Video surveillance system employing video primitives

1. A method comprising:

detecting an object in a video from a single camera;

detecting a plurality of attributes of the object by analyzing the video from said single camera, the plurality of attributes including at least one of a physical attribute and a temporal attribute, each attribute representing a characteristic of the detected object;

selecting a new user rule after detecting the plurality of attributes; and

after detecting the plurality of attributes and after selecting the new user rule, identifying an event of the object that is not one of the detected attributes of the object by applying the new user rule to the plurality of detected attributes;

wherein the plurality of attributes that are detected are independent of which event is identified,

wherein the step of identifying the event of the object identifies the event without reprocessing the video, and

wherein the event of the object refers to the object engaged in an activity.

2. The method of claim 1 , wherein selecting the new user rule comprises selecting a subset of the plurality of attributes for analysis.

3. The method of claim 1 , wherein the plurality of attributes that are detected are defined in a device prior to a selection of a subset of the plurality of attributes.

4. The method of claim 1 , wherein no analysis is performed on at least some of the detected attributes to detect an event.

5. The method of claim 1 , wherein the plurality of attributes include plural physical attributes and the method comprises applying the new user rule to a plural number of physical attributes.

6. The method of claim 1 , wherein the plurality of attributes include plural temporal attributes and the method comprises applying the new user rule to a plural number of temporal attributes.

7. The method of claim 1 , further comprising:

storing the detected attributes in memory; and

identifying the event of the object by analyzing only a subset of the attributes stored in the memory.

8. A method comprising:

detecting first and second objects in a video from a single camera;

detecting a plurality of attributes of each of the detected first and second objects by analyzing the video from said single camera, each attribute representing a characteristic of the respective detected object;

selecting a new user rule; and

after detecting the plurality of attributes, identifying an event that is not one of the detected attributes of the first and second objects by applying the new user rule to the plurality of detected attributes;

wherein the plurality of attributes that are detected are independent of which event is identified,

wherein the step of identifying an event of the object comprises identifying a first event of the first object interacting with the second object by analyzing the detected attributes of the first and second objects, the first event not being one of the detected attributes, and

wherein the event of the object refers to the object engaged in an activity.

9. A video device comprising:

means for detecting an object in a video from a single camera;

means for detecting a plurality of attributes of the object by analyzing the video from said single camera, the plurality of attributes including at least a physical attribute and a temporal attribute, each attribute representing a characteristic of the detected object;

a memory storing the plurality of detected attributes;

means for selecting a new user rule after the plurality of detected attributes are stored in memory; and

means for identifying an event of the object that is not one of the detected attributes of the object by applying a selected new user rule to the plurality of attributes stored in memory, for identifying the event independent of when the attributes are stored in memory and for identifying the event without reprocessing the video, and

wherein the event of the object refers to the object engaged in an activity.

10. The video device of claim 9 , further comprising:

a video camera operable to obtain the video.

11. The video device of claim 9 , wherein the means for identifying an event of the object comprises means for identifying a first event of the object in real time by analyzing, of the plurality of attributes, only a first selected subset of the plurality of attributes.

12. The video device of claim 11 , wherein the means for identifying an event of the object comprises means for identifying a second event of the object by analyzing, of the plurality of attributes, only a second selected subset of the plurality of attributes that have been archived.

13. The video device of claim 9 , wherein applying a selected new user rule comprises analyzing, of the plurality of attributes, only a selected subset of the plurality of attributes.

14. The video device of claim 9 ,

wherein the memory is configured to store at least some of the plurality of attributes for at least two months, and

wherein the means for identifying an event of the object includes means for identifying an event of the object by analyzing only a selected subset of the plurality of attributes including the at least some of the plurality of attributes stored for at least two months.

15. The video device of claim 9 , wherein the means for identifying an event includes means for identifying the event by analyzing at least two selected physical attributes of the plurality of attributes.

16. The video device of claim 9 , wherein the identifying means identifies an event by analyzing a selection of individual ones of the detected plural attributes.

17. The video device of claim 9 , wherein the plural attributes detected by the means for detecting are defined in the video device independent of a selection of the detected plural attributes.

18. The video device of claim 9 , wherein the video surveillance device is a computer system configured as a video surveillance device.

19. The video device of claim 9 , further comprising video sensors.

20. A method comprising:

providing a video device which detects an object upon analyzing a video from a single camera and which detects plural attributes of the detected object upon analyzing the video from said single camera, the plurality of attributes including at least a physical attribute and a temporal attribute; and

then, selecting a rule, which is not a rule used to detect any individual attribute, as a new user rule, the new user rule providing an analysis of a combination of the attributes to detect an event that is not one of the detected attributes,

wherein the attributes to be detected are independent of the event to be detected, and

wherein the event of the object refers to the object engaged in an activity.

