Method and apparatus for processing video frame

• US 8,922,649 B2
• Filed: 05/19/2008
• Issued: 12/30/2014
• Est. Priority Date: 08/29/2007
• Status: Active Grant

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: Kim, Kwang Baek
• Primary Examiner(s): ELFERVIG, TAYLOR A
• Application Number:
  US12/122,862
• Publication Number:
  US 20090059002A1
• Time in Patent Office: 2,416 Days
• Field of Search: 348/143
• US Class Current: 348/143
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm
• CPC Class Codes: G08B 13/19671 Addition of non-video data, i.e. metadata, to video stream
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A surveillance video processing method including selecting at least one target object from a surveillance area, capturing image information of the surveillance area, detecting motion has occurred in the surveillance area using the captured image information, extracting feature data of an object causing the detected motion, comparing the extracted feature data of the object causing the detected motion and feature data of the at least one target object, and determining whether or not to perform a recording operation for recording the captured image information based on a result of the comparing step.

Claims

1. A surveillance video processing method, comprising:

selecting at least one target object from a surveillance area;

capturing images of the surveillance area;

detecting whether motion has occurred in the surveillance area by calculating a motion component between a current frame and a neighboring frame of the captured images and determine whether the motion component of the detected motion is equal to or greater than a certain value;

extracting feature data of an object causing the detected motion;

determining a type of object and distinguishing between objects of a same type based on the extracted feature data;

comparing the extracted feature data of the object causing the detected motion and feature data of the at least one target object;

deciding whether the object causing the motion is identical or similar to the target object; and

determining whether or not to perform a recording operation for recording the captured images based on a result of the decision,

wherein when the deciding step decides the object causing the motion is identical or similar to the target object, the determining step does not perform the recording operation, and

wherein, when the deciding step decides the object causing the motion is not identical or similar to the target object, the determining step performs the recording operation;

assigning priority levels to sub-areas within the surveillance area;

assigning a priority level to the target object;

determining if the assigned priority level of the target object is less than an assigned priority level of a corresponding sub-area when the target object is viewed within the corresponding sub-area of the surveillance area;

performing a predetermined camera function to capture images of the target object based on a result of the determining step;

wherein the performing step performs a camera zooming function and records the images captured for the target object in the corresponding sub-area when the determining step determines the assigned priority level of the target object is less than the assigned priority level of the corresponding sub-area and when a difference of the priority levels is more than one level, and performs a non-zooming camera function and records the images captured for the target object in the corresponding sub-area when the determining step determines the assigned priority level of the target object is less than the assigned priority level of the corresponding sub-area and when a difference of the priority levels is one level.

2. The video processing method of claim 1, wherein the feature data of the at least one target object and the object causing the detected motion comprises at least one of a shape, a size, a texture, a color, an edge, and a motion of the object.

3. The video processing method of claim 1, further comprising:

storing the feature data of the target object before extracting the feature data of the object causing the detected motion.

4. The video processing method of claim 3, wherein the storing step stores the feature data of the target object in association with a corresponding target object ID.

5. The video processing method of claim 3, wherein the storing step stores the feature data of the target object in association with information indicating an area where motion of the target object will occur.

6. The video processing method of claim 3, wherein the storing step stores the feature data of the target object in association with valid channel information indicating that motion generated by the target object is to be disregarded.

7. The video processing method of claim 3, wherein the storing step stores the feature data of the target object in association with information indicating a level of a channel in which motion generated by the target object is to be disregarded.

8. The video processing method of claim 1, wherein the selecting step comprises a user selecting the target object by designating a portion within the surveillance area.

9. The video processing method of claim 1, wherein the comparing step compares a plurality of feature factors corresponding to the feature data between the target object and the object causing the motion.

10. The video processing method of claim 9, wherein the comparing step decides the object causing the motion is identical or similar to the target object when a predetermined number of the feature factors are identical or similar to each other, or a degree in which the feature factors are identical to each other is above a predetermined threshold.

