Video Mask Frame Generation for Bullet Screen Layout

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Excessive bullet screens during video broadcasts can heavily block video content, negatively impacting the viewing experience, leading users to shield all bullet screens, which reduces interaction in live broadcast rooms.

Innovation Solution

A method of obtaining mask frame data using image segmentation algorithms, such as semantic and instance segmentation models, to identify the main area of a video frame and generate mask frame data, allowing bullet screen information to be displayed outside this area, thereby improving the user's viewing experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If bullet screens are displayed during video broadcasts, then user interaction is enhanced, but the main video area becomes blocked

Engineering Contradiction:
Improveuser interactionVSAvoidvisible video area
Core Design Contradiction:
Adaptability or versatilityVSArea of stationary object

Solution Approach 1:

The display area is segmented into multiple regions: the main video area and alternative display areas for bullet screens. By dividing the screen space and assigning different functions to different segments, the system maintains both video visibility and interaction capabilities simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Bullet screens are relocated from the traditional full-screen overlay approach to alternative areas such as corners or edges of the display. This spatial repositioning in different dimensional zones allows interaction elements to coexist with video content without blocking the main viewing area.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If bullet screens are displayed in the main area, then interaction is maintained, but viewing experience deteriorates

Engineering Contradiction:
ImproveinteractionVSAvoidviewing experience
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

Different regions of the display are assigned different qualities and functions: the main video area prioritizes visual quality and clarity, while alternative areas accommodate interaction elements. This local differentiation ensures that each zone optimizes its primary function without compromising the other.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The potential harm of bullet screens blocking video content is converted into a benefit by strategically positioning them in alternative areas. What could have been a harmful obstruction becomes a useful interaction space that enhances user engagement without degrading video quality.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

3Object-affected harmful factors

If all bullet screens are shielded to improve viewing experience, then visual quality improves, but user interaction is reduced

Engineering Contradiction:
Improveviewing experienceVSAvoidinteraction
Core Design Contradiction:
Object-affected harmful factorsVSAdaptability or versatility

Solution Approach 1:

The display is segmented into protected main video areas and dedicated interaction zones. This segmentation allows the system to shield only the necessary portions from interaction elements while preserving video quality, rather than shielding all bullet screens completely.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Interaction elements are moved to alternative dimensional spaces such as corner regions or edge zones rather than being overlaid on the main video area. This spatial relocation preserves viewing experience while maintaining interaction capabilities in separate display dimensions.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS11475666B2Method of obtaining mask frame data, computing device, and readable storage medium
Publication Date: 2022.10.18 SHANGHAI BILIBILI TECH CO LTD
  • US11475666B2 patent drawing
  • US11475666B2 patent drawing
  • US11475666B2 patent drawing

AI summary

The present disclosure describes techniques for generating a mask frame data segment corresponding to a video frame. The disclosed techniques include obtaining a frame of a video; identifying a main area of the frame using an image segmentation algorithm; and generating a mask frame data segment corresponding to the frame based on the main area of the frame, wherein the generating a mask frame data segment corresponding to the frame based on the main area of the frame further comprises generating the mask frame data segment based on a timestamp of the frame in the video, a width and a height of the main area of the frame.