21. The method of claim 20 , further comprising:

providing a video device which detects an object upon analyzing a video and which detects plural physical attributes and plural temporal attributes of the detected object upon analyzing the video; and

then, selecting the new user rule to provide an analysis of a combination of the plural physical attributes and the plural temporal attributes to detect the event.

22. A non-transitory computer-readable storage medium containing instructions that when executed by a computer system cause said computer system to implement the following method comprising:

detecting an object in a video from a single camera;

detecting a plurality of attributes of the object by analyzing the video from said single camera, the plurality of attributes including at least one of a physical attribute and a temporal attribute, each attribute representing a characteristic of the detected object;

selecting a new user rule after detecting the plurality of attributes; and

after detecting the plurality of attributes and after selecting the new user rule, identifying an event of the object that is not one of the detected attributes of the object by applying the new user rule to the plurality of detected attributes, the event of the object being identified without reprocessing the video;

wherein the plurality of attributes that are detected are independent of which event is identified, and

wherein the event of the object refers to the object engaged in an activity.

23. The non-transitory computer-readable storage medium of claim 22 , wherein selecting the new user rule comprises selecting a subset of the plurality of attributes for analysis.

24. The non-transitory computer-readable storage medium of claim 22 , wherein the plurality of attributes that are detected are defined in a device prior to a selection of a subset of the plurality of attributes.

25. The non-transitory computer-readable storage medium of claim 22 , wherein the instructions executed by the computer system do not cause the computer system to perform an analysis on at least some of the detected attributes to detect an event.

26. The non-transitory computer-readable storage medium of claim 22 ,

wherein the plurality of attributes include plural physical attributes, and

wherein the method implemented by the computer system further comprises applying the new user rule to a plural number of physical attributes.

27. The non-transitory computer-readable storage medium of claim 22 ,

wherein the plurality of attributes include plural temporal attributes, and

wherein the method implemented by the computer system further comprises applying the new user rule to a plural number of temporal attributes.

28. The non-transitory computer-readable storage medium of claim 22 , wherein the method implemented by the computer system further comprises:

storing the detected attributes in memory; and

identifying the event of the object by analyzing only a subset of the attributes stored in the memory.

29. A non-transitory computer-readable storage medium containing instructions that when executed by a computer system cause said computer system to implement the following method comprising:

detecting first and second objects in a video from a single camera;

detecting a plurality of attributes of each of the detected first and second objects by analyzing the video from said single camera, each attribute representing a characteristic of the respective detected object;

selecting a new user rule; and

after detecting the plurality of attributes, identifying an event that is not one of the detected attributes of the first and second objects by applying the new user rule to the plurality of detected attributes;

wherein the plurality of attributes that are detected are independent of which event is identified,

wherein the step of identifying an event comprises identifying a first event of the first object interacting with the second object by analyzing the detected attributes of the first and second objects, the first event not being one of the detected attributes, and

wherein the event of the object refers to the object engaged in an activity.

30. A video device comprising:

means for detecting first and second objects in a video from a single camera;

means for detecting a plurality of attributes of the object by analyzing the video from said single camera, each attribute representing a characteristic of the respective detected object;

a memory storing the plurality of detected attributes; and

means for identifying an event of the first object interacting with the second object by applying a selected new user rule to the plurality of attributes stored in memory, and for identifying the event independent of when the attributes are stored in memory, the event not being one of the detected attributes,

wherein the event of the object refers to the object engaged in an activity.

31. The video device of claim 30 , further comprising:

a video camera operable to obtain the video.

32. The video device of claim 30 , wherein the means for identifying an event of the first object interacting with the second object comprises means for identifying a first event in real time by analyzing, of the plurality of attributes, only a first selected subset of the plurality of attributes.

33. The video device of claim 32 , wherein the means for identifying an event of the first object interacting with the second object comprises means for identifying a second event by analyzing, of the plurality of attributes, only a second selected subset of the plurality of attributes which have been archived.

34. The video device of claim 30 , wherein applying a selected new user rule comprises analyzing, of the plurality of attributes, only a selected subset of the plurality of attributes.

35. The video device of claim 30 ,

wherein the memory is configured to store at least some of the plurality of attributes for at least two months, and

wherein the means for identifying an event of the first object interacting with the second object includes means for identifying the event by analyzing only a selected subset of the plurality of attributes including the at least some of the plurality of attributes stored for at least two months.

36. The video device of claim 30 , wherein the means for identifying an event includes means for identifying the event without reprocessing the video.

37. The video device of claim 30 , wherein the means for identifying an event includes means for identifying the event by analyzing at least two selected physical attributes of the plurality of attributes.

38. The video device of claim 30 , wherein the identifying means identifies an event by analyzing a selection of individual ones of the detected plural attributes.

39. The video device of claim 30 , wherein the plural attributes detected by the means for detecting are defined in the video device independent of a selection of the detected plural attributes.

40. The video device of claim 30 , wherein the video surveillance device is a computer system configured as a video surveillance device.

41. The video device of claim 30 , further comprising video sensors.