Scene Frame Matching via Centroid Distance for ACR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic content recognition (ACR) systems face challenges in accurately matching scene frames due to differences in frame rates between broadcast and media device streams, leading to timing mismatches that can result in incorrect identification of user position within media content, potentially causing dynamic advertising replacement errors.
Innovation Solution
The method involves determining scene centroids by averaging pixel values of frames and calculating distances between these centroids and target fingerprints, using Pearson correlation coefficients to identify matching frames, thereby ensuring accurate scene frame matching even with varying frame rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional frame-by-frame matching is used, then the system can handle varying frame rates, but the timing accuracy deteriorates leading to incorrect user position identification
Solution Approach 1:
The patent introduces scene centroids as intermediary reference points between broadcast frames and media device frames. These centroids serve as mediators that enable accurate matching despite frame rate differences, resolving the contradiction between adaptability to varying frame rates and timing precision.
Solution Approach 2:
The patent transforms the matching approach by changing from direct frame-to-frame comparison to centroid-to-centroid distance calculation. This parameter transformation enables the system to maintain timing accuracy while adapting to different frame rates, as centroids provide a stable reference that is less sensitive to frame rate variations.
2Measurement precision
If scene centroids are calculated by averaging all frame pixel values, then scene representation accuracy improves, but computational complexity increases
Solution Approach 1:
The patent extracts only the essential information needed for matching by calculating scene centroids from key frame representations rather than processing all frame data. This extraction approach maintains scene representation accuracy while reducing computational complexity by focusing on the most relevant features.
3Measurement precision
If Pearson correlation coefficient is used for frame matching, then matching accuracy improves, but processing time increases
Solution Approach 1:
The patent performs preliminary calculation of scene centroids before the actual matching process. This preliminary action prepares the data in advance, allowing the Pearson correlation coefficient to be applied more efficiently during matching, thus reducing overall processing time while maintaining high matching accuracy.
Data Source
AI summary
A method for scene frame matching for automatic content recognition. The method includes receiving fingerprints indicative of frames of a media stream. The method also includes obtaining scene centroids of corresponding scenes of the media stream. Each scene includes fingerprints ranging from an initial frame having a corresponding initial fingerprint and a last frame having a corresponding last fingerprint. Each scene centroid represents a mean of fingerprints corresponding to a respective scene. The mean of fingerprints is determined by an average of pixel values corresponding to the fingerprints of the respective scene. For each scene centroid, the method includes determining a distance between the respective scene centroid and a target fingerprint of a corresponding target frame of the media stream and determining a target scene of the target frame as being the respective scene of the scene centroid having a shortest distance to the target fingerprint of the target frame.