Method and apparatus for converting 2D video image into 3D video image
A method of converting a two-dimensional video to a three-dimensional video, the method comprising: comparing an image of an n th frame with an accumulated image until an n−1 th frame in the two-dimensional video to calculate a difference in a color value for each pixel; generating a difference image including information on a change in a color value for each pixel of the n th frame; storing an accumulated image until the n th frame by accumulating the information on the change in the color value for each pixel until the n th frame; performing an operation for a pixel in which a change in a color value is equal to or larger than a predetermined level by using the difference image to generate a division image and a depth map image; and converting the image of the n th frame to a three-dimensional image by using the depth map image.
1. A method of converting a two-dimensional video to a three-dimensional video, the method comprising:
comparing an image of an n th frame with an accumulated image until an n−1 th frame in the two-dimensional video to calculate a difference in a color value for each pixel;
generating a difference image including information on a change in a color value for each pixel of the n th frame by using the difference in the color value;
storing an accumulated image until the n th frame by accumulating the information on the change in the color value for each pixel until the n th frame;
performing an operation only for a pixel in which a change in a color value is equal to or larger than a predetermined level in the n th frame by using the difference image to generate a division image and a depth map image of the n th frame; and
converting the image of the n th frame to a three-dimensional image by using the depth map image.
2. The method of claim 1 , wherein the generating of the difference image comprises generating an image by classifying a pixel in which the difference in the color value between the image of the n th frame and the accumulated image until the n−1 th frame is equal to or larger than a predetermined value into a first area and a pixel in which the difference in the color value is smaller than the predetermined value into a second area, respectively.
3. The method of claim 2 , wherein the storing of the accumulated image comprises allocating a color value of the image of the n th frame to a pixel included in the first area of the difference image in the n th frame and allocating a color value of the accumulated image until the n−1 th frame to a pixel included in the second area.
4. The method of claim 2 , wherein the generating of the division image comprises dividing the image of the n th frame into two or more division areas according to a color value for each pixel, wherein a division area is newly determined only for a pixel included in the first area of the difference image and a division area of the n−1 th frame is equally applied to a pixel included in the second area.
5. The method of claim 4 , wherein the generating of the depth map image comprises backwardly allocating a depth value in a unit of division areas from a bottom side to a top side of the division image of the n th frame according to a predetermined depth value assignment rule.
6. The method of claim 5 , wherein the converting to the three-dimensional image comprises shifting the image of the n th frame according to the depth value of the depth map image to horizontally generate left and right parallax.