Object selective video recording

• US 7,650,058 B1
• Filed: 01/08/2002
• Issued: 01/19/2010
• Est. Priority Date: 11/08/2001
• Status: Active Grant

• Current Assignee: Cernium Corporation (Kastle Systems International LLC)
• Original Assignee: Cernium Corporation (Kastle Systems International LLC)
• Inventors: Garoutte, Maurice V.
• Primary Examiner(s): Tran; Thai
• Assistant Examiner(s): Zhao; Daquan
• Application Number:
  US10/041,402
• Time in Patent Office: 2,933 Days
• Field of Search: 386/111, 386/109, 386/129, 386/68, 386/69, 386/95, 382/103, 382/104, 382/203
• US Class Current: 386/326
• CPC Class Codes: G08B 13/19604 involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change
• 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 13/19667 Details realated to data compression, encryption or encoding, e.g. resolution modes for reducing data volume to lower transmission bandwidth or memory requirements
• CPC Class Codes: G08B 13/19673 Addition of time stamp, i.e. time metadata, to video stream
• CPC Class Codes: H04N 5/915 for field- or frame-skip recording or reproducing
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 9/8042 involving data reduction

Abstract

An object selective video analysis and recordation system in which one or more video cameras provide video output to be recorded in a useful form on recording media with reduction of the amount of the recording media, with preservation of intelligence content of the output. Video output is both background video and object video, as images of objects appearing against a background scene. Preset knowledge of symbolic categories of objects in the scene and analysis of object attributes is provided by the system. Spatial resolution and temporal resolution of objects in the scene are automatically varied in accordance with preset criteria based on predetermined interest in the object attributes while recording the background video and object video. A user of the system may query recorded video images by content, enabling the user to recall recorded data according to symbolic content, by requesting data with specified symbolic content.

Claims

1. A system for selective video recording, comprising:

a video camera that provides output video;

a video separator that separates the output video into object video including one or more objects and background video against which the one or more objects appear;

a video analysis module that respectively identifies each of the one or more objects as a predetermined type of object by tracking each of the one or more objects over two or more video frames; and

a storage control module that independently stores the object video and background video, an object from the one or more objects being associated with an image header having an indication that the object is one of several predetermined types of objects, the image header having coordinate data associated with a position of the object in relation to the background video, the background video being associated with an image header having an indication that the background video is a background video,

wherein each of the one or more objects is recorded at a respective frame rate corresponding to the predetermined type of object identified by the video analysis module.

2. The system of claim 1, wherein the object from the one or more objects is a first object, the first object being identified as a first predetermined type of object and being recorded at a first frame rate, a second object from the one or more objects being identified as a second predetermined type of object and being is recorded at a second frame rate.

3. The system of claim 1, wherein the object from the one or more objects is recorded at a first frame rate for a first number of frames and is recorded at a second frame rate for a second number of frames.

4. The system of claim 1, wherein each of the one or more objects is recorded at a respective compression ratio corresponding to the predetermined type of object identified by the video analysis module.

5. The system of claim 4, wherein the object from the one or more objects is a first object, the first object being identified as a first predetermined type of object and being recorded at a first compression ratio, a second object from the one or more objects being identified as a second predetermined type of object and being recorded at a second compression ratio.

6. The system of claim 5, wherein the first object from the one or more objects is recorded at a first frame rate and the second object from the one or more objects is recorded at a second frame rate.

7. The system of claim 4, wherein the object from the one or more objects is a first object, the first object being recorded at a first compression ratio for a first number of frames, the first object being recorded at a second compression ratio for a second number of frames.

8. The system of claim 7, wherein the first object from the one or more objects is recorded at a first frame rate for the first number of frames and is recorded at a second frame rate for the second number of frames.

9. The system of claim 1, wherein the background video is recorded at a different frame rate than the one or more objects in the object video.

10. The system of claim 1,

wherein the storage control module further stores a textual identification of the type of each of the one or more objects;

and

further comprising a query module configured to receive a textual query that specifies at least one object type of interest and to retrieve, based on the textual identification of each of the one or more objects, object video and background video stored by the storage control module that corresponds to the textual query.

11. The system of claim 1, further comprising:

a playback control module that retrieves the object video and the background video and reconstructs the output video using the object video, the background video and the coordinate data from the image header associated with the object from the one or more objects.

12. The system of claim 1, wherein the object from the one or more objects is a sudden stop car or a fallen person.

13. The system of claim 1, wherein the object from the one or more objects is a first object, a second object from the one or more objects being associated with an image header having an indication that the second object is an object and having coordinate data associated with a position of the second object in relation to the background video.

14. The system of claim 1, wherein the background video is recorded at a different compression ratio than the one or more objects in the object video.