VIDEO CAMERA HAVING RELATIONAL VIDEO DATABASE WITH ANALYTICS-PRODUCED METADATA

• US 20110050947A1
• Filed: 11/05/2010
• Published: 03/03/2011
• Est. Priority Date: 03/03/2008
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: VideoIQ, Inc. (Motorola Solutions, Inc.)
• Inventors: Marman, Douglas H., Saptharishi, Mahesh
• Granted Patent: US 8,736,701 B2
• Time in Patent Office: Days
• US Class Current: 348/222.1
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices
• CPC Class Codes: H04N 5/772 the recording apparatus and the television camera being placed in the same enclosure
• CPC Class Codes: H04N 9/7921 for more than one processing mode
• CPC Class Codes: H04N 9/8205 involving the multiplexing of an additional signal and the colour video signal

Abstract

Video analytics and a mass storage unit are contained in a camera housing of a video camera. The camera produces video data representing the field of view of a scene observed by the camera. The video analytics analyzes the video data and detects whether there is an occurrence of a defined feature of an object or a defined event of interest. The video analytics also generates metadata based upon the content of the video data. The video data and metadata are stored in the mass storage unit. Access to stored video data may be controlled based on content, and access to live video data may be controlled as metadata corresponding to the video data is created. The metadata can be used to search for corresponding video data representing the detected feature of an object or event of interest observed in the scene.

Claims

1. A method of implementing in a video camera content aware detection of a feature of an object of interest or an occurrence of an event of interest and use of metadata to search for video data stored in a mass storage unit and representing the detected feature of an object or event of interest, the video camera including a camera housing and producing video data representing a field of view of a scene observed by the video camera, comprising:

using a configured feature of an object of interest or configured event of interest for detection by analysis of the video data produced by the video camera, the video camera provided with video analytics and a mass storage unit contained in or forming part of the camera housing;

causing the video analytics to analyze the video data produced by the video camera and detect whether there is an occurrence of the feature of an object or the event of interest, the video analytics generating metadata corresponding to the video data representing the feature of an object or the event of interest detected by the video analytics;

storing in the mass storage unit the metadata and the corresponding video data representing the detected feature of an object or event of interest observed in the scene; and

using the metadata to search for the corresponding stored video data representing the detected feature of an object or event of interest observed in the scene.

2. The method of claim 1, in which the event of interest includes motion detected within the field of view of the video camera.

3. The method of claim 1, in which the event of interest includes motion of a blob detected within the field of view of the video camera.

4. The method of claim 1, in which the event of interest includes recognizing a predefined object or tracking movement of the predefined object.

5. The method of claim 4, in which the video analytics uses geometric calibration to recognize the predefined object as it moves to various portions of the field of view.

6. The method of claim 1, in which the video data are stored at a second bit rate when no feature of an object or event of interest is detected and are stored at a first bit rate when the feature of an object or the event of interest is being detected.

7. The method of claim 1, in which the feature of an object of interest includes one of a type of the object, size of the object, speed of the object, trajectory of the object, location of the object, appearance of the object, and number count of the object.

8. The method of claim 1, further comprising using a rules based engine in operative association with the video analytics, the rules based engine defining rules specifying features of an object or events of interest that are detectable by the video analytics.

9. The method of claim 8, in which the rules are defined in the rules engine before the video camera produces the video data.

10. A method of using metadata to search for video data stored in mass storage units associated with video cameras in a distributed network video surveillance system, the video cameras producing video data representing scenes under observation by the video cameras and including camera housings, comprising:

using a configured feature of an object of interest or configured event of interest for detection by analysis of the video data produced by the video cameras, the video cameras provided with video analytics and associated mass storage units contained in or forming part of the camera housings;

causing the video analytics to analyze the video data produced by the video cameras and detect whether there is an occurrence of the feature of an object or the event of interest, the video analytics generating metadata corresponding to the video data representing the feature of an object or the event of interest detected by the video analytics;

storing in the mass storage units the metadata and the corresponding video data representing the detected feature of an object or event of interest observed in the scenes; and

using the metadata to search for the corresponding stored video data representing the detected feature of an object or event of interest observed in the scenes.

11. The method of claim 10, in which the video data represent fields of view of the scenes under observation by the video cameras, and in which the event of interest includes motion detected within one or more of the fields of view of the video cameras.

12. The method of claim 10, in which the video data represent fields of view of the scenes under observation by the video cameras, and in which the event of interest includes motion of a blob detected within one or more of the fields of view of the video cameras.

13. The method of claim 10, in which the video data represent fields of view of the scenes under observation by the video cameras, and in which the event of interest includes recognizing a predefined object and tracking movement of the predefined object.

14. The method of claim 13, in which the video analytics uses geometric calibration to recognize the object as the object moves to various portions of one or more of the fields of view.

15. The method of claim 10, in which the feature of an object of interest includes one of a type of the object, size of the object, speed of the object, trajectory of the object, location of the object, appearance of the object, and number count of the object.

16. The method of claim 10, further comprising using rules based engines in operative association with the video analytics, the rules based engines defining rules specifying features of an object or events of interest that are detectable by the video analytics.

17. The method of claim 16, in which the rules are defined in the rules engines before the video cameras produce the video data.