11. The video processing method of claim 1, wherein the performing step does not record the images captured for the target object in the corresponding sub-area when the determining step determines the assigned priority level of the target object is not less than the assigned priority level of the corresponding sub-area.

12. The video processing method of claim 1, wherein the type of object is persons.

13. A surveillance video processing apparatus, comprising:

an input device allows a user to select at least one target object from a surveillance area;

a camera captures images of the surveillance area;

a motion detector detects motion has occurred in the surveillance area by calculating a motion component between a current frame and a neighboring frame of the captured images and determine whether the motion component of the detected motion is equal to or greater than a certain value;

a feature extractor extracts feature data of an object causing the detected motion; and

a controller;

determines a type of object and distinguishing between objects of a same type based on the extracted feature data;

compares the extracted feature data of the object causing the detected motion and feature data of the at least one target object;

decides whether the object causing the motion is identical or similar to the target object; and

determines whether or not to perform a recording operation for recording the captured images based on a result of the decision when the motion detector determines the detected motion component is equal to or greater than a certain value,

wherein when the controller decides the object causing the motion is identical or similar to the target object, the controller does not perform the recording operation,

wherein, when the controller decides the object causing the motion is not identical or similar to the target object, the controller performs the recording operation, and

wherein the input device, the camera, the motion detector and the feature extractor operate under a control of the controller;

wherein the controller assigns priority levels to sub-areas within the surveillance area, and to assign a priority level to the target object, and

wherein the controller determines if the assigned priority level of the target object is less than an assigned priority level of a corresponding sub-area when the target object is viewed within the corresponding sub-area of the surveillance area, and to perform a predetermined camera function to capture images of the target object based on a result of the determination;

wherein the controller performs a camera zooming function and record the images captured for the target object in the corresponding sub-area when the controller determines the assigned priority level of the target object is less than the assigned priority level of the corresponding sub-area and when a difference of the priority levels is more than one level, and to perform a non-zooming camera function and record the images captured for the target object in the corresponding sub-area when the controller determines the assigned priority level of the target object is less than the assigned priority level of the corresponding sub-area and when a difference of the priority levels is one level.

14. The video processing apparatus of claim 13, wherein the feature data of the at least one target object and the object causing the detected motion comprises at least one of a shape, a size, a texture, a color, an edge, and a motion of the object.

15. The video processing apparatus of claim 13, further comprising:

a memory stores the feature data of the target object before extracting the feature data of the object causing the detected motion.

16. The video processing apparatus of claim 15, wherein the memory stores the feature data of the target object in association with a corresponding target object ID.

17. The video processing apparatus of claim 15, wherein the memory stores the feature data of the target object in association with information indicating an area where motion of the target object will occur.

18. The video processing apparatus of claim 15, wherein the memory stores the feature data of the target object in association with valid channel information indicating that motion generated by the target object is to be disregarded.

19. The video processing apparatus of claim 15, wherein the memory stores the feature data of the target object in association with information indicating a level of a channel in which motion generated by the target object is to be disregarded.

20. The video processing apparatus of claim 13, wherein the input device comprises a designation feature allowing a user to select the target object by designating a portion within the surveillance area.

21. The video processing apparatus of claim 13, wherein the controller compares a plurality of feature factors corresponding to the feature data between the target object and the object causing the motion.

22. The video processing apparatus of claim 21, wherein the controller decides whether the object causing the motion is identical or similar to the target object when a predetermined number of the feature factors are identical or similar to each other, or a degree in which the feature factors are identical to each other is above a predetermined threshold.

23. The video processing apparatus of claim 13, wherein the controller does not record the images captured for the target object in the corresponding sub-area when the controller determines the assigned priority level of the target object is not less than the assigned priority level of the corresponding sub-area.

24. The video processing apparatus of claim 13, wherein the type of object is persons.