View handling in video surveillance systems

• US 7,733,369 B2
• Filed: 09/28/2004
• Issued: 06/08/2010
• Est. Priority Date: 09/28/2004
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: ObjectVideo Incorporated (Alarm.com Holdings, Inc.)
• Inventors: Chosak, Andrew J., Myers, Gary W., Frazier, Matthew F., Haering, Niels, Zhang, Zhong, Lipton, Alan J., Yin, Weihong, Madden, Donald G., Sfekas, James S., Clark, John Ian Wallace, Egnal, Geoffrey, Venetianer, Péter L., Mannebach, Michael C.
• Primary Examiner(s): CZEKAJ, DAVID J
• Application Number:
  US10/950,680
• Publication Number:
  US 20060066722A1
• Time in Patent Office: 2,079 Days
• Field of Search: 348143-155, 348/169
• US Class Current: 348/143
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A method of video processing may include analyzing input video information to determine if a current video frame is directed to a same view as a previous video frame; determining whether a new view is present; and indicating a need to use video processing information pertaining to the new view if a new view is determined to be present.

Claims

1. A method of video processing, the method comprising:

receiving a single video feed provided by a source, wherein the source is one of a video buffer, a camera, or a multiplexer coupled to a plurality of cameras;

determining a known view model set comprising at least one known view model representing a scene of the single video feed and comprising a video frame from the single video feed and a background model of the scene;

creating video analytics functionally relevant to the scene represented by at least one known view model of the known view model set;

receiving a current frame from the single video feed;

determining which known view model from the known view model set represents the scene depicted in the current frame, wherein the determined known view model is designated as a current known view model;

performing video analytics for the current known view model on the current frame;

receiving a next frame from the single video feed; and

determining whether the next frame is directed to the current known view model by using video processing;

if the video processing determines that the next frame is directed to the current known view model, performing video analytics for the current known view model on the next frame; and

if the video processing determines that the next frame is not directed to the current known view model, determining whether the next frame is directed to any other known view model of the known view model set by using video processing;

if the video processing determines that the next frame is directed to a different known view model of the known view model set, performing video analytics for the different known view model on the next frame; and

if the video processing determines that the next frame is not directed to any other known view model of the known view model set, discarding the next frame.

2. The method according to claim 1, wherein said video processing comprises:

performing analysis to determine whether said next frame should be discarded by comparing a foreground area of the next frame with a threshold.

3. The method according to claim 1, further comprising:

maintaining a histogram of discarded frames according to discarded frame types; and

upon the occurrence of a predetermined number of consecutive discarded frames, determining that a gross change has occurred.

4. The method according to claim 3, further comprising:

if a gross change has occurred, selecting a type of gross change based on said histogram.

5. The method according to claim 3, further comprising:

clearing said histogram if said next frame is not a discarded frame.

6. The method according to claim 1, further comprising:

retrieving stored view information based on at least a portion of the current frame; and

using said stored view information to select an initial set of rules,

wherein view information comprises the background model of the current known view model.

7. The method according to claim 1, further comprising:

adding a new known view model based on the next frame to the known view model set.

8. The method according to claim 7, wherein said adding the new known view model comprises:

obtaining background data associated with a new view;

obtaining an image representing said new view;

storing said new view with the known view model set; and

providing view change notification to indicate a need to use new video analytics associated with said new known view model.

9. The method according to claim 1, wherein said video processing comprises:

evaluating if signal quality of said next frame falls outside an acceptable range.

10. A machine-readable medium containing instructions that, when executed by a processor, cause the processor to perform the method according to claim 1.

11. A computer system comprising:

a processor to receive the single video feed provided by the source; and

at least one computer-readable medium containing instructions that, when executed by the processor, cause the processor to perform the method according to claim 1.

12. The method according to claim 1, wherein the video processing to determine whether the next frame is directed to the cuffent known view model:

applying edge detection to images associated with the current known view model and the next frame model to obtain first and second edge images;

determining first and second edge masks for the first and second edge images;

determining first horizontal and vertical vectors for the first edge mask and second horizontal and vertical vectors for the second edge mask;

determining a horizontal correlation for the first and second horizontal vectors and a vertical correlation for the first and second vertical vectors; and

determining whether said next frame is directed to the current known view model based on the horizontal and vertical correlations.

13. The method according to claim 1, wherein the video analytics for the current known view model comprises:

enabling a rule set corresponding to the current known view model;

checking video primitives based on the current frame against the rule set;

detecting an event if a rule in the rule set has been satisfied by checking the video primitives; and

determining an appropriate response for the event.

14. The method according to claim 1, wherein the background model for the current known view model comprises a background mean and at least one standard deviation image.