Advertisement Frame Identification via Pearson Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic content recognition systems face challenges in accurately identifying advertisement frames within media streams, particularly due to resolution issues and sensitivity to pixel value outliers, which can lead to misidentification of advertisements amidst live programming.
Innovation Solution
The method employs scene-change Pearson correlation coefficients and match Pearson correlation coefficients to determine scene changes and identify advertisement frames, using fingerprints that represent average pixel values or 16 integer vectors of sub-frames, allowing for precise identification of advertisement scenes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional automatic content recognition systems use pixel value comparison methods, then they can identify frames in media streams, but they suffer from resolution issues and sensitivity to pixel value outliers leading to misidentification of advertisements
Solution Approach 1:
The patent transforms the identification approach by changing from direct pixel value comparison to using Pearson correlation coefficients. This parameter transformation makes the system insensitive to pixel value outliers and resolution variations, as correlation coefficients normalize the data and focus on pattern matching rather than absolute value matching, thereby resolving the misidentification problem while maintaining accuracy
Solution Approach 2:
The patent introduces Pearson correlation coefficients as an intermediary between raw pixel values and identification decisions. This intermediary transforms the raw data into a more robust representation that is invariant to resolution changes and pixel value outliers, allowing accurate advertisement frame identification without being affected by the previously problematic direct pixel comparison methods
2Measurement precision
If the system uses detailed pixel value analysis for scene change detection, then it can identify scene boundaries, but it becomes sensitive to outliers and resolution variations
Solution Approach 1:
The patent changes the detection parameter from absolute pixel values to Pearson correlation coefficients. This transformation preserves the ability to detect scene changes accurately by identifying patterns and transitions, while simultaneously eliminating sensitivity to pixel value outliers and resolution variations, as correlation analysis focuses on relative changes rather than absolute values
Data Source
AI summary
A method for flagging advertisement frames for automatic content recognition is provided. The method includes receiving broadcast fingerprints indicative of broadcast frames of a media stream comprising a series of broadcast scenes. The method also includes receiving advertisement fingerprints indicative of ad frames of ad scenes. The method further includes determining a scene change between a first broadcast scene and a second broadcast scene. The scene change is based on a Pearson correlation coefficient between an initial broadcast fingerprint of an initial broadcast frame of the second broadcast scene and a last broadcast fingerprint of a last broadcast frame of the first broadcast scene. The method also further includes determining whether the second broadcast scene is one of the ad scenes. When the second broadcast scene is one of the ad scenes, the method associates an identification of the second broadcast scene as the one of the ad scenes.