Analyzing a segment of video

• US 9,014,429 B2
• Filed: 12/10/2013
• Issued: 04/21/2015
• Est. Priority Date: 11/27/2007
• Status: Active Grant

• Current Assignee: Intelliview Technologies Inc.
• Original Assignee: Intelliview Technologies Inc.
• Inventors: Badawy, Wael, Gomaa, Hazem
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US14/102,302
• Publication Number:
  US 20140098994A1
• Time in Patent Office: 497 Days
• Field of Search: 368/68
• US Class Current: 382/103
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• 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: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence

Abstract

There is disclosed a quick and efficient method for analyzing a segment of video, the segment of video having a plurality of frames. A reference portion is acquired from a reference frame of the plurality of frames. Plural subsequent portions are then acquired from a corresponding subsequent frame of the plurality of frames. Each subsequent portion is then compared with the reference portion, and an event is detected based upon each comparison. There is also disclosed a method of optimizing video including selectively storing, labeling, or viewing video based on the occurrence of events in the video. Furthermore, there is disclosed a method for creating a video summary of video which allows a used to scroll through and access selected parts of a video. The methods disclosed also provide advancements in the field of video surveillance analysis.

Claims

1. A method of analyzing a segment of video comprising frames, the frames comprising pixels, the method comprising:

extracting a respective line portion from a location on each frame of a plurality of frames of the segment of video, each respective line portion comprising a portion of pixels of the respective frame of the plurality of frames;

arranging the respective line portions from the location on each frame of the plurality of frames to form a visual summary,

detecting a portion of the pixels of the visual summary as corresponding to an object, in which one of the frames of the plurality of frames is a reference frame, and the portion of the pixels of the visual summary detected as corresponding to the object are detected as corresponding to the object based on a comparison of the pixels to corresponding pixels of the reference frame, and in which the portion of the pixels of the visual summary detected as corresponding to the object are detected as corresponding to the object based on a measure of the differences of the pixels of the portion of the pixels of the visual summary and the corresponding pixels of the reference frame, the portion of the pixels of the visual summary detected as corresponding to the object having a shape; and

determining a property of an event based on the shape of the portion of the pixels of the visual summary detected as corresponding to the object.

2. The method of claim 1 in which the location on each frame of the plurality of frames is defined by x-y pixel coordinates.

3. The method of claim 1 wherein determining the property of the event corresponds to detection of at least a characteristic of a vehicle.

4. The method of claim 1 further comprising storing, labeling, or both storing and labeling a video scene corresponding to the event.

5. The method of claim 1 further comprising retrieving a video scene corresponding to a selected line portion displayed on the visual summary.

6. The method of claim 1 further comprising:

manipulating a pointer to a desired line portion displayed in the visual summary;

retrieving a desired frame corresponding to the desired line portion from a memory unit; and

displaying the desired frame.

7. The method of claim 6 further comprising displaying at least a part of the segment of video from a location denoted by the desired frame.

8. The method of claim 6 further comprising selecting a video scene to be stored or labeled on the memory unit, the video scene corresponding to the desired line portion.

9. A method of analyzing a segment of video comprising frames, the frames comprising pixels, the method comprising:

extracting a respective line portion from a location on each flame of a plurality of frames of the segment of video, each respective line portion comprising a portion of pixels of the respective flame of the plurality of frames;

detecting a plurality of the line portions as corresponding to an object, in which one of the frames of the plurality of frames is a reference frame, and the plurality of line portions detected as corresponding to the object is detected as corresponding to the object based on a comparison of the pixels of the plurality of line portions to corresponding pixels of the reference frame, and in which each line portion of the plurality of line portions detected as corresponding to the object is detected as corresponding to the object based on a measure of the differences of the pixels of the line portion of the plurality of line portions and the corresponding pixels of the reference frame; and

determining a property of an event based on the plurality of line portions corresponding to the object.

10. The method of claim 9 in which the location on each frame of the plurality of frames is defined by x-y pixel coordinates.

11. The method of claim 9 wherein extracting the respective line portion from a location on each frame of the plurality of frames comprises extracting multiple line portions of each frame of the plurality of frames.

12. The method of claim 9 wherein detecting a plurality of the line portions as corresponding to an object comprises detecting a set of the line portions from a location on each frame of the plurality of frames as corresponding to a plurality of objects.

13. The method of claim 9 in which the measure of the difference of the pixels is a sum of pixel differences.

14. The method of claim 9 in which each line portion of the plurality of line portions detected as corresponding to the object is detected as corresponding to the object based on comparing the measure of the differences of the pixels of the line portion of the plurality of line portions and the corresponding pixels of the reference frame to a threshold.

15. The method of claim 14 in which the plurality of line portions is detected as corresponding to the object based on the measure of the differences of the pixels of the line portion of the plurality of line portions and the corresponding pixels of the reference frame being above the threshold for at least a predetermined number of frames.

16. The method of claim 14 in which the threshold is determined by a comparison of the reference frame to a set of frames in which no event is detected.

17. The method of claim 16 in which the comparison of the reference frame to a set of frames in which no event is detected comprises determining a sum of absolute differences of the pixels of a line portion of the plurality of line portions from the set of frames in which no event is detected and the corresponding pixels of the reference frame.