TOF Data Acquisition With Projection-Off Overexposure Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Facial recognition systems face challenges in ensuring secure, accurate, and rapid operation, particularly due to malicious attacks, poor image quality, and excessive latency.
Innovation Solution
The system employs a Time of Flight (TOF) camera with controlled light source operations to acquire and process TOF data, utilizing a trusted execution environment (TEE) for secure data processing, and adjusts exposure parameters based on ambient light conditions to enhance data quality and speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the TOF light source is continuously on to ensure sufficient illumination for facial recognition, then the image quality and recognition accuracy are improved, but overexposure occurs which degrades data quality
Solution Approach 1:
The patent applies preliminary anti-action by capturing projection off data (TOF data without light source) before or during the infrared data acquisition. This preliminary data is then used to subtract and remove the overexposure effects from the infrared data, effectively counteracting the harmful overexposure that occurs when the light source is on.
Solution Approach 2:
The patent converts the harmful overexposure effect into a beneficial correction process. By intentionally allowing overexposure when the light source is on, the system captures both the infrared reflection data and the overexposure artifact data. The projection off data serves as a reference to quantify and remove the overexposure component, transforming the harmful overexposure into useful information for correction.
2Reliability
If multiple frames of TOF data are acquired and processed to improve recognition accuracy, then the security and accuracy of facial recognition are enhanced, but the processing time and latency increase
Solution Approach 1:
The patent applies preliminary action by pre-processing the TOF data to generate depth images and infrared images from the projection off data and infrared data respectively. These pre-processed images are then used for anti-counterfeiting recognition, enabling security verification to be performed more efficiently without requiring extensive real-time processing of raw TOF data.
Solution Approach 2:
The patent segments the TOF data processing into distinct components: projection off data processing for depth images, infrared data processing for infrared images, and their combination for anti-counterfeiting recognition. This segmentation allows parallel processing of different data types and optimization of each processing pipeline independently, reducing overall latency.
3Reliability
If the TOF camera processes both projection off data and infrared data to generate depth images and infrared images for anti-counterfeiting recognition, then the security against malicious attacks is improved, but the device complexity and processing overhead increase
Solution Approach 1:
The patent applies universality by using the same TOF camera hardware to perform multiple functions: capturing projection off data for depth information, capturing infrared data for thermal/infrared imaging, and combining both for anti-counterfeiting recognition. This multi-functionality is achieved through software control of the light source and data processing, avoiding the need for separate hardware systems.
Solution Approach 2:
The patent merges the depth image processing and infrared image processing pipelines into a unified anti-counterfeiting recognition system. By combining the complementary information from depth data (geometric features) and infrared data (thermal/infrared features), the system achieves enhanced security against various malicious attacks including photo, video, and 3D mask attacks.
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 improves the security, accuracy, and speed of facial recognition by correcting overexposure, minimizing latency, and optimizing image quality using TOF data within the TEE, thereby enhancing user experience.
Implementation Method 1
obtaining the first frame of time of flight (TOF) data, where the first frame of TOF data includes projection off data and infrared data
Data Source
AI summary
A first frame of time of flight (TOF) data including projection off data and infrared data is obtained, and after determining that a data block satisfying that a number of data points with values greater than a first threshold is greater than a second threshold is present in the infrared data, TOF data for generating a first frame of a TOF image is obtained based on a difference between the infrared data and the projection off data. Because the data block satisfying the number of data points with values greater than the first threshold is greater than the second threshold is an overexposed data block, and the projection off data is TOF data acquired by a TOF camera with a TOF light source being off, the difference between the infrared data and the projection off data can correct the overexposure, improving quality of the first frame of the TOF image.