Presence Detection System Using Fusion Unit for False Trigger Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional human presence detectors face challenges in accurately distinguishing a potential user from a passer-by due to frequent false detections and misses, especially when only partial body images are captured, leading to inefficiencies in waking up electronic devices.
Innovation Solution
A human presence detection system that combines a camera with an appearance-based detector and a proximity detector, using a fusion unit to integrate face detection and motion detection signals to accurately identify a user's intent to use a device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If face detection is used to determine human presence, then detection accuracy is improved when clear facial features are available, but detection fails when face is occluded, out of camera field-of-view or of poor image quality
Solution Approach 1:
The patent combines face detection results with motion detection results through a fusion unit. When face detection fails due to occlusion, poor quality, or field-of-view limitations, the system supplements this with motion detection in a predetermined window, ensuring reliable presence detection under various conditions.
Solution Approach 2:
The fusion unit acts as an intermediary that integrates outputs from both face detection and motion detection modules. It combines these detection signals to produce a final presence detection result, allowing the system to overcome limitations of individual detection methods.
2Adaptability or versatility
If motion detection is used as an auxiliary mechanism for human detection, then detection coverage is improved, but false detections increase due to inability to distinguish potential users from passers-by
Solution Approach 1:
The system merges motion detection with appearance-based detection in a fusion unit. Motion detection provides broad coverage by detecting any movement in the predetermined window, while appearance-based detection refines this by identifying specific features, together reducing false detections of passers-by.
Solution Approach 2:
The system dynamically adjusts detection sensitivity and fusion logic based on detection conditions. The fusion unit processes detection signals adaptively, combining results from motion and appearance detectors to maintain high reliability while preserving broad detection coverage.
3Ease of operation
If conventional human presence detectors are used to wake up electronic devices, then device activation is enabled, but frequent false triggers and detection misses occur due to inability to distinguish user intent
Solution Approach 1:
The patent combines multiple detection approaches (face detection and motion detection) in a fusion unit to determine user presence with intent. This multi-modal detection approach reduces false triggers and detection misses by cross-validating detection results from different methods before triggering device activation.
Data Source
AI summary
A presence detection system includes a camera that captures an image; an appearance-based detector that detects appearance of an object according to the image, thereby outputting an appearance-detection signal that is asserted when the appearance is detected; a proximity detector that detects motion of the object on a predetermined detection window on the image, thereby outputting a proximity-detection signal that is asserted when the motion is detected; and a fusion unit that receives the appearance-detection signal and the proximity-detection signal, thereby outputting an object-presence signal that is asserted when the appearance-detection signal or the proximity-detection signal is asserted.