Dynamic Resolution Switching for Face Detection Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Face detection in electronic devices can be unstable, particularly when the user is viewed from a side profile, leading to incorrect detection of user presence or absence, especially when using infrared sensors or low-resolution images.
Innovation Solution
An electronic apparatus that uses a processor to detect face areas in images captured at predetermined intervals, switching between low-resolution and high-resolution modes based on detection stability, and adjusts the detection range and threshold for movement to accurately determine user presence, employing a face detection unit, detection state determination unit, and movement amount determination unit to enable or disable detection accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If face detection is performed using low-resolution image data, then processing speed and power consumption are improved, but detection accuracy deteriorates
Solution Approach 1:
The system dynamically adjusts the resolution of image data used for face detection based on the detection state. When faces are consecutively detected, low-resolution data is used for efficient processing. When detection becomes unstable, the system switches to high-resolution data to improve accuracy, thus making the resolution parameter dynamic rather than fixed.
Solution Approach 2:
The invention changes the parameter of image resolution based on detection stability. By monitoring whether face areas are consecutively detected, the system switches between using first-resolution (low) and second-resolution (high) image data, effectively using parameter changes to balance processing efficiency and detection accuracy.
2Measurement precision
If face detection is performed using high-resolution image data, then detection accuracy is improved, but processing load and power consumption increase
Solution Approach 1:
Instead of continuously using high-resolution data, the system applies high-resolution processing only partially - specifically when detection stability deteriorates. This partial application of high-resolution processing provides sufficient accuracy improvement without the continuous energy cost of high-resolution processing.
Solution Approach 2:
The system makes the resolution level dynamic based on detection needs. During stable detection periods, low-resolution processing reduces power consumption. When instability is detected, the system transitions to high-resolution processing only when necessary, optimizing the balance between accuracy and energy usage.
3Area of stationary object
If detection range is expanded to cover more image areas, then detection coverage is improved, but false detection from non-user movements increases
Solution Approach 1:
The system segments the detection process into two stages: first using low-resolution data to identify potential face areas, then using high-resolution data specifically in those identified areas when stability deteriorates. This segmentation allows comprehensive coverage while reducing false detections by focusing high-resolution processing only where needed.
Solution Approach 2:
The detection state determination unit acts as an intermediary that monitors detection stability and triggers resolution switching. This intermediary mechanism prevents false detections by intervening when detection patterns suggest instability, switching to high-resolution verification only when necessary.
4Area of stationary object
If infrared sensor is used for person detection, then detection range is improved, but false detection of non-person objects increases
Solution Approach 1:
The system uses infrared sensor data as an intermediary to identify potential person locations, then applies face detection as a verification step. This two-stage approach with the infrared sensor as the first intermediary allows broad detection range while using the more specific face detection as a second intermediary to filter out false detections of non-person objects.
Solution Approach 2:
The detection process is segmented into broad person detection using infrared sensors followed by specific face verification. This segmentation allows the system to first cast a wide net for potential persons, then apply more precise face detection only to identified candidates, balancing detection range with accuracy.
Data Source
AI summary
An electronic apparatus includes a memory which temporarily stores image data of an image captured by an imaging device, and a processor which processes image data stored in the memory. The processor processes image data of plural images captured by the imaging device at predetermined time intervals and stored in the memory, detects face areas with faces captured therein from among the plural images based on first-resolution image data and second-resolution image data, and determines whether or not the face areas are consecutively detected from the plural images. Further, when determining that the state is changed between a state where face areas are consecutively detected and a state where face areas are not consecutively detected while performing processing to detect the face areas based on first-resolution image data, the processor detects face areas from among the plural images based on the second-resolution image data.