thereof, wherein said at least one classifier comprises at least one computer vision-based image content classifier;

tracking at least one vehicle within said video of said entrance to said parking lot utilizing said at least one classifier;

analyzing said video output data for parking lot occupancy data, wherein an impact of camera shake with respect to said at least one video camera is minimized to determine parking lot occupancy;

determining an access type with respect to said parking lot based on said parking lot occupancy data, after analyzing said video output data for said parking lot occupancy data;

incorporating said potential camera shake level considerations into training of said at least one classifier used for computer vision-based processing for said computer vision-based region of interest for vehicle validation and used for trajectory smoothing said video output data to remove an impact of high-frequency components in said camera shake;

video processing said video at said pre-defined video-based region of interest for motion detection and tracking, if motion is detected within said pre-defined vision-based region of interest;

analyzing said video for a vehicle trajectory of said at least one vehicle to determine if said at least one vehicle is entering or exiting said parking lot;

training said at least one classifier based on pulled samples indicative of camera shake in scone to include said potential camera shake disturbances into said at least one classifier;

deriving new pixel locations with respect to said computer vision-based region of interest for said vehicle validation if a determined amount exceeds a pre-determined threshold, and if said amount does not exceed said pre-determined threshold, leave pixel locations unchanged with respect to said computer vision-based region of interest for vehicle validation;

wherein said computer vision-based region of interest for vehicle validation is contained within said video-based region of interest for motion detecting and tracking;

randomly moving, rotating, scaling, and warping said computer vision-based region of interest; and

cropping said training samples to capture said samples indicative of said camera shake.

13. The system of claim 12 further comprising a data-processing system comprising said processor that communicates with an HDD (Hard Disk Drive).

14. The system of claim 12 further comprising a data-processing system comprising a server comprising said processor.

15. The system of claim 12 further comprising a tablet computing device comprising said processor or a smartphone comprising said processor.

16. The system of claim 12 wherein said instructions are further configured for manipulating distortion parameters to generate a plurality of varying levels of simulated camera shake samples for use as said training samples.