Black edge detection method and device

By determining the predicted top and bottom black edge areas in the image frame and using image similarity conditions and fixed identifiers to adjust the quantity threshold, the problem that motion estimation cannot accurately distinguish between video content and black edges is solved, thereby improving the accuracy of black edge detection and the image quality after motion compensation.

CN116012749BActive Publication Date: 2025-09-23SHANGHAI SJ ELECTRONIC TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211561578.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-07
Publication Date
2025-09-23
Estimated Expiration
2042-12-07

AI Technical Summary

Technical Problem

In the prior art, motion estimation cannot accurately distinguish between video content and black-border content, resulting in fragmentation or unclear image boundaries after motion compensation interpolation.

Method used

By determining the predicted top and bottom black edge areas of the image frame and adjusting the quantity threshold using image similarity conditions and fixed identifiers, the accuracy of black edge detection is improved, ensuring accurate marking and protection of black edges during motion estimation.

Benefits of technology

The accuracy of black edge detection is improved, and the image quality after motion estimation compensation is improved to ensure the clarity of image boundaries.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116012749B_ABST
    Figure CN116012749B_ABST
Patent Text Reader

Abstract

The embodiments of the present application provide a black edge detection method and device to solve the problem of inaccurate black edge detection in the prior art. The method provided by the present application includes: determining a predicted top black edge region and a first predicted bottom black edge region of an image frame to be processed, and determining a second predicted bottom black edge region based on the predicted top black edge region and the first predicted bottom black edge region; when the image frame to be processed meets a set condition, determining the top black edge region included in the image frame to be processed as the predicted top black edge region, and the bottom black edge region included in the image frame to be processed as the second predicted bottom black edge region; wherein the set condition is that the images of the second predicted bottom black edge regions respectively determined for any two adjacent image frames in N consecutive image frames are similar; the N consecutive image frames include the image frame to be processed and the N‑1 image frames before the image frame to be processed.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method and device for detecting OSD image in video image and terminal equipment

    CN111652237A

  • Subtitle cut video identification method and device, electronic equipment and storage medium

    CN114666649A