VIDEO SYSTEM WITH INTELLIGENT VISUAL DISPLAY

• US 20120062732A1
• Filed: 09/10/2010
• Published: 03/15/2012
• Est. Priority Date: 09/10/2010
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: VideoIQ, Inc. (Motorola Solutions, Inc.)
• Inventors: Marman, Douglas H., Saptharishi, Mahesh, Glozman, Levi, Ushomirsky, Michael
• Granted Patent: US 10,645,344 B2
• Time in Patent Office: Days
• US Class Current: 348/142
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• 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 13/19671 Addition of non-video data, i.e. metadata, to video stream
• CPC Class Codes: G08B 13/19682 Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A video system for intelligent visual display includes a video camera having an imager that produces a first set of image data representing an image of a scene. Video analytics receive and analyze the first set of image data to track an object. The video analytics generate metadata synchronized to the first set of image data and representing location information of an image of the object in the image of the scene. A display management module receives the first set of image data and the metadata and uses the metadata to derive from the first set of image data a second set of image data representing a cropped close-up image of the object. The second set of image data is distinct from the first set of image data to enable separate display presentation of the cropped close-up image and the image of the scene.

Claims

1. A video system for intelligent visual display of an object of interest, comprising:

a video camera having an imager that produces a first set of image data representing an image of a scene within a field of view of the video camera;

video analytics receiving and analyzing the first set of image data to track an object of interest present in the scene, the video analytics generating metadata representing location information corresponding to a location of an image of the object of interest in the image of the scene, the metadata being synchronized to the first set of image data; and

a display management module receiving the first set of image data and the metadata, the display management module using the metadata to derive from the first set of image data a second set of image data representing a cropped close-up image of the object of interest, the second set of image data being distinct from the first set of image data to enable separate display presentation of the cropped close-up image of the object of interest and the image of the scene.

2. The video system of claim 1, further comprising a display system including a display, the display system receiving the first set of image data in a first data stream to enable the display to present the image of the scene in a first viewing window, and the display system receiving the second set of image data in a second data stream distinct from the first data stream to enable the display to present the cropped close-up image of the object in a second viewing window.

3. The video system of claim 1, in which the first set of image data represents a full resolution image of the scene.

4. The video system of claim 1, in which the first set of image data represents a mega-pixel image of the scene.

5. The video system of claim 1, further comprising a data storage system for storing the first set of image data to enable playback display presentation of the image of the scene.

6. The video system of claim 5, in which the metadata are stored in the data storage system.

7. The video system of claim 5, in which the video camera includes a camera housing and the data storage system includes a storage device that is contained in or forms a part of the camera housing, the first set of image data being stored in the storage device.

8. The video system of claim 7, in which the storage device stores the second set of image data to enable playback display presentation of the cropped close-up image of the object of interest.

9. The video system of claim 1, in which the object of interest is a first object of interest, a second object of interest is present in the scene, the video analytics analyze the first set of image data to track the first and second objects of interest, and the metadata represent location information corresponding to locations of images of the first and second objects of interest in the image of the scene.

10. The video system of claim 9, in which the display management module is operable to use the metadata to derive a cropped close-up image that includes the first and second objects of interest.

11. The video system of claim 9, in which the video analytics are operable to track the first object of interest independent of the second object of interest, and in which the metadata generated by the video analytics include identification information of the first object of interest, the display management module being operable to use the metadata to identify the first object of interest so that the cropped close-up image is localized corresponding to the first object of interest.

12. The video analytics of claim 11, in which the localized cropped close-up image of the first object of interest is a first localized image, the video analytics are operable to track the second object of interest independent of the first object of interest, and the metadata generated by the video analytics include identification information of the second object of interest, the display management module being operable to use the metadata to identify the second object of interest to derive from the first set of image data a second localized image representing a cropped close-up image that is localized corresponding to the second object of interest.

13. The video system of claim 11, in which the display management module is a first display management module, the video analytics being operable to track the second object of interest independent of the first object of interest, and the metadata generated by the video analytics including identification information of the second object of interest, further comprising:

a second display management module receiving the first set of image data and the metadata, the second display management module using the second set of metadata to derive from the first set of image data a third set of image data representing a cropped close-up image that is localized corresponding to the second object of interest, the third set of image data being distinct from the first set of image data;

a first display system having a first display, the first display system communicating with the first display management module and receiving the second set of image data so that the localized cropped close-up image of the first object of interest is presented on the first display; and

a second display system having a second display, the second display system communicating with the second display management module and receiving the third set of image data so that the localized cropped close-up image of the second object of interest is presented on the second display.

14. The video system of claim 1, in which the video camera includes a camera housing and the video analytics are contained in or form a part of the camera housing.

15. The video system of claim 14, in which the display management module is part of a processor that is remote from the video camera.

