System and method for converting two dimensional to three dimensional video

Abstract

A system and method for converting two dimensional video to three dimensional video includes a processor having an input for receiving a two dimensional image data and an output for outputting three dimensional image data to a display. The processor is configured to receive two dimensional image data, segment a specific object in the two dimensional image data based on variations in brightness and sharpness in the two dimensional image data to identify and locate the specific object in the two dimensional image data. The processor is also configured to adjust the depth value of the specific object over the period of time as the size of the specific object changes in each of the two dimensional images or adjust the depth value of the specific object over the period of time as the size of the specific object changes in each of the two dimensional images.

What is claimed is: 
     
         1 . A method for converting two dimensional video to three dimensional video, the method comprising:
 receiving a two dimensional image;   segmenting a specific object in the two dimensional image based on variations in brightness in the two dimensional image to identify and locate the specific object in the two dimensional image;   generating a depth map comprising depth values indicating object depth of the specific object in the two dimensional image;   determining a depth value in the depth map for the specific object based on the sharpness of the object; and   generating a three dimensional image comprising the specific object located according to the depth map.   
     
     
         2 . The method of  claim 1 , further comprising generating a right view output picture and a left view output picture based on the three dimensional image. 
     
     
         3 . The method of  claim 1 , wherein generating the depth map further comprises generating a row accumulated depth map having depth values. 
     
     
         4 . The method of  claim 3 , wherein the depth values of the row accumulated depth map are arranged to place the smallest values in middle rows of the depth map. 
     
     
         5 . The method of  claim 3 , wherein the depth values of the row accumulated depth map are arranged to place the smallest values in top or bottom or both top and bottom rows of the depth map. 
     
     
         6 . The method of  claim 3 , wherein generating the depth map further comprises:
 generating a column accumulated depth map comprising depth values;   combining the depth values in the row calculated depth map and the column accumulated depth map to generate the depth map; and   wherein smallest values of the depth map are located in the middle rows and middle columns of the depth map.   
     
     
         7 . The method of  claim 1 , further comprising:
 segmenting a plurality of objects in the two dimensional image based on variations in brightness in the two dimensional image   determining a depth value in the depth map of each of the plurality of objects based on the sharpness of each of the plurality of objects; and   generating a three dimensional image based on the depth map and the plurality of objects, wherein objects that have substantially similar brightness and sharpness and have a substantially similar depth value.   
     
     
         8 . The method of  claim 1 , further comprising the steps of:
 generating the depth map by utilizing two generated baseline depth surfaces that are row-accumulated and column-accumulated, wherein each baseline depth surface being generated using the difference of the largest edge values across two rows;   inverting the sign of accumulation of the difference of largest edge values across two rows; and   combining the two baseline depth surfaces by taking minimum, maximum, or average of the two surfaces at each depth pixel location.   
     
     
         9 . The method of  claim 8 , further comprising the steps of:
 setting the edge values to between a preset lower and upper bound; and   blending the edge values to the global depth surfaces with a preset blending factor.   
     
     
         10 . The method of  claim 1 , further comprising the step replacing a current depth value of a pixel of the three dimensional image with a new depth value based on a neighboring pixels characteristics. 
     
     
         11 . A system for converting two dimensional video to three dimensional video, the system comprising:
 a processor having an input for receiving a two dimensional image data and an output for outputting three dimensional image data to a display;   the processor being configured to receive two dimensional image data, segment a specific object in the two dimensional image data based on variations in brightness in the two dimensional image data to identify and locate the specific object in the two dimensional image data, generate a depth map comprising depth values indicating object depth of the specific object in the two dimensional image data, determine a depth value in the depth map for the specific object based on the sharpness of the object, and generate three dimensional image data comprising the specific object located according to the depth map.   
     
     
         12 . The system of  claim 11 , wherein the processor is further configured to generate a right view output picture and a left view output picture based on the three dimension image data. 
     
     
         13 . The system of  claim 11 , wherein the depth map is a row accumulated depth map having depth values. 
     
     
         14 . The system of  claim 13 , wherein the depth values of the row accumulated depth map are arranged to place the smallest values in middle rows of the depth map. 
     
     
         15 . The system of  claim 13 , wherein the depth values of the row accumulated depth map are arranged to place the smallest values in top or bottom or both top and bottom rows of the depth map. 
     
     
         16 . The system of  claim 13 , wherein the depth map further comprises a column accumulated depth map comprising depth values, wherein smallest values of the depth map are located in the middle rows and middle columns of the depth map. 
     
     
         17 . The system of  claim 11 , wherein the processor is further configured to segment a plurality of objects in the two dimensional image data based on variations in brightness in the two dimensional image data, determine a depth value in the depth map of each of the plurality of objects based on the sharpness of each of the plurality of objects, and generate a three dimensional image data based on the depth map and the plurality of objects, wherein objects that have substantially similar brightness and sharpness and have a substantially similar depth value. 
     
     
         18 . The system of  claim 11 , wherein the processor is further configured to:
 generate the depth map by utilizing two generated baseline depth surfaces that are row-accumulated and column-accumulated, wherein each baseline depth surface being generated using the difference of the largest edge values across two rows;   invert the sign of accumulation of the difference of largest edge values across two rows; and   combine the two baseline depth surfaces by taking minimum, maximum, or average of the two surfaces at each depth pixel location.   
     
     
         19 . The system of  claim 18 , wherein the processor is further configured to:
 set the edge values to between a preset lower and upper bound; and   blend the edge values to the global depth surfaces with a preset blending factor.   
     
     
         20 . The system of  claim 11 , wherein the processor is further configured to replace a current depth value of a pixel of the three dimensional image with a new depth value based on a neighboring pixels characteristics.