Method and system to characterize video background changes as abandoned or removed objects
View Patent ↗A method and system for analyzing video data in a security system. An analysis compares a current frame to a background model. The analysis system compares the background model to the current frame to identify changed pixel patches. The analysis system uses morphological image processing to generate masks based on the changed pixel patches. Next, the analysis system applies the masks to the background model and the current frames to determine whether the changed pixel patches are characteristic of abandoned or removed objects within the video data.
1. A method for analyzing video data in a security system, the method comprising:
comparing a background model to at least one frame of the video data to identify at least one patch of changed pixels between the background model and the at least one frame;
generating masks based on the at least one patch of changed pixels that define contours around the at least one patch of changed pixels; and
applying the masks to the background model and the at least one frame and calculating similarity scores, which characterize degrees of similarity, based on the masks to determine whether the at least one patch of changed pixels is characteristic of an abandoned object or a removed object.
2. The method according to claim 1 , further comprising computing the similarity score for the at least one frame as a sum of the square of dot product between a gradient vector computed for a blurred difference mask and a gradient vector for the at least one frame over border pixels of a boundary mask.
3. The method according to claim 1 , further comprising computing the similarity score for the background model as a sum of the square of dot product between a gradient vector computed for a blurred difference mask and a gradient vector for the background model over border pixels of a boundary mask.
4. The method according to claim 1 , further comprising associating metadata with the at least one frame and creating alerts based on the metadata.
5. The method according to claim 1 , further comprising performing morphological image processing on the at least one patch of changed pixels.
6. The method according to claim 5 , wherein the morphological image processing includes dilations.
7. The method according to claim 5 , wherein the morphological image processing includes erosions.
8. The method according to claim 1 , further comprising blurring the at least one frame and background model to reduce noise and variations.
9. The method according to claim 1 , further comprising converting the masks to a high precision representation.
10. The method according to claim 1 , further comprising continually updating the background model based determination of abandoned objects and/or removed objects.
11. A security system comprising:
video cameras to capture video data;
a video recorder to store the captured video data;
an analysis system that analyzes the video data of the security system; and
wherein the analysis system compares a background model to at least one frame of the video data to identify at least one patch of changed pixels between the background model and the at least one frames, generates masks based on the at least one patch of changed pixels, which define contours around the at least one patch of changed pixels, applies the masks to the background model and the at least one frame, calculates similarity scores, which characterize degrees of similarity, based on the masks, and determines whether the at least one patch of changed pixels is characteristic of abandoned objects or removed objects.
12. The system according to claim 11 , wherein the analysis system computes the similarity score for the at least one frame as a sum of the square of dot product between a gradient vector computed for a blurred difference mask and a gradient vector for the at least one frame over border pixels of a boundary mask.
13. The system according to claim 11 , wherein the analysis system computes a similarity score for the background model as a sum of the square of dot product between a gradient vector computed for a blurred difference mask and a gradient vector for the background model over all border pixels of a boundary mask.
14. The system according to claim 11 , wherein the analysis system associates metadata with the at least one frame and creating alerts based on the metadata.
15. The system according to claim 11 , wherein the analysis system performs morphological image processing on the at least one patch of changed pixels.
16. The system according to claim 15 , wherein the morphological image processing includes dilations.
17. The system according to claim 15 , wherein the morphological image processing includes erosions.
18. The system according to claim 11 , wherein the analysis system blurs the at least one frame and background model to reduce noise and variations.
19. The system according to claim 11 , wherein the analysis system converts the masks to a high precision representation.
20. The system according to claim 11 , wherein the analysis system continually updates the background model based determination of abandoned objects and/or removed objects.