Analytics-Driven Surveillance Summary Views With Event Cropping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video surveillance systems lack situational awareness, as operators face a 'wall of monitors' with cycling feeds and lack effective discrimination between camera views, failing to provide a comprehensive sense of what is happening across the monitored area.
Innovation Solution
A method and system for generating analytics-driven summary views that dynamically compose selected surveillance video streams based on detected events, cropping frames to show only relevant portions of the scene, using video analytics in cameras and servers to identify and prioritize events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If operators monitor all video feeds simultaneously on multiple monitors, then comprehensive coverage of surveillance areas is achieved, but operators cannot effectively discriminate between camera views and lose situational awareness
Solution Approach 1:
The system extracts and displays only the relevant portions of video frames that contain detected events, removing irrelevant background areas. This allows operators to focus on critical areas across multiple camera feeds without being overwhelmed by unnecessary visual information, thereby maintaining comprehensive coverage while improving discrimination ability.
Solution Approach 2:
The system applies different display qualities and levels of detail to different regions of the video feed based on event detection. Areas with detected events receive enhanced focus and detail, while areas without events are summarized or minimized. This creates a hierarchical visual structure that improves operator discrimination without sacrificing overall coverage.
2Loss of information
If operators view complete video frames from multiple cameras, then all details are visible, but operators cannot quickly identify critical events across numerous feeds
Solution Approach 1:
The system performs preliminary analysis of video frames using computer vision algorithms to detect events before presenting them to operators. By pre-identifying relevant portions containing events, the system prepares prioritized visual information in advance, allowing operators to immediately focus on critical areas without manually scanning entire frames, thus reducing event identification time while preserving detail visibility.
Solution Approach 2:
The system segments video frames into relevant and irrelevant portions based on detected events. Only segments containing events are highlighted or extracted for detailed viewing, while other segments are minimized or summarized. This segmentation allows operators to quickly locate critical events across multiple feeds without losing access to complete frame details when needed.
3Measurement precision
If the system displays all video streams in full resolution, then image quality is maintained, but the wall of monitors becomes overwhelming and reduces situational awareness
Solution Approach 1:
The system dynamically adjusts the level of detail and resolution allocated to different video feeds based on detected events. Feeds containing events receive higher resolution and more display space, while feeds without events are summarized at lower resolution or combined into overview panels. This dynamic adaptation maintains image quality for critical areas while reducing overall display complexity and preventing operator overwhelm.
Data Source
AI summary
A method of displaying surveillance video streams is provided that includes receiving surveillance video streams generated by a plurality of video cameras, and displaying a selected subset of the surveillance video streams in a summary view on at least one display device, wherein, for each surveillance video stream in the summary view, only a relevant portion of each frame in the surveillance video stream is displayed, and wherein a relevant portion is a subset of a frame for at least some of the surveillance video streams in the summary view.