IR Illuminator Array Depth Map for False Alert Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video surveillance systems face challenges in efficiently utilizing infrared emitters to provide accurate depth maps and object classification, leading to false positives and inefficient motion detection, particularly in environments with complex lighting conditions and multiple movement sources.
Innovation Solution
The system employs a 2D array of image sensors and IR illuminators to generate lookup tables for depth estimation, allowing for the classification of objects and detection of movement by simulating virtual surfaces and normalizing IR light intensity vectors, which are used to create depth maps and identify specific features like windows and floors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional motion detection algorithms are used in video surveillance systems, then the system can detect movement in the scene, but it generates false positives and cannot accurately distinguish between significant motion and insignificant motion sources
Solution Approach 1:
The patent introduces depth as a new dimension by using infrared illuminators at multiple positions to capture intensity variations. By analyzing how infrared light intensity changes across different illuminator positions, the system constructs depth information that traditional 2D video surveillance lacks. This additional dimensional information enables more accurate distinction between actual intruders and false motion sources.
Solution Approach 2:
The patent uses infrared light as an intermediary to obtain depth information indirectly. Instead of directly measuring depth, the system illuminates the scene with infrared light from multiple positions and uses the intensity variations to infer depth. This intermediary approach allows the system to gain three-dimensional spatial understanding without requiring complex depth sensors.
2Measurement precision
If infrared emitters are used to illuminate the scene for depth estimation, then depth information can be obtained, but the system complexity increases due to multiple illuminator positions and intensity vector processing
Solution Approach 1:
The patent segments the infrared illuminators into multiple discrete positions arranged in an array. Each illuminator position acts as an independent measurement point, and the system processes intensity vectors from each segment separately. This segmentation allows the complex problem of depth estimation to be broken down into manageable intensity comparisons across discrete illuminator positions.
Solution Approach 2:
The patent changes the spatial parameter of the infrared illuminators by positioning them at multiple locations in an array. By varying the illuminator position parameter and measuring intensity changes accordingly, the system extracts depth information. This parameter change approach transforms a complex depth measurement problem into a series of simpler intensity ratio comparisons.
3Reliability
If the system captures and processes large amounts of video data continuously, then comprehensive monitoring is achieved, but the processing efficiency decreases and storage requirements increase
Solution Approach 1:
The patent extracts only the essential depth information from the infrared intensity data using pre-computed lookup tables. Instead of processing and storing all raw video frames, the system extracts depth maps and motion information selectively. This extraction approach maintains comprehensive monitoring while significantly reducing the data processing and storage burden.
Solution Approach 2:
The patent performs preliminary computation by pre-calculating lookup tables that map infrared intensity ratios to depth values. This preliminary action allows the system to quickly convert raw intensity measurements into meaningful depth information without real-time complex calculations, thereby improving processing efficiency while maintaining monitoring comprehensiveness.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of depth estimation and object classification, reduces false positives, and improves motion detection by providing a more nuanced understanding of the scene, enabling better alert systems and zone management in video surveillance.
Implementation Method 1
Many such cameras use infrared (IR) illuminators, which allow video capture without illuminating a scene with visible light
Implementation Method 2
The process uses the captured IR images to form an intensity map of the scene with an intensity value determined for each pixel
Data Source
AI summary
A process reduces false positive security alerts. The process is performed at a computing device having one or more processors, and memory storing one or more programs configured for execution by the one or more processors. The process computes a depth map for a scene monitored by a video camera using a plurality of IR images captured by the video camera and uses the depth map to identify a first region within the scene having historically above average false positive detected motion events. In some instances, the first region is a ceiling, a window, or a television. The process monitors a video stream provided by the video camera to identify motion events, excluding the first region, and generates a motion alert when there is detected motion in the scene outside of the first region and the detected motion satisfies threshold criteria.