# US 10,368,740 B2 · Method and system for noncontact vision-based 3D cognitive fatigue measuring by using task evoked pupillary response

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,368,740 B2
- Document ID: US10368740B2
- Status: Granted
- Kind: B2
- Application number: 15/869,550
- Filed: 2018-01-12
- Published: 2018-08-09
- Granted: 2019-08-06
- Earliest claimed: 2017-02-03
- Assignees: Sangmyung University Industry-Academy Cooperation Foundation; Center of Human-Centered Interaction for Coexistence
- Applicants: Sangmyung University Industry-Academy Cooperation Foundation; Center of Human-Centered Interaction for Coexistence
- Inventors: Min Cheol Whang; Sang In Park; Myoung Ju Won; Dong Won Lee
- Web page: https://patentgrep.com/patent/US10368740B2

## CPC

- A61B 3/112: {for measuring diameter of pupils}
- A61B 5/162: {Testing reaction times}
- A61B 5/163: {by tracking eye movement, gaze, or pupil change}
- A61B 5/375: using biofeedback
- A61B 5/378: Visual stimuli
- A61B 5/4064: {Evaluating the brain (for intracranial pressure A61B5/031; for cerebral blood gases A61B5/14553; using EEG A61B5/369)}
- A61B 5/7235: {Details of waveform analysis (detecting specific parameters of the electrocardiograph cycle A61B5/349)}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

Provided are a method and system for noncontact vision-based 3D cognitive fatigue measuring. The method comprises: acquiring pupil images of a subject exposed to visual stimuli; extracting a task evoked pupillary response (TEPR) by using the pupil images; detecting dominant peaks from the TEPR; calculating latency of dominant peaks; and determining cognitive fatigue of the subject by comparing a value of the latency to a predetermined reference value.

## Claims

### Claim 1

A method of measuring noncontact-vision-based cognitive fatigue, the method comprising;
acquiring pupil images of a subject exposed to visual stimuli;
extracting a task evoked pupillary response (TEPR) by using the pupil images;
detecting dominant peaks from the TEPR;
calculating latency of the dominant peaks; and
determining cognitive fatigue of the subject by comparing a value of the latency to a predetermined reference value associated with cognitive fatigue.

### Claim 2 (depends on 1)

The method of claim 1, wherein the acquiring of the pupil images comprises:
capturing face images of the subject by using a video camera;
extracting the pupil images from the face images; and
extracting a pupil size variation (PSV) from the pupil images, and
wherein the calculating comprises calculating the TEPR from the PSV.

### Claim 3 (depends on 2)

The method of claim 2, wherein the extracting of the PSV comprises:
resampling the face images at a predetermined frequency; and
extracting the PSV from the resampled face images.

### Claim 4 (depends on 3)

The method of claim 3, further comprising: extracting unit PSVs divided into epochs of 1200 ms based on a stimulus onset of −200 to 1000 milliseconds.

### Claim 5 (depends on 4)

The method of claim 4, wherein the TEPR is calculated or produced by combining the unit PSVs by using a grand average technique.

### Claim 6

A system for measuring noncontact-vision-based cognitive fatigue, the system comprising:
a video camera configured to acquire pupil images of a subject exposed to visual stimuli;
a processing unit configured to process the pupil images; and
an analyzing unit configured to extract a task evoked pupillary response (TEPR) by using the pupil images, detect dominant peaks from the TEPR, calculate latency of the dominant peaks, and determine the cognitive fatigue by comparing a value of the latency to a predetermined reference value associated with cognitive fatigue.

### Claim 7 (depends on 6)

The system of claim 6, wherein the processing unit is further configured to extract the pupil images from face images and extract a pupil size variation (PSV) from the pupil images by resampling at a predetermined sampling frequency.

### Claim 8 (depends on 7)

The system of claim 7, wherein the analyzing unit is further configured to calculate unit PSVs divided into epochs of 1200 ms based on a stimulus onset of −200 to 1000 milliseconds.

### Claim 9 (depends on 8)

The system of claim 8, wherein the analyzing unit is further configured to calculate the TEPR by combining the unit PSVs by using a grand average technique.