Method for enhancing object contour of image in real-time video
US12131445B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 29, 2020 |
| Grant date | Oct 29, 2024 |
| Priority date | — |
| Expiry date | Sep 27, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20192
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for enhancing the contour of an object in a real-time video image includes: acquiring a captured video, and dividing a next frame of image in the video into a plurality of image blocks; subjecting each pixel in each of the image blocks to contour enhancement based on a gradient algorithm; subjecting the plurality of contour-enhanced image blocks as a whole to noise filtering by using a Gaussian filtering method to obtain a noise-filtered image; and subjecting the entire noise-filtered image to contrast processing based on gamma transformation to obtain a final enhanced image. The method is used for image contour enhancement, and solves the problem that it is hard to recognize an object with low recognizability in an image (i.e., original image) output by a device in the prior art.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.