Group Action Recognition Using Absence Duration Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In group action recognition, temporary absence or non-detection of individuals can lead to decreased accuracy due to the exclusion of absent or undetected persons, which affects the overall recognition process.
Innovation Solution
The image recognition device employs duration-based thresholds to determine when a person's absence or non-detection is temporary, allowing for the continuation of group action recognition by substituting past reliable results when necessary, thereby preventing immediate determination of impossibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If absent or undetected persons are excluded from group action recognition, then the recognition process can proceed with available data, but the accuracy of group action recognition decreases
Solution Approach 1:
The system performs preliminary actions by maintaining historical action recognition results for persons who are temporarily absent. Instead of immediately excluding absent persons, the system preserves their past reliable action data and uses it to continue group action recognition, thereby preventing accuracy degradation while maintaining process continuity
Solution Approach 2:
The system provides beforehand cushioning by establishing a mechanism that compensates for temporary absences. When a person is absent, the system uses their historical action recognition results as a buffer or cushion, allowing the recognition process to continue without immediate accuracy loss. This cushioning mechanism resolves the contradiction by preparing advance alternatives to the excluded data
2Speed
If immediate determination is made that group action recognition is impossible when a person is absent, then the system responds quickly to absences, but the accuracy of group action recognition decreases due to temporary absences being treated as permanent
Solution Approach 1:
The system applies dynamics by making the absence determination dynamic rather than static. Instead of immediate permanent exclusion, the system continuously monitors the duration of absence and adjusts its response. When absence duration exceeds the threshold, the system then determines recognition is impossible, allowing quick response to genuine absences while avoiding premature judgment on temporary absences
Solution Approach 2:
The system performs preliminary monitoring of absence duration before making the final determination that group action recognition is impossible. This preliminary action phase allows the system to distinguish between temporary absences (where recognition can continue using historical data) and permanent absences (where recognition must be suspended), thereby maintaining both speed and accuracy
Data Source
AI summary
An image recognition device includes one or more processors configured to perform group action recognition for a group from results of person action recognition. The one or more processors are configured to perform: a person action recognition determination process of, when a first duration in which a person who was present in a past frame image is not present in a newest frame image continuously is less than a first time threshold value, determining that the person action recognition is impossible for the person subjected to determination on the first duration; and a group action recognition determination process of determining that the group action recognition is impossible when a second duration in which the number of persons for whom the person action recognition is determined to be impossible is continuously equal to or more than a number threshold value is equal to or more than a second time threshold value.