Image processing device, method and program
AssigneeNippon Telegraph and Telephone Corporation
InventorsTakashi SANO, Masato ONO, Yumi KIKUCHI, Shinji FUKATSU
Life of this patent
Estimating the term…
Abstract
According to an aspect of the present invention, when a depth map of a moving image is generated from the moving image, first filtering of performing edge-preserving smoothing on first depth map information generated for each of a plurality of frames constituting the moving image by using segmentation information generated separately and second filtering of smoothing, in a time direction, a pixel value of a pixel corresponding to a position coordinate in a frame of the first depth map information in the plurality of frames are performed to generate corrected second depth map information.
Claims7
A video information processing apparatus that generates a depth map of a moving image from the moving image, the video information processing apparatus comprising:
- depth map information acquisition processing circuitry configured to acquire first depth map information generated for each of a plurality of frames constituting the moving image;
- segmentation information acquisition processing circuitry configured to acquire segmentation information generated by dividing an image area including an object into a plurality of pixel blocks for each of the plurality of frames;
- and
- smoothing processing circuitry configured to perform first filtering of performing edge-preserving smoothing on the first depth map information by using the segmentation information as a guide image for each of the plurality of frames and second filtering of smoothing, in a time direction, a pixel value of a pixel corresponding to a position in the first depth map information in the plurality of frames to generate corrected second depth map information.
A video information processing method, comprising:
- acquiring first depth map information generated for each of a plurality of frames constituting the moving image;
- acquiring, for each of the plurality of frames, segmentation information generated by dividing an image area including an object into a plurality of pixel blocks;
- and
- performing first filtering of performing edge-preserving smoothing on the first depth map information by using the segmentation information as a guide image for each of the plurality of frames and second filtering of smoothing, in a time direction, a pixel value of a pixel corresponding to a position in the first depth map information in the plurality of frames, to generate corrected second depth map information.
Dependencies are inferred from the claim text.