Method and system for analyzing multi-channel images

1. A method of analyzing multi-channel images, the method comprising:

receiving a plurality of images through a plurality of channels, respectively;

combining selected images among the plurality of images into a single image, wherein at least one selected image having a first size is resized to a second size in the combined image;

obtaining information regarding each of the selected images in the combined image;

determining, based on the obtained information, an image analysis with respect to:

entirety of the combined image by treating the selected images as a single image; or

each of the selected images by separating the combined image into the selected images, the separated selected images comprising the at least one selected image having the first size; and

performing an image analysis according to a result of the determination.

2. The method of claim 1 , wherein, in case of performing the image analysis with respect to each of the separated selected images, different image analyzing methods are applied to at least two of the separated selected images, respectively.

3. The method of claim 1 , wherein, if all of the selected images in the combined image are larger than a reference size, the image analysis is performed with respect to entirety of the combined image by treating the selected images as a single image, and

wherein, if at least one of the selected images in the combined image is not larger than the reference size, the image analysis is performed with respect to each of the separated selected images.

4. The method of claim 1 , wherein the information regarding each of the selected images comprises a number of pixels constituting each of the selected images.

5. The method of claim 1 , wherein, if all of the selected images in the combined image are constituted by pixels larger than a reference number of pixels, the image analysis is performed with respect to entirety of the combined image by treating the selected images as a single image, and

wherein, if at least one of the selected images in the combined image is constituted by pixels not larger than the reference number of pixels, the image analysis is performed with respect to each of the separated selected images.

6. The method of claim 1 , further comprising pre-processing the combined image before the performing the image analysis,

wherein the pre-processing comprises at least one of image size conversion, color space conversion and color dimension conversion.

7. The method of claim 1 , further comprising detecting a foreground region in the combined image by processing the entirety of the combined image by treating the selected images as a single image,

wherein the performing the image analysis comprises detecting occurrence of camera tempering to at least one of a plurality of cameras, from which the plurality of images are obtained, with respect to each of the plurality of channels.

8. The method of claim 1 , further comprising:

detecting a motion region in the combined image by processing the entirety of the combined image with treating the selected images as a single image;

obtaining location information about the motion region; and

determining a channel, among selected channels among the plurality of channels, corresponding to the motion region.

9. The method of claim 1 , further comprising:

combining the separated selected images used for the image analysis into another single image, after performing the image analysis with respect to each of the separated selected images; and

outputting the other single image with a result of the image analysis.

10. A multi-channel image analyzing system comprising at least one processor, the multi-channel image analyzing system further comprising:

an image receiving unit, controlled by the at least one processor, and configured to receive a plurality of images through a plurality of channels, respectively;

an image combining unit, controlled by the at least one processor, and configured to combine selected images among the plurality of images into a single image, wherein at least one selected image having a first size is resized to a second size in the combined image;

an image analyzing method selecting unit, controlled by the at least one processor, and configured to obtain information regarding each of the selected images in the combined image and determine, based on the obtained information, whether to perform an image analysis with respect to:

entirety of the combined image by treating the selected images as a single image; or

each of the selected images by separating the combined image into the selected images, the separated selected images comprising the at least one selected image having the first size; and

an image analyzing unit, controlled by the at least one processor, and configured to perform an image analysis according to a result of the determination.

11. The multi-channel image analyzing system of claim 10 , wherein the image analyzing unit performs the image analysis with respect to each of the separated selected images by applying different image analyzing methods to at least two of the separated selected images, respectively.

12. The multi-channel image analyzing system of claim 10 , wherein, if the image analyzing method selecting unit determines that all of the selected images in the combined image are larger than a reference size, the image analyzing unit performs the image analysis with respect to entirety of the combined image by treating the selected images as a single image, and

wherein, if the image analyzing method selecting unit determines that at least one of the selected images in the combined image is not larger than the reference size, the image analyzing unit performs the image analysis with respect to each of the separated selected images.

13. The multi-channel image analyzing system of claim 10 , wherein the information regarding each of the selected images comprises a number of pixels constituting each of the selected images.

14. The multi-channel image analyzing system of claim 10 , wherein, if the image analyzing method selecting unit determines that all of the selected images in the combined image are constituted by pixels larger than a reference number of pixels, the image analyzing unit performs the image analysis with respect to entirety of the combined image by treating the selected images as a single image, and

wherein, if the image analyzing method selecting unit determines that at least one of the selected images in the combined image is constituted by pixels not larger than the reference number of pixels, the image analyzing unit performs the image analysis with respect to each of the separated selected images.

15. The multi-channel image analyzing system of claim 10 , further comprising an image pre-processing unit, controlled by the at least one processor, and configured to perform pre-processing the combined image before the image analyzing unit performs the image analysis,

wherein the pre-processing comprises at least one of image size conversion, color space conversion and color dimension conversion.

16. The multi-channel image analyzing system of claim 10 , wherein the image analyzing unit comprises:

a foreground detection unit, controlled by the at least one processor, and configured to detect a foreground region in the combined image by processing the entirety of the combined image by treating the selected images as a single image; and

an event detecting unit, controlled by the at least one processor, and configured to detect occurrence of camera tempering to at least one of a plurality of cameras, from which the plurality of images are obtained, with respect to each of the plurality of channels.

17. The multi-channel image analyzing system of claim 10 , wherein the image analyzing unit comprises:

a foreground detection unit, controlled by the at least one processor, and configured to detect a motion region in the combined image by processing the entirety of the combined image with treating the selected images as a single image; and

an event detecting unit, controlled by the at least one processor, and configured to obtain location information about the motion region, and determine a channel, among selected channels in the plurality of channels, corresponding to the motion region.

18. The multi-channel image analyzing system of claim 10 , further comprising an image output unit, controlled by the at least one processor, and configured to:

combine the selected images used for the image analysis into another single image, after the image analyzing unit performs the image analysis with respect to each of the separated selected images; and

output the other single image with a result of the image analysis.