Video Reception Device Region Segmentation for Content Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing video reception systems face challenges in accurately recognizing and superimposing additional information, such as advertisements, onto video signals due to the presence of superimposed content like captions or OSDs, which can lead to failed content recognition and reduced precision in video analysis.

Innovation Solution

The system employs a video reception device that detects superimposed information and sets video recognition regions or candidate regions to exclude such information, generating fingerprints for precise content recognition and superimposing additional data correctly on the video signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If video recognition is performed on the entire video signal including superimposed content, then the recognition process covers all areas, but the recognition precision decreases due to interference from captions and OSDs

Engineering Contradiction:
Improvevideo recognition areaVSAvoidcontent recognition precision
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The video signal is divided into multiple regions: a video recognition region excluding superimposed content areas, and a superimposition region for displaying additional information. This segmentation allows fingerprint extraction only from relevant areas, improving recognition precision while maintaining adequate coverage.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts and excludes superimposed content (captions, OSDs) from the video recognition region. By removing these interfering elements from the analysis area, the system achieves more accurate content recognition without being misled by overlaid information.

Inventive Principle:
Principle #2Taking out (Extraction)

2Ease of operation

If additional information is superimposed on video signals without considering existing superimposed content, then the additional information can be displayed, but it may overlap with captions or OSDs reducing display quality

Engineering Contradiction:
Improveadditional information displayVSAvoidsuperimposition positioning precision
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The system performs preliminary detection of superimposed content (captions, OSDs) in the video signal before determining the superimposition region for additional information. This advance knowledge allows the system to position additional information in areas free from existing overlays, ensuring high display quality.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies different processing to different regions of the video signal. The video recognition region excludes superimposed content areas for accurate fingerprint extraction, while the superimposition region is specifically selected to avoid overlapping with existing overlays, ensuring optimal display quality for additional information.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3043570B1Video reception device, video recognition method, and additional information display system
Publication Date: 2018.10.24 PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
  • EP3043570B1 patent drawingFigure 1
  • EP3043570B1 patent drawingFigure 2
  • EP3043570B1 patent drawingFigure 3A~3B

AI summary

Video recognition processing on video signals input from an outside is performed. Hence, video reception device (40) which is configured to transmit and receive data through communication network (16) includes input unit (65), video extraction unit (45), video recognition region setting unit (66), control unit (41) and additional information display control unit (46). The video recognition region setting unit detects superimposing information superimposed on a partial video, and sets a video recognition region or video recognition candidate regions to the partial video based on a detection result. The additional information display control unit generates content recognition information in the video recognition region or in the video recognition candidate regions of the partial video. The control unit performs control of requesting video recognition device (20) to perform video recognition processing on this content recognition information.