Video event trigger and tracking system using fuzzy comparators

• US 5,539,454 A
• Filed: 02/06/1995
• Issued: 07/23/1996
• Est. Priority Date: 02/06/1995
• Status: Expired due to Term

• Current Assignee: National Aeronautics and Space Administration (Government of the United States of America)
• Original Assignee: The United States of America As Represented By The Secretary of Agriculture
• Inventors: Williams, Glenn L.
• Primary Examiner(s): Kostak, Victor R.
• Assistant Examiner(s): Acosta, Juan G.
• Application Number:
  US08/386,999
• Time in Patent Office: 533 Days
• Field of Search: 348/169, 348/172, 348/170, 348/155, 348/700, 348/701
• US Class Current: 348/169
• CPC Class Codes: G01S 3/7865 using correlation of the live video image with a stored image
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19667 Details realated to data compression, encryption or encoding, e.g. resolution modes for reducing data volume to lower transmission bandwidth or memory requirements

Abstract

A video observation method and apparatus, the apparatus having a frame storage mechanism, a dividing mechanism, a plurality of fuzzy comparators and a trigger signal mechanism. The frame storage mechanism stores at least one non-current video frame of a viewing field. The dividing mechanism divides a current video frame of the viewing field and the at least one non-current video frame into a plurality of corresponding trigger sections. The plurality of fuzzy comparators each compare and detect a fuzzy logic difference between one trigger section of the current video frame and the corresponding trigger sections of the at least one non-current video frame, the number of fuzzy comparators being selected so that every trigger section of the current video frame is compared. The trigger signal mechanism provides a trigger signal when a fuzzy logic difference is detected between any of the corresponding current and non-current trigger sections. A video observation mechanism and data reducing mechanism may be included with the above apparatus or alone with only a frame storage mechanism, a single generic comparator and a trigger signal mechanism. The video observation mechanism provides a video data stream, wherein each pixel of each frame of a viewing field is provided as multiple bits of data. The data reducing mechanism reduces each set of multiple bits of data which correspond to each pixel to one bit of binary data based on whether the pixel has a level of grey which is above or below a threshold level of grey.

Claims

1. A video observation apparatus, comprising:

a video camera;

frame storage means, operatively connected to the video camera, for storing at least one non-current video frame of a viewing field;

dividing means, operatively connected to the frame storage means, for dividing a current video frame of the viewing field and at least one non-current video frame into a plurality of corresponding trigger sections;

a plurality of fuzzy comparator means, operatively connected to the dividing means, each for comparing and detecting a fuzzy logic difference between one trigger section of the current video frame and the corresponding trigger sections of the at least one non-current video frame, the number of fuzzy comparator means being selected so that every trigger section of the current video frame is compared, the fuzzy logic difference being a degree of mismatch; and

trigger signal means, operatively connected to the fuzzy comparator means, for providing a trigger signal when a fuzzy logic difference is detected between any of the corresponding current and non-current trigger sections.

2. The video observation apparatus as claimed in claim 1, wherein the non-current video frames are at least one video frame taken immediately prior to the current video frame.

3. The video observation apparatus as claimed in claim 1, wherein the non-current video frames are at least one video frame taken at a time prior to the current video frame with a plurality of video frames between the non-current and current video frames.

4. The video observation apparatus as claimed in claim 1, wherein the trigger signal is provided within four milliseconds of an action which causes the fuzzy logic difference to be detected and thereby the trigger signal to be produced.

5. The video observation apparatus as claimed in claim 1, further comprising:

greatest fuzzy logic difference detecting means, operatively connected to said trigger signal means, for determining in which trigger section was the greatest fuzzy logic difference detected;

motion tracking means, operatively connected to the greatest fuzzy logic difference detecting means, for dividing into corresponding tracking sections the current video frame trigger section and the corresponding at least one non-current video frame trigger section in which the greatest fuzzy logic difference was detected, the number of tracking sections being the same as the number of fuzzy comparator means, the motion tracking means providing one set of corresponding tracking sections to each of the fuzzy comparator means for comparing and detecting a fuzzy logic difference; and

tracking signal means, operatively connected to said motion tracking means, for providing a tracking signal which contains information as to which fuzzy comparator means detected a fuzzy logic difference between the corresponding tracking sections.

