Key Frame Extraction for Blackboard Occlusion in Online Education

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current online education video systems struggle to provide clear context and user-friendly interaction, as users face difficulties in viewing blackboard content due to occlusions and lack of preprocessing, leading to restricted viewing experiences and high recording costs.

Innovation Solution

A method and system that automatically identifies and extracts key frames from video streams, focusing on blackboard content, by detecting object movements, occlusions, and information changes, and serializing these frames with timestamps, allowing for improved user interaction and reduced recording costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If video recording of classroom is provided for online education, then accessibility is improved, but user experience is worsened due to restricted view of content context

Engineering Contradiction:
ImproveaccessibilityVSAvoiduser experience
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system segments the video content by identifying and extracting key frames that contain important blackboard information, separating essential content from redundant visual data. This allows users to access content more effectively without viewing the entire video stream.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system extracts key frames containing blackboard content from the video stream, isolating important information from the full video. This extraction process removes occlusions and focuses on essential educational content, improving user experience while maintaining accessibility.

Inventive Principle:
Principle #2Taking out (Extraction)

2Loss of information

If full video recording is provided, then complete content is available, but recording cost and complexity increase

Engineering Contradiction:
Improvecontent completenessVSAvoidrecording complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs preliminary processing by identifying and marking key frames during or after video capture. This preliminary action of selecting important frames reduces the overall data volume that needs to be stored and transmitted, simplifying the recording system while preserving essential content.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates simplified copies of the video content in the form of key frames that represent essential blackboard information. These key frame copies capture the essential educational content without requiring storage and transmission of the complete high-resolution video stream.

Inventive Principle:
Principle #26Copying

3Device complexity

If video playback is provided without preprocessing, then simplicity is maintained, but user comprehension is reduced due to occlusions and playback difficulties

Engineering Contradiction:
Improvesystem simplicityVSAvoidcontent comprehension
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The system performs preliminary processing by identifying and marking key frames during or after video capture. This preliminary action of selecting important frames reduces the overall data volume that needs to be stored and transmitted, simplifying the recording system while preserving essential content.

Inventive Principle:
Principle #10Preliminary action

4Ease of operation

If key frame extraction is implemented, then user experience is improved with clear blackboard focus, but processing complexity increases

Engineering Contradiction:
Improveuser experienceVSAvoidprocessing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system employs automated algorithms that self-service the key frame extraction process without requiring manual intervention. The system automatically identifies blackboard regions, detects occlusions, and selects key frames based on content importance, reducing the need for complex manual processing while improving user experience.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10720187B2Method and apparatus to extract key video frames from online education
Publication Date: 2020.07.21 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10720187B2 patent drawing
  • US10720187B2 patent drawing
  • US10720187B2 patent drawing

AI summary

A method stored in a computer readable medium, including identifying a predetermined object having viewable information from a plurality of frames, identifying a movement of the predetermined object from a video stream of the plurality of frames, identifying a current state of the predetermined object based on a movement of another object or region from the plurality of frames having an occlusion region of a current frame, determining an information change of the viewable information in the plurality of frames, marking a frame with maximum information of the viewable information in the predetermined object as a key frame; and serializing the key frame according to time stamps.