Audio Video Fingerprinting for Repeating Content Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for identifying commercials in video data streams are ineffective, and there is a need for new approaches to accurately detect commercials and repeating content.

Innovation Solution

The method involves receiving and parsing video data streams into segments, creating audio fingerprints, storing them in a database, and identifying matching fingerprints to determine potential repeating content, with subsequent actions taken by a content processing platform for recognition processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional feature-based detection methods are used to identify commercials, then the detection process can be performed, but the accuracy and reliability of commercial identification is insufficient

Engineering Contradiction:
Improvecommercial identification accuracyVSAvoiddetection effectiveness
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The video data stream is divided into multiple segments, with each segment being independently fingerprinted and analyzed. This segmentation allows for more precise localization of commercials within the video stream, improving both identification accuracy and reliability by examining specific portions rather than treating the entire stream as a single unit.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Audio fingerprints are introduced as an intermediary mechanism to bridge the gap between raw video data and commercial identification. The audio fingerprinting system serves as a mediator that transforms complex audio-visual content into comparable signature patterns, enabling more accurate and reliable detection of commercial content.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If audio fingerprints are created for all video segments, then repeating content can be identified, but storage requirements and processing overhead increase

Engineering Contradiction:
Improverepeating content detection accuracyVSAvoidstorage overhead
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

Only audio fingerprints are extracted and stored, omitting the need to store complete video segments or comprehensive metadata. This extraction approach retains the essential identifying features for detecting repeating content while significantly reducing storage requirements compared to storing full segment data.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of storing actual video segments, the system creates compact audio fingerprint copies that represent the essential characteristics of each segment. These fingerprint copies serve as lightweight surrogates that enable repeating content detection without the storage burden of the original video data.

Inventive Principle:
Principle #26Copying

3Measurement precision

If video fingerprints are created for all segments, then accurate content recognition is achieved, but processing time and computational resources increase significantly

Engineering Contradiction:
Improvecontent recognition accuracyVSAvoidprocessing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system processes video data in segmented portions, creating audio fingerprints for each segment independently. This segmentation enables parallel processing of multiple segments simultaneously, improving processing efficiency while maintaining recognition accuracy through systematic analysis of divided content units.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system creates audio fingerprints for all segments but only performs detailed video fingerprint comparison for segments that show audio matches. This partial action approach applies the more computationally intensive video analysis only where necessary, rather than uniformly processing all segments, thereby improving overall processing efficiency.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3776263B1System and method for detecting repeating content, including commercials, in a video data stream using audio-based and video-based automated content recognition
Publication Date: 2022.11.30 ALPHONSO INC
  • EP3776263B1 patent drawingFigure 1
  • EP3776263B1 patent drawingFigure 2
  • EP3776263B1 patent drawingFigure 3

AI summary

Methods and apparatus are provided for detecting potential repeating content, such as commercials, in a video data stream by receiving one or more video data streams, parsing each video data stream into a plurality of segments, creating audio fingerprints of each segment, storing the plurality of audio fingerprints in a database, and identifying any audio fingerprints in the received and parsed one or more video data streams that match audio fingerprints in the database that were previously stored from video data streams that were previously received and parsed. Video fingerprints are then created for these same pairs of segments and a similarity analysis is performed. The results of the video fingerprint analysis is used to make a determination of subsequent actions to be taken by a content processing platform that performs recognition processing of the content associated with the segments identified as being potentially repeating content.