6. The video observation apparatus as claimed in claim 5, wherein a viewing field is divided lengthwise in a first direction and heightwise in a second direction to determine the trigger sections, and the motion tracking means divides the trigger section lengthwise in the second direction and heightwise in the first direction to determine the tracking sections.

7. A video observation apparatus, comprising:

video observation means for providing a video data stream, wherein each pixel of each frame of a viewing field is provided as multiple bits of data;

data reducing means for reducing each set of multiple bits of data which correspond to each pixel to one bit of binary data based on whether the pixel has a level of grey which is above or below a threshold level of grey;

frame storage means for storing at least one non-current data reduced video frame of the viewing field;

a comparator means for comparing and detecting a fuzzy logic difference between the reduced data of a current video frame and the reduced data of the at least one non-current video frames, the fuzzy logic difference being a degree of mismatch; and

trigger signal means for providing a trigger signal when the fuzzy logic difference is detected between any of the reduced data of the current and non-current video frames.

8. The video observation apparatus as claimed in claim 7, wherein the non-current video frames are at least two data reduced video frames taken immediately prior to the current video frame.

9. The video observation apparatus as claimed in claim 7, wherein the non-current video frames are at least two data reduced video frames taken at a time prior to the current video frame with a plurality of video frames between the non-current and current video frames.

10. A video observation method, comprising the steps of:

storing at least one non-current data-reduced video frame of a viewing field;

dividing a current data-reduced video frame of said viewing field and said at least one non-current data-reduced video frame into a plurality of corresponding trigger sections;

using a plurality of fuzzy comparators to compare and detect a fuzzy logic difference between each trigger section of the current video frame and the corresponding trigger sections of the at least one non-current video frame, the fuzzy logic difference being a degree of mismatch; and

providing a trigger signal when a fuzzy logic difference is detected between any of the corresponding current and non-current trigger sections.

11. The video observation method as claimed in claim 10, wherein the non-current video frames are at least two data-reduced video frames taken immediately prior to the current video frame.

12. The video observation method as claimed in claim 10, wherein the non-current video frames are at least two data-reduced video frames taken at a time prior to the current video frame with a plurality of video frames between the non-current and current video frames.

13. The video observation method as claimed in claim 11, wherein the trigger signal is provided within milliseconds of an action which causes the fuzzy logic difference to be detected and thereby the trigger signal to be produced.

14. The video observation method as claimed in claim 11, further comprising the steps of:

determining in which trigger section the greatest fuzzy logic difference detected;

dividing into corresponding tracking sections the current video frame trigger section and the corresponding at least one non-current video frame trigger section in which the greatest fuzzy logic difference was detected, the number of tracking sections being the same as the number of fuzzy comparator means;

using the plurality of fuzzy comparators to compare and detect a fuzzy logic difference between each tracking section of the current video frame and the corresponding tracking sections of the at least one non-current video frame; and

providing a tracking signal which contains information on which of the corresponding tracking sections detected a fuzzy logic difference.

15. The video observation method as claimed in claim 14, wherein the viewing field is divided lengthwise in a first direction and heightwise in a second direction to arrive at the trigger sections, and the trigger section in which the greatest fuzzy logic difference is detected is divided lengthwise in the second direction and heightwise in the first direction to arrive at the tracking sections.

16. The video observation method as claimed in claim 10, further comprising the steps of:

providing a video data stream, wherein each pixel of each frame of the viewing field is provided as multiple bits of data; and

reducing each set of multiple bits of data which correspond to each pixel to one bit of binary data based on whether the pixel has a level of grey which is above or below a threshold level of grey, the data being reduced before being compared by the comparator means.

17. A video observation method, comprising the steps of:

providing a video data stream, wherein each pixel of each frame of a viewing field is provided as multiple bits of data;

reducing each set of multiple bits of data which correspond to each pixel to one bit of binary data based on whether the pixel has a level of grey which is above or below a threshold level of grey;

storing at least one non-current video frame of the viewing field;

comparing and detecting a fuzzy logic difference between the reduced data of a current and the reduced data of the at least one non-current video frames, the fuzzy logic difference being a degree of mismatch; and

providing a trigger signal when the fuzzy logic difference is detected between any of the reduced data of the current and non-current video frames.