Generation of salient contours using live video

Patent metadata

Field	Value
Publication number	US-10325175-B2
Application number	US-201615242080-A
Country	US
Kind code	B2
Filing date	Aug 19, 2016
Priority date	Mar 12, 2015
Publication date	Jun 18, 2019
Grant date	Jun 18, 2019

Abstract

In various implementations, a computing device is configured to provide a live preview of salient contours generated on a live digital video feed. In particular, a designer can use a computing device with a camera, such as a smart phone, to view a real-time preview of salient contours generated from edges detected in frames of a live digital video feed prior to capture, thereby eliminating the unpredictability of salient contours generated from a previously captured image. In some implementations, the salient contours are overlaid on a greyscale conversion of the live digital video feed for improved processing and visual contrast. Other implementations modify aspects of edge-detecting or post-processing filters for improved performance on mobile computing devices.

First claim

What is claimed is:

1. A non-transitory computer storage medium storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations for capturing salient contours, the operations comprising:
detecting, in a frame of a live digital video, an edge and adjacent gradients;
providing for display, in real-time, the detected edge and corresponding adjacent gradients overlaid on the frame of the live digital video;
in response to a received user input, capturing the detected edge and the corresponding adjacent gradients; and
converting the captured detected edge and corresponding adjacent gradients into a smooth vector graphic.

2. The non-transitory computer storage medium of claim 1 , wherein the at least one detected edge is detected utilizing an edge-detecting filter.

3. The non-transitory computer storage medium of claim 2 , wherein the corresponding adjacent gradients is detected utilizing a plurality of filters configured to collectively preserve at least some gradient information corresponding to at least some pixels adjacent to the at least one detected edge to detect the corresponding adjacent gradients.

4. The non-transitory computer storage medium of claim 3 , wherein the plurality of filters include a first filter operable to generate at least some progressive gradients adjacent to the at least one detected edge.

5. The non-transitory computer storage medium of claim 4 , wherein the plurality of filters further include a second filter operable to intensify contrast in color values associated with the at least some progressive gradients generated by the first filter.

6. The non-transitory computer storage medium of claim 3 , the plurality of filters including a Gaussian blur filter and a modified threshold filter.

7. The non-transitory computer storage medium of claim 1 , the operations further comprising:
storing the at least one smooth vector graphic into a memory.

8. A computer-implemented method for capturing salient contours, comprising:
detecting, by a computing device, an edge and adjacent gradients from a frame of a live digital video;
providing for display, by the computing device, the detected edge and corresponding adjacent gradients overlaid on the frame of the live digital video;
in response to a received user input, capturing, by the computing device, the detected edge and the corresponding adjacent gradients; and
converting, by the computing device, the captured detected edge and corresponding adjacent gradients into at least one smooth vector graphic.

9. The computer-implemented method of claim 8 , wherein the detected edge is detected utilizing an edge-detecting filter.

10. The computer-implemented method of claim 9 , wherein the corresponding adjacent gradients is detected utilizing a plurality of filters configured to collectively preserve at least some gradient information corresponding to at least some pixels adjacent to the at least one detected edge to detect the corresponding adjacent gradients.

11. The computer-implemented method of claim 10 , wherein the plurality of filters include a first filter operable to generate at least some progressive gradients adjacent to the at least one detected edge.

12. The computer-implemented method of claim 11 , wherein the plurality of filters further include a second filter operable to intensify contrast in color values associated with the at least some progressive gradients generated by the first filter.

13. The computer-implemented method of claim 10 , the plurality of filters including a Gaussian blur filter and a modified threshold filter.

14. A computing device for capturing salient contours, comprising:
a vector graphic conversion component for:
receiving, a detected edge and corresponding adjacent gradients from a frame of a live digital video captured in response to a received user input with a display of the detected edge and corresponding adjacent gradients overlaid on the frame of the live digital video, and
converting the detected edge and corresponding adjacent gradients of the frame of the live digital video into at least one smooth vector graphic.

15. The computing device of claim 14 , further comprising:
an edge detecting filter component for detecting the edge and the corresponding adjacent gradients from the frame of the digital video based at least in part on an edge-detecting filter applied to the frame.

16. The computing device of claim 14 , further comprising:
a video feed overlay component for providing for display the corresponding frame of the live digital video having overlaid thereon the detected edge and corresponding adjacent gradients.

17. The computing device of claim 16 , wherein each of the overlaid detected edge and corresponding adjacent gradients are provided for display utilizing a bright, solid color to clearly contrast with the corresponding frame.

18. The computing device of claim 15 , wherein the corresponding adjacent gradients are detected based further in part on a plurality of filters configured to collectively preserve at least some color gradient information corresponding to at least some pixels adjacent to the at least one detected edge.

Assignees

• Adobe Inc

Inventors

• Jain Atishay
• Mehta Shamit Kumar
• Garg Stakshi Jindal
• Dowd Geoffrey Charles
• Behzadi Arian
• Andolina Joseph Michael
• Ericksen David

Classifications

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06T7/13 Primary

  Edge detection · CPC title

• H04N23/632

  for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters · CPC title

• H04N23/80

  Camera processing pipelines; Components thereof · CPC title

• H04N23/633

  for displaying additional information relating to control or operation of the camera · CPC title