Deep information processing method and deep information processing system using the same

A depth information processing method, comprising:

• obtaining a first image and a second image of an original image group;
• performing a low-pass filtering process on the original image group to obtain a non-filtered first image and a filtered second image of a filtered image group, wherein the non-filtered first image is identical to the first image;
• combining the original image group and the filtered image group to obtain a combined image;
• performing a depth information processing on the combined image of the original image group by using a predetermined disparity search range, and performing the depth information processing on the combined image of the filtered image group of by using an expanded disparity search range to obtain an initial depth information, wherein the initial depth information has a basic depth information corresponding to the original image group and a compensated depth information corresponding to the filtered image group, the expanded disparity search range is N times the predetermined disparity search range, and N is a positive integer;
• dismantling the initial depth information to be the basic depth information and the compensated depth information;
• performing a numerical restoration process on the compensated depth information;
• and
• fusing the basic depth information and the compensated depth information to obtain a fused depth information.

A depth information processing system, comprising:

• a converting unit, used to perform a pixel shifting process on a first image and a second image of an original image group, to obtain a zero-shifted first image and a shifted second image of a shifted image group, wherein the zero-shifted first image is identical to the first image, the shifted second image is shifted by N pixels relative to the second image, and N is a positive integer;
• a combining unit, used to combine the original image group and the shifted image group, to obtain a combined image;
• a depth generating unit, used to perform a depth information processing on the combined image by using a predetermined disparity search range, to obtain an initial depth information, wherein the initial depth information has a basic depth information corresponding to the original image group and a compensated depth information corresponding to the shifted image group;
• a dismantling unit, used to dismantle the initial depth information to be the basic depth information and the compensated depth information;
• a restoring unit, used to perform a numerical restoration process on the compensated depth information, to obtain a restored depth information;
• and
• a fusing unit, used to fuse the basic depth information and the restored depth information, to obtain a fused depth information.