System and method for searching for changes in surveillance video
View Patent ↗Systems and methods for determining when a change has occurred in an area-of-interest included in an image region are disclosed. The system and methods may perform a specially modified background subtraction method. The systems and methods may initialize a background image region and then comparing a first image region from a second frame to the background image region to classify pixels as foreground pixels or background pixels. The foreground pixels are then classified based on predetermined characteristics. The background image region may then be updated to include foreground pixels that did not have the predetermined characteristics. The systems and methods allow for searching for background updates to thereby determine when a change has occurred in the area-of-interest.
1. A computerized method of determining when a change has occurred in an area-of-interest included in an image region of a series of video frames, the method comprising steps of:
initializing at least a portion of the image region as a background image region;
receiving a first video frame including pixels not included in th background image region;
classifying the pixels as foreground pixels;
based on subsequently received frames, updating the background image region to include at least one of the pixels previously classified as a foreground pixel; and
in response receiving a request from a user to identify the time at which the background image region was updated, presenting and the first video frame to the user.
2. The method of claim 1 , further comprising a step of recording when the background image region was updated.
3. The method of claim 2 , wherein the step of recording includes saving in a database the location of the second frame.
4. The method of claim 2 , further comprising a step of searching the recorded video to determine when the background image was updated.
5. The method of claim 4 , wherein the step of searching includes a step of determining whether all areas-of-interest have been processed.
6. The method of claim 4 wherein the step of searching includes a step of determining the number pixels that were incorporated into the background in the step of updating the background that are within the area-or-interest.
7. The method of claim 6 , further comprising a step of comparing the number pixels that were incorporated into the background in the step of updating the background that are within the area-or-interest with a threshold to determine if a threshold is exceed.
8. The method of claim 7 , further comprising a step of returning a positive search result if the threshold is exceeded.
9. The method of claim 7 , further comprising a step of backtracking to a frame where the pixels that were incorporated into the background were first classified as foreground pixels.
10. The method of claim 1 , wherein the step of classifying includes a step of classifying the foreground pixels based on a static property.
11. The method of claim 10 , wherein the static property is at least one of color, size, texture, or shape.
12. The method of claim 1 , wherein the step of classifying includes a step of classifying the foreground pixels based on a dynamic property.
13. The method of claim 12 , wherein the dynamic property is at least one of velocity, acceleration, change in size, change in area, change in color, or lack of motion.
14. The method of claim 1 , wherein the step of updating the background image includes a step of incorporating the at least one foreground pixel that does not embody the predetermined characteristics into the background image.
15. The method of claim 14 , wherein the step of incorporating includes overwriting the at least one foreground pixel onto the background image.
16. A computerized method of searching video information to determine when a change has occurred in an area-of-interest comprising the steps of:
classifying pixels within a first video frame as foreground pixels;
incorporating the foreground pixels into a background image after tracking the pixels for a series of frames;
recording, as a background update occurrence, when the foreground pixels were incorporated into the background in a database; and
in response to a request from a user for the background update occurrence, searching the database for background update occurrences, backtracking to the first video frame and presenting the first video frame to the user.
17. The method claim 16 , further comprising a step of classifying pixels as foreground pixels or background pixels.