Intelligent image surveillance system using network camera and method therefor

• US 9,143,759 B2
• Filed: 05/23/2012
• Issued: 09/22/2015
• Est. Priority Date: 05/26/2011
• Status: Active Grant

• Current Assignee: LG CNS Company Limited (LG Corporation)
• Original Assignee: LG CNS Company Limited (LG Corporation)
• Inventors: Choi, Sung Hoon, Lee, Sang Jean
• Primary Examiner(s): Perungavoor, Sath V
• Assistant Examiner(s): Duley, Janese
• Application Number:
  US13/478,793
• Publication Number:
  US 20130141543A1
• Time in Patent Office: 1,217 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 15/00 3D [Three Dimensional] image rendering
• CPC Class Codes: G08B 13/19641 Multiple cameras having overlapping views on a single scene
• 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 13/19671 Addition of non-video data, i.e. metadata, to video stream
• CPC Class Codes: G08B 13/19691 Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound
• CPC Class Codes: H04N 13/204 using stereoscopic image cameras stereoscopic photography G03B35/00
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

An intelligent control system according to an exemplary embodiment of the present disclosure includes a plurality of network cameras to photograph a surveillance area; an image gate unit to perform image processing of image data, which is input from the plurality of network cameras, according to a specification that is requested by a user; a smart image providing unit to convert a plurality of image streams, which are image processed by the image gate unit, to a single image stream; and an image display unit to generate a three-dimensional (3D) image by segmenting, into a plurality of images, the single image stream that is input from the smart image providing unit and by disposing the segmented images on corresponding positions on a 3D modeling.

Claims

1. An intelligent control system, comprising:

a plurality of network cameras to monitor a surveillance area;

at least one memory; and

program instructions stored in the memory that cause the system to;

perform, by a plurality of image gates, image processing of image data, which is input from the plurality of network cameras, according to a specification that is requested by a user, where in the specification comprises a viewpoint of the user;

adjust a resolution of the image data based on the viewpoint of the user;

convert a plurality of image streams associated with the requesting user to a single image stream via image processing; and

generate a three-dimensional (3D) image by segmenting the single image stream into a plurality of images based on an image resolution and a frame size, and by disposing the segmented images on corresponding positions on a 3D modeling;

wherein each of the plurality of image gates includes a plurality of image processors, each of the image processors comprising;

a decoder configured to decode image data that is input in real time from the plurality of network cameras;

a plurality of processors configured to perform image processing of the image data, which is decoded by the decoder, according to the specification that is requested by the user;

a plurality of encoders configured to encode data that is image processed by the plurality of processors; and

a plurality of streamers configured to perform image streaming of the data that is encoded by the plurality of encoders.

2. The system of claim 1, the program instructions further causing the system to:

provide a plurality of users, present in a network, with the plurality of image streams.

3. The system of claim 1, the program instructions further causing the system to:

provide a senior supervisor, present in the network, with a final screen.

4. The system of claim 1, the plurality of image gates configured to process image data that is input from a predetermined network camera group among the plurality of network cameras.

5. The system of claim 4, wherein the plurality of image processors are connected one-to-one with cameras belonging to the network camera group, respectively.

6. The system of claim 1, the program instructions further causing the system to:

generate image segmentation information for disposing image data as different sizes of images on a single screen.

7. The system of claim 6, the program instructions further causing the system to dispose the image data as the different sizes of images according to resolutions of the image data.

8. The system of claim 1, further comprising:

a plurality of decoders configured to decode image data that is input from the image gate; and

a plurality of encoders configured to provide a multi-streaming service by encoding and streaming a plurality of images that are decoded by the plurality of decoders.

9. The system of claim 1, further comprising:

a plurality of image displays configured to display the plurality of images on different screens in response to a request of the user.

10. The system of claim 9, wherein each of the plurality of image displays comprises:

program instructions causing the display to segment a single image stream into a plurality of images for configuring a single screen;

a 3D model generator configured to model the surveillance area to a 3D image; and

a rendering processor configured to generate a 3D image by disposing the images on corresponding positions of the 3D modeling.

11. The system of claim 10, wherein each of the image displays further comprises:

a decoder configured to decode the single image stream and to provide the decoded image stream for image segmentation; and

a display configured to display the 3D image that is generated by the rendering processor.

12. The system of claim 1, the program instructions further causing the system to:

calculate resolutions of a plurality of images to be included in a corresponding screen by analyzing the screen; and

provide the calculated resolutions to an image gate.

13. The system of claim 9, further comprising:

a plurality of encoders configured to encode a screen, output in real time, configured to provide the senior supervisor with a finally output screen, and to perform multi-streaming of the encoded screen.

14. The system of claim 1, wherein the image data is encoded and decoded using H.264 or MPEG 4.

15. An intelligent control method, comprising the computer implemented steps of:

receiving, from a plurality of network cameras, image data in which a surveillance area is monitored;

performing image processing with a plurality of image gates, wherein each of the plurality of image gates includes a plurality of image processors, of the received image data according to a specification that is requested by a user, where in the specification comprises a viewpoint of the user;

adjusting a resolution of the image data based on the viewpoint of the user;

converting the plurality of image processed image data to a single image stream to be displayed on a single screen wherein the plurality of image processed image data is associated with the requesting user; and

generating a 3D image by segmenting the converted single image stream into a plurality of images based on an image resolution and a frame size, and by disposing the segmented images on corresponding positions of a 3D modeling,

wherein each of the image processors comprises;

a decoder configured to decode image data that is input in real time from the plurality of network cameras;

a plurality of processors configured to perform image processing of the image data, which is decoded by a decoder, according to the specification that is requested by the user;

a plurality of encoders configured to encode data that is image processed by the plurality of processors; and

a plurality of streamers configured to perform image streaming of the data that is encoded by the plurality of encoders.

16. The method of claim 15, further comprising the computer implemented steps of:

providing a plurality of users, present in a network, with the plurality of image processed image streams; and

providing a senior supervisor, present in the network, with the generated 3D image.

17. The method of claim 15, wherein the performing of the image processing comprises the computer implemented steps of:

decoding the received image data;

performing image processing of the decoded image data according to the specification that is requested by the user; and

encoding the image processed data and performing image streaming of the encoded data.

18. The method of claim 15, wherein the converting comprises the computer implemented steps of:

decoding the plurality of image processed image data;

generating image segmentation information for disposing the plurality of decoded images as different sizes of images on a single screen; and

encoding the plurality of decoded images to convert the plurality of encoded images to a single image stream.

19. The method of claim 15, wherein the generating comprises the computer implemented steps of:

segmenting the converted single image stream into a plurality of images for configuring a single screen;

modeling the surveillance area to a 3D image; and

generating the 3D image by disposing the plurality of segmented images on corresponding positions of the 3D modeling.