16. The video system of claim 15, in which the video camera includes a communication interface for transmitting to the display management module the first set of image data and the metadata in a data stream, the data stream comprising a first track that includes the first set of image data and a second track that includes the metadata.

17. The video system of claim 16, in which the first set of image data represents multiple video frames of the scene and the metadata includes multiple metadata frames representing location information corresponding to locations of images of the object of interest in the multiple video frames, each of the metadata frames corresponding and being synchronized to a distinct one of the multiple video frames.

18. The video system of claim 1, in which the video camera includes a camera housing and the video analytics and the display management module are each contained in or form a part of the camera housing.

19. The video system of claim 18, further comprising a display system including a display, the video camera including a communication interface for transmitting to the display system the first and second sets of image data, the video camera transmitting to the display system the first set of image data in a first data stream and the second set of image data in a second data stream distinct from the first data stream.

20. The video system of claim 1, further comprising a data storage system for storing a video data stream produced by the video camera, the video data stream including a first segment corresponding to non-event video data and a second segment in which the object of interest is present in the scene, the second segment including a representation of the cropped close-up image of the object of interest derived by the display management module, the metadata including activity level information associated with the first and second segments that distinguishes the second segment from the first segment, the activity level information enabling adaptive control of playback speed of the video data stream in which the second segment is played at an event playback speed.

21. The video system of claim 20, in which the display management module is operable to play the first segment of the video data stream at a non-event playback speed that is faster than the event playback speed, the display management module being operable to automatically switch between the non-event playback speed and the event playback speed when transitioning between playback of the first and second segments.

22. The video system of claim 21, in which a resolution of the first segment of the video data stream is the same as a resolution of the second segment.

23. The video system of claim 20, in which the display management module is operable to skip over the first segment during playback of the video data stream.

24. A method for producing an intelligent visual display of an object of interest captured by a video camera, comprising:

producing a first set of image data representing video images of a scene within a field of view of a video camera;

providing video analytics that analyze the first set of image data to track an object of interest present in the scene, the video analytics generating metadata synchronized to the first set of image data, the metadata representing location information corresponding to locations of images of the object of interest in the video images of the scene; and

operating a display management module that receives the first set of image data and the metadata, the display management module using the metadata to derive from the first set of image data a second set of image data representing cropped close-up video images of the object of interest, the second set of image data being distinct from the first set of image data to thereby enable separate display of the cropped close-up video images of the object of interest from the video images of the scene.

25. The method of claim 24, further comprising storing in a data storage system the first set of image data to enable playback display presentation of the video images of the scene.

26. The method of claim 25, further comprising storing the metadata in a data storage system.

27. The method of claim 24, in which the video images represented in the first set of image data are high resolution images and the cropped close-up images represented in the second set of image data are characterized by a resolution lower than the resolution of the high resolution images of the first set of image data, and in which the video camera includes a housing and a storage device contained in or forming part of the housing, further comprising storing the first set of image data, the second set of image data, and the metadata in the storage device.

28. The method of claim 24, in which the video images of the scene represented by the first set of image data are characterized by a first resolution, and in which the video camera includes a housing and a storage device contained in or forming part of the housing, further comprising:

producing from the first set of image data a third set of image data representing low resolution video images of the scene, the low resolution video images having a second resolution less than the first resolution; and

storing in the storage device the third set of image data.

29. The method of claim 28, in which the cropped close-up images represented in the second set of image data are characterized by a resolution lower than the first resolution, further comprising storing the second set of image data in the storage device.

30. The method of claim 24, further comprising storing a snapshot image of the object of interest, the snapshot image being derived from the cropped close-up video images of the object of interest.

31. The method of claim 30, in which the snapshot image corresponds to a cropped close-up image of the object of interest corresponding to an instance in time when the object of interest triggered an alarm.

32. The method of claim 30, further comprising selecting with the video analytics one of the cropped close-up images to use as the snap shot image, the selection being based on image quality.

33. The method of claim 24, in which the cropped close-up images of the object of interest include a cropped close-up image of a selected feature of the object of interest.

34. The method of claim 33, in which the object of interest is a human and the selected feature corresponds to the face of the human.

35. The method of claim 33, in which the object of interest is a vehicle and the selected feature is an identifying feature of the vehicle.

36. The method of claim 24, in which the object of interest is one of multiple objects present in the scene and represented in the first set of image data, further comprising:

tracking the multiple objects of interest using the video analytics, the metadata generated by the video analytics including identification information and location information for the multiple objects;

deriving from a video image represented in the first set of image data multiple cropped close-up images corresponding to the multiple objects of interest.

37. The method of claim 36, further comprising storing the multiple cropped close-up images and the video image from which the multiple cropped close-up images are derived.

38. The method of claim 24, further comprising:

determining whether the object of interest has violated a rule; and

deriving the second set of image data when the object of interest violates the rule.