Video Analytics Reporting Threshold Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Security operators face challenges in manually screening large video streams from CCTV cameras, leading to missed detections and false alarms due to varying definitions of suspicious activities across different video analytics systems, which can result in unreported incidents of interest.
Innovation Solution
A video analytics data reporting system that adjusts the reporting threshold for video capturing devices deployed near an incident location, temporarily lowering the threshold to increase the reporting of video analytics data, thereby enhancing the detection of related events of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a high video analytics data reporting threshold is used, then false alarms are reduced, but the detection of relevant events may be missed
Solution Approach 1:
The patent applies dynamics by making the reporting threshold adjustable rather than fixed. The system can dynamically change the threshold based on the operational context - using a high threshold during normal operations to reduce false alarms, and temporarily lowering it when incidents are detected to improve detection of related events. This resolves the contradiction by allowing the threshold to adapt to changing requirements.
Solution Approach 2:
The patent implements parameter changes by modifying the reporting threshold parameter in response to detected incidents. When an incident is detected, the system changes the threshold parameter from high to low for a specified period, enabling the system to capture related events while maintaining reliability during normal operations. This parameter adjustment directly addresses the trade-off between false alarm reduction and missed detections.
2Loss of information
If a low video analytics data reporting threshold is used, then the detection of relevant events is improved, but false alarms increase
Solution Approach 1:
The system dynamically adjusts the reporting threshold based on operational needs. During normal conditions, a high threshold maintains reliability by reducing false alarms. When incidents are detected, the threshold is temporarily lowered to improve detection of related events. This dynamic adjustment allows the system to optimize for different objectives at different times, resolving the contradiction between detection capability and false alarm rate.
Solution Approach 2:
The patent changes the reporting threshold parameter in response to detected incidents. The system transitions from a high threshold (for reliability) to a low threshold (for improved detection) when needed, and can revert when the incident is resolved. This parameter change strategy allows the system to achieve both low false alarm rates during normal operations and high detection capability when incidents occur.
3Productivity
If the video analytics data reporting threshold is lowered temporarily, then the reporting of relevant events is increased, but system complexity increases
Solution Approach 1:
The system implements self-service by automatically detecting incidents and autonomously adjusting the reporting threshold without requiring manual intervention. The system monitors its own performance, detects when incidents occur, and automatically modifies its reporting behavior accordingly. This automation reduces the operational complexity of managing different reporting modes while maintaining high productivity in event detection.
Solution Approach 2:
The patent employs feedback mechanisms where the system continuously monitors video analytics data, detects incidents, and uses this information to adjust the reporting threshold. The feedback loop ensures that the threshold adjustment is based on actual system performance and detected conditions, allowing the system to optimize event reporting while managing complexity through automated, data-driven decision-making.
Data Source
AI summary
A process for adjusting an amount of video analytics data reported by video capturing devices deployed in a given location. In operation, an electronic computing device detects occurrence of an incident at an incident location based on processing video data or sensor data that are captured corresponding to the incident location. When it is determined that a video capturing device that is deployed within a predetermined distance from the incident location is currently configured with a second video analytics data reporting threshold that is greater than the first video analytics data reporting threshold, the electronic computing device transmits an instruction to the video capturing device to lower the second video analytics data reporting threshold to the first video analytics data reporting threshold and further report video analytics data corresponding to a video stream captured by the video capturing device as a function of the first video analytics data reporting threshold.