Method of estimating depths from a single image displayed on display
AssigneeArcSoft Hangzhou Co., Ltd.
InventorsMiao Hu, Jian-Hua Lin, Jin Wang
Life of this patent
Estimating the term…
Abstract
A method of estimating depths on a monocular image displayed on a display is utilized for improving correctness of depths shown on the display. Feature vectors are calculated for each patch on the monocular image for determining an intermediate depth map of the monocular image in advance. For improving the correctness of the intermediate depth map, an energy function in forms of vectors is minimized for calculating a best solution of the depth map of the monocular image. Therefore, the display may display the monocular image according to a calculated output depth map for having an observer of the display to correctly perceive depths on the monocular image.
Claims4
A method of estimating depths on a monocular image displayed on a display, comprising:
- transforming grey levels of a monocular image from a first color field to a second color field, which is indicated by an intensity channel and two color channels;
- segmenting the monocular image into a plurality of patches;
- calculating a feature vector for each of the plurality of patches according to a serial of filters whose output combined with their square energies form the feature vector;
- determining an intermediate depth map of the monocular image according to the calculated feature vector of each of the plurality of patches;
- and
- determining an output depth map according to an equation
- (L+λU)d=λdp;
- wherein λ is a normalized parameter, U indicates an identity matrix, dp indicates the intermediate depth map, d indicates the output depth map, and L is a matting Laplacian matrix.
Dependencies are inferred from the claim text.