Method and graphical user interface for modifying depth maps
AssigneeHer Majesty the Queen in right of Canada, as represented by the Minister of Industry, through the Communications Research Centre Canada
InventorsWa James Tam, Carlos Vázquez
Life of this patent
Estimating the term…
Abstract
The invention relates to a method and a graphical user interface for modifying a depth map for a digital monoscopic color image. The method includes interactively selecting a region of the depth map based on color of a target region in the color image, and modifying depth values in the thereby selected region of the depth map using a depth modification rule. The color-based pixel selection rules for the depth map and the depth modification rule selected based on one color image from a video sequence may be saved and applied to automatically modify depths maps of other color images from the same sequence.
Claims19
A computer-implemented method for modifying a depth map of a two-dimensional color image for enhancing a 3D image rendered therefrom, comprising:
- A) obtaining a first color image and a depth map associated therewith containing depth values for pixels of the first color image;
- B) displaying at least one of the first color image and the depth map on a computer display;
- C) selecting a depth adjustment region (DAR) in the depth map for modifying depth values therein by performing the steps of:
- a) receiving a first user input identifying a first pixel color within a range of colors of a target region in the first color image;
- b) upon receiving a second user input defining a pixel selection rule for selecting like-coloured pixels based on the first pixel color, using said pixel selection rule for identifying a plurality of the like-coloured pixels in the first color image;
- c) displaying a region visualization image (RVI) representing pixel locations of the plurality of like-coloured pixels;
- d) repeating steps (b) and (c) to display a plurality of different region visualization images corresponding to a plurality of different pixel selection rules for selection by a user;
- and
- e) identifying a region in the depth map corresponding to a user selected region visualization image from the plurality of different region visualization images, and adopting said region in the depth map as the DAR;
- D) generating a modified depth map by modifying the depth values in the DAR using a selected depth modification rule.
A method for modifying depth maps for 2D color images for enhancing 3D images rendered therewith, comprising:
- a) selecting a first color image from a video sequence of color images and obtaining a depth map associated therewith, wherein said video sequence includes at least a second color image corresponding to a different frame from a same scene and having a different depth map associated therewith;
- b) selecting a first pixel color in the first color image within a target region;
- c) determining pixel locations of like-coloured pixels of the first color image using one or more color selection rules, the like-coloured pixels having a pixel color the same as the first pixel color or in a specified color tolerance range thereabout;
- and,
- d) applying a selected depth modification rule to modify the depth map of the first color image at depth map locations corresponding to the pixel locations of the like-coloured pixels to obtain a modified depth map of the first color image;
- e) applying the one or more color selection rules and the selected depth modification rule to identify like-coloured pixels in the second color image of the video sequence and to modify the depth map of the second color image at depth map locations corresponding to the pixel locations of the like-coloured pixels in the second color image to obtain a modified depth map of the second color image;
- and,
- f) outputting the first and second color images and the modified depth maps associated therewith for rendering an enhanced video sequence of 3D images;
- and,
- wherein the one or more color selection rules and the selected depth modification rule are obtained based on the first color image.
Dependencies are inferred from the claim text.