Virtual fitting device and virtual fitting method thereof

1. A virtual fitting method, comprising:

acquiring a live video obtained by photographing a user;

acquiring a virtual video which includes an avatar corresponding to the user based on a body shape of the user and a movement of the user;

determining each composition area of the live video and the virtual video by analyzing the live video and the virtual video; and

composing the composition area of the live video and the composition area of the virtual video to generate a virtual fitting video; and

outputting the virtual fitting video,

wherein the determining comprises:

determining an area in which actual clothes worn by the user are located from the live video and an area in which virtual clothes worn by the avatar are located from the virtual video;

determining an area excluding the area in which the actual clothes are located and an area corresponding to the area in which the virtual clothes are located from the live video as the composition area of the live video; and

determining an area excluding an area corresponding to the composition area of the live video as the composition area of the virtual video.

2. The method as claimed in claim 1 , further comprising determining an area where the actual clothes are positioned to be part of the composition area of the virtual video, determining an area where the virtual clothes are positioned among areas where the actual clothes are not positioned to be part of the composition area of the virtual video, and determining an area where the actual clothes and the virtual clothes are not positioned to be the composition area of the live video.

3. The method as claimed in claim 1 , further comprising:

receiving input for selecting one of actual accessories or one of virtual accessories; and

in response to one of actual accessories being selected, determining a certain area which includes an area where the one of actual accessories is positioned as at least a part of the composition area of the live video and, in response to one of virtual accessories being selected, determining a certain area which includes an area where the one of virtual accessories is positioned as at least a part of the composition area of the virtual video.

4. The method as claimed in claim 1 , wherein acquiring the live video comprises acquiring the live video by photographing the user by using a video camera, and

wherein acquiring the virtual video comprises photographing the body shape and the movement of the user by using a depth camera or a video camera and generating an avatar based on the photographed body shape and the photographed movement of the user.

5. The method as claimed in claim 1 , wherein the virtual fitting video reflects characteristic information of virtual clothes.

6. The method as claimed in claim 5 , further comprising:

in response to a movement of the user, determining an extent of stretchiness of the virtual clothes with respect to the movement of the user based on the characteristic information of the virtual clothes; and

in response to the extent of stretchiness of the virtual clothes being equal to or greater than a threshold value, stopping a movement of a user image which is included in the virtual fitting video or controlling a speed of the movement of the user image.

7. The method as claimed in claim 5 , further comprising:

in response to a movement of the user, determining a body shape change of the user; and

generating the virtual fitting video based on the characteristic information of the virtual clothes and the body shape change of the user.

8. The method as claimed in claim 5 , further comprising:

receiving information regarding external force; and

generating the virtual fitting video based on the characteristic information of the virtual clothes and the information regarding external force.

9. The method as claimed in claim 5 , wherein the virtual fitting video displays a main point of the virtual clothes based on information regarding the main point of the virtual clothes.

10. A virtual fitting device, comprising a processor configured to:

acquire a live video of a user obtained by photographing the user;

acquire a virtual video including an avatar corresponding to the user based on a body shape of the user and a movement of the user;

determine each composition area of the live video and the virtual video by analyzing the live video and the virtual video;

compose the composition area of the live video and the composition area of the virtual video to generate a virtual fitting video; and

output the virtual fitting video,

wherein the determining of each composition area comprises:

determining an area in which actual clothes worn by the user are located from the live video and an area in which virtual clothes worn by the avatar are located from the virtual video;

determining an area excluding the area in which the actual clothes are located and an area corresponding to the area in which the virtual clothes are located from the live video as a composition area of the live video; and

determining an area excluding an area corresponding to the composition area of the live video as a composition area of the virtual video.

11. The device as claimed in claim 10 , wherein the processor is configured to determine an area where the actual clothes are positioned to be part of the composition area of the virtual video, determine an area where the virtual clothes are positioned among areas where the actual clothes are not positioned to be part of the composition area of the virtual video, and determine an area where the actual clothes and the virtual clothes are not positioned to be the composition area of the live video.

12. The device as claimed in claim 10 , further comprises:

a receiver configured to receive input for selecting one of actual accessories or one of virtual accessories,

wherein the processor is configured to, in response to one of actual accessories being selected, determine a certain area which includes an area where the one of actual accessories is positioned as at least a part of the composition area of the live video and, in response to one of virtual accessories being selected, determine a certain area which includes an area where the one of virtual accessories is positioned as at least a part of the composition area of the virtual video.

13. The device as claimed in claim 10 , wherein the live video is obtained by photographing the user by using a video camera, and

wherein acquiring the virtual video comprises photographing the body shape and the movement of the user by using a depth camera or a video camera and generating an avatar based on the photographed body shape and the photographed movement of the user.