Automatic Content Recognition System for Erroneous Commercial Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic content recognition (ACR) systems struggle to accurately identify and log commercials in video data streams due to scenarios where identical or similar commercials with different lengths, or those with similar audio and visual content, result in erroneous logging of start and end times.
Innovation Solution
The method involves forming clusters of commercials with overlapping time and content, generating permutations of commercial break timelines, ranking them based on best fit criteria, and permanently logging only the best fit timeline to remove erroneous commercial logs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If ACR systems log all detected commercials, then the quantity of logged commercials increases, but the accuracy of commercial detection decreases due to erroneous identification
Solution Approach 1:
The system performs preliminary clustering of detected commercials based on temporal and content-based similarities before final logging. By pre-grouping potentially duplicate or overlapping detections, the system can apply consistency checks and resolve ambiguities before committing to the final log, thus maintaining high quantity while improving accuracy.
Solution Approach 2:
The system uses feedback mechanisms where initially logged commercials are evaluated for consistency. When conflicts or errors are detected in the logged data, the system automatically triggers re-detection or correction processes, allowing continuous improvement of detection accuracy while maintaining comprehensive logging.
2Measurement precision
If ACR systems perform detailed analysis to improve detection accuracy, then the measurement precision improves, but the processing time increases
Solution Approach 1:
The detection process is segmented into multiple stages: initial quick detection, clustering analysis, and detailed verification only for ambiguous cases. This segmentation allows the system to process most commercials quickly while applying detailed analysis only where necessary, thus improving overall accuracy without proportionally increasing processing time.
Solution Approach 2:
The system applies full analytical processing only to a subset of commercials that show detection ambiguity or overlap, while using simplified processing for clear-cut cases. This partial application of excessive action ensures high accuracy for problematic detections while maintaining efficiency for routine detections.
3Device complexity
If ACR systems use simple detection methods, then the device complexity decreases, but the reliability of commercial identification decreases
Solution Approach 1:
The system introduces clustering as an intermediary processing layer between simple detection and final logging. This intermediary step adds minimal complexity but significantly improves reliability by resolving ambiguities and eliminating duplicate detections before final identification is committed.
Solution Approach 2:
The system employs self-correcting mechanisms where the clustering and verification processes automatically identify and resolve their own errors without external intervention. This self-service capability improves reliability while keeping the overall system complexity manageable through automated error correction.
Data Source
AI summary
Methods and apparatus are provided for automatically removing erroneously logged commercials from a listing of commercials that are detected in a video data stream by performing automatic content recognition on the video data stream and detecting the identity of each of the commercials played in a commercial break, temporarily logging the identity and start and end time of each detected commercial in a log of played commercials, forming clusters from commercials that overlap in time and have related content, or have significant overlap in time, forming permutations of commercial break timelines from the detected commercials, ranking the timelines based on best fit criteria and selecting the best fit timeline, permanently logging only the commercials in the best fit timeline, and removing the remaining commercials from the temporary log. The remaining logged commercials are presumed to be either erroneously identified commercials or properly identified commercials with erroneous start and end times.