Oculometric Digital Marker Detection via Video Deconvolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for monitoring neurological disorders using eye movements are hindered by the need for expensive and inconvenient laboratory setups, and they often lack the necessary resolution for accurate measurements.
Innovation Solution
A system and method that utilize a video stream to determine oculometric parameters, including a pupillary response function of brightness or a gaze response function, through a deconvolution process, allowing for the identification of digital markers indicative of neurological or mental health conditions without the need for controlled lab settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated devices with controlled lab settings are used to measure eye movements, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a camera to capture images of the eye, creating a visual copy of the eye's state. This copy is then processed to extract oculometric parameters, replacing the need for complex dedicated measurement devices while maintaining measurement capability.
Solution Approach 2:
The patent replaces mechanical eye tracking devices with an optical system (camera) and computational processing. Instead of using physical sensors to directly measure eye movements, the system uses images and deconvolution algorithms to derive the same information, simplifying the overall system.
2Measurement precision
If dedicated eye tracking devices are used, then measurement precision is improved, but cost increases
Solution Approach 1:
The patent employs standard camera technology and computational algorithms that can be implemented with inexpensive components. Instead of requiring expensive dedicated eye tracking hardware, the system uses readily available camera technology combined with software processing to achieve the same measurement goals.
Solution Approach 2:
The invention replaces costly mechanical eye tracking equipment with a camera-based optical system and digital processing. This substitution maintains measurement precision while dramatically reducing hardware costs through the use of standard imaging technology and computational algorithms.
3Measurement precision
If controlled lab settings with standardized stimuli are used, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent transitions from static, controlled lab conditions to dynamic, real-world monitoring. The system can capture eye movements and responses in various lighting conditions and environmental contexts, allowing continuous monitoring without requiring controlled settings. This dynamic approach maintains measurement precision while greatly improving ease of operation.
Solution Approach 2:
The system handles varying parameters such as lighting conditions, camera distance, and environmental factors through computational deconvolution and algorithmic correction. By changing the approach from controlling physical parameters to compensating for parameter variations through software, the system maintains accuracy while enabling flexible, convenient operation in diverse settings.
4Measurement precision
If deconvolution process is applied to video stream, then measurement precision is improved, but processing time increases
Solution Approach 1:
The patent applies deconvolution processing selectively and iteratively, applying the computation only where needed and adjusting the level of processing based on requirements. This partial application of the deconvolution process achieves sufficient measurement precision without the full computational burden, balancing accuracy with processing time.
Data Source
AI summary
Disclosed are system, method, and computer program product embodiments for determining a digital marker. An embodiment operates by determining one or more oculometric parameters associated with an eye of a user using a video stream. The video stream comprises at least one image of a face of the user. The embodiment then determines a pupillary response function of brightness or a gaze response function by performing a deconvolution process based on at least the one or more oculometric parameters. The pupillary response function of brightness or the gaze response function is indicative of a response of the eye of the user to an external factor. The embodiment determines one or more digital markers of the user based on the pupillary response function of brightness or the gaze response function. The one or more digital markers are indicative of a neurological condition or a mental health condition of the user.


