Dual-Stream Surveillance Camera for Detection and Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic surveillance systems face challenges in simultaneously detecting unusual acts and identifying subjects within a scene using a single camera, as they either lose detection capability when zooming in for identification or can be deceived by decoys due to limitations in Pan, Tilt, and Zoom (PTZ) camera capabilities.
Innovation Solution
The system captures and processes two image streams from a single camera, with a lower resolution stream for detection and a higher resolution stream for identification, allowing for continuous detection and simultaneous identification of multiple events without losing scene coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a PTZ camera zooms in to identify an object, then identification capability is improved, but detection capability is lost
Solution Approach 1:
The patent divides the image processing into two separate streams: a low-resolution stream for detection and a high-resolution stream for identification. This segmentation allows the system to maintain wide scene coverage through the low-resolution stream while simultaneously providing detailed identification through the high-resolution stream, resolving the contradiction between identification capability and scene coverage.
2Measurement precision
If multiple cameras are used to maintain scene coverage and identification, then identification capability is improved, but device complexity increases
Solution Approach 1:
The patent makes a single camera perform multiple functions by capturing images at two different resolutions simultaneously. The same camera hardware serves both detection (wide coverage, low resolution) and identification (detailed view, high resolution) purposes, eliminating the need for multiple cameras and reducing system complexity.
3Measurement precision
If PTZ camera is used for surveillance, then identification capability is improved, but reliability decreases due to decoy deception
Solution Approach 1:
The patent performs preliminary detection using the low-resolution stream to identify suspicious activities or objects before committing resources to detailed analysis. This preliminary action allows the system to maintain continuous monitoring of the entire scene and only activate high-resolution identification when necessary, preventing decoys from successfully diverting attention from real threats.
Data Source
AI summary
A system and method for surveillance of a scene comprising the steps of: capturing a scene via at least two image streams; processing the first of the two image streams to detect an act, event or object; and, wherein when an act, event or object is detected, storing portions of the second image stream corresponding to the act, event or object independently of the first image stream.