# US 2026/0188026 A1 · Method for detecting abnormal activity of driver

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

- Number: US 2026/0188026 A1
- Document ID: US20260188026A1
- Status: Published application
- Kind: A1
- Application number: 19/436,739
- Filed: 2025-12-30
- Published: 2026-07-02
- Earliest claimed: 2025-01-02
- Assignees: MiTAC Digital Technology Corporation
- Applicants: MiTAC Digital Technology Corporation
- Inventors: Hsiang-Yu HSIEH
- Web page: https://patentgrep.com/patent/US20260188026A1

## CPC

- G06V 20/597: {Recognising the driver's state or behaviour, e.g. attention or drowsiness}
- A61B 5/0077: {Devices for viewing the surface of the body, e.g. camera, magnifying lens}
- A61B 5/1114: {Tracking parts of the body}
- A61B 5/1118: {Determining activity level}
- A61B 5/1121: {Determining geometric values, e.g. centre of rotation or angular range of movement}
- A61B 5/1128: {using image analysis (A61B5/1127 takes precedence)}
- A61B 5/18: for vehicle drivers {or machine operators}
- A61B 5/6893: {Cars}
- A61B 5/726: {using Wavelet transforms}
- A61B 5/7267: {involving training the classification device}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- A61B 2503/22: Motor vehicles operators, e.g. drivers, pilots, captains
- G06T 2207/20064: Wavelet transform [DWT]
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30196: Human being; Person
- G06T 2207/30268: Vehicle interior
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for detecting abnormal activity of a driver implemented by a monitoring device which includes an angle acquisition unit that obtains an angle signal during a preset time period, and a processing unit. The method includes: generating a spectrogram from the angle signal; obtaining a frequency set within the preset time period; obtaining, based on the frequency set, candidate time point(s), each corresponding to a frequency in the spectrogram that is greater than a dynamic frequency threshold; obtaining a base frequency signal based on the spectrogram; converting the base frequency signal to a base angle signal using a signal conversion technique; obtaining a peak time point that corresponds to a maximum angle value of the base angle signal within the preset time period; and obtaining an occurrence period related to an occurrence of the abnormal activity based on the peak time point and the candidate time point(s).

## Claims

### Claim 1

A method for detecting an abnormal activity of a driver, the method to be implemented by an in-vehicle monitoring device, the monitoring device including an angle acquisition unit that is configured to obtain an angle signal during a preset time period, and a processing unit that is electrically connected to the angle acquisition unit, the method comprising steps of, by the processing unit:
generating a spectrogram from the angle signal by performing a time-frequency analysis;
obtaining, based on a high frequency part of the spectrogram, a frequency set within the preset time period;
obtaining, based on the frequency set, at least one candidate time point, each corresponding to a frequency in the spectrogram that is greater than a dynamic frequency threshold;
obtaining a base frequency signal based on the spectrogram;
converting the base frequency signal to a base angle signal using a signal conversion technique;
obtaining a peak time point that corresponds to a maximum angle value of the base angle signal within the preset time period; and
obtaining an occurrence period related to an occurrence of the abnormal activity based on the peak time point and the at least one candidate time point.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the step of obtaining the base frequency signal includes:
obtaining, from the spectrogram, at least one candidate signal content with a time-frequency window that is greater than a window width threshold; and
obtaining the base frequency signal based on the at least one candidate signal content.

### Claim 3 (depends on 1)

The method as claimed in claim 1, the angle acquisition unit including a capturing module that is configured to obtain a plurality of images related to a head portion of the driver during the preset time period, and a processing module that is electrically connected to the capturing module and that is configured to convert the plurality of images to the angle signal, the method further comprising, before the step of generating the spectrogram, steps of:
for each image of the plurality of images, the processing module obtaining a raw angle of the head portion of the driver in the image;
the processing module obtaining an initial signal based on a plurality of the raw angles that are obtained respectively from the plurality of images during the preset time period; and
the processing module obtaining the angle signal based on the initial signal using a calibration technique.

### Claim 4 (depends on 3)

The method as claimed in claim 3, wherein the step of obtaining the raw angle for each image of the plurality of images includes:
obtaining a plurality of head feature points of the head portion of the driver in the image using a feature algorithm; and
obtaining the raw angle related to the head rotation of the driver based on the plurality of head feature points.

### Claim 5 (depends on 3)

The method as claimed in claim 3, wherein the calibration technique includes calculating an average offset of the initial signal, and removing the average offset from the initial signal so as to obtain the angle signal.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein, in the step of generating the spectrogram from the angle signal, the processing unit generates the spectrogram using a wavelet transform, and, in the step of converting the base frequency signal to the base angle signal, the processing unit converts the base frequency signal to the base angle signal using an inverse wavelet transform.

### Claim 7 (depends on 1)

The method as claimed in claim 1, wherein the step of obtaining the occurrence period includes:
for each candidate time point of the at least one candidate time point, obtain a time variation value by obtaining an absolute value of the difference between the candidate time point and the peak time point;
from among at least one time variation value obtained respectively from the at least one candidate time point, obtaining a target time point that corresponds to a minimum one of the at least one time variation value; and
obtaining the occurrence period based on the target time point and the peak time point.

### Claim 8 (depends on 1)

The method as claimed in claim 1, wherein, in the step of obtaining the at least one candidate time point, the at least one candidate time point includes a plurality of candidate time points, and the step of obtaining the occurrence period includes:
from among the plurality of candidate time points, obtaining a first target time point that is immediately before the peak time point and a second target time point that is immediately after the peak time point; and
obtaining the occurrence period based on the first target time point and the second target time point.

### Claim 9 (depends on 1)

The method as claimed in claim 1, wherein the at least one candidate time point is one of an instantaneous time point and a time period.

### Claim 10 (depends on 1)

The method as claimed in claim 1, the monitoring device further including a storage medium, the angle acquisition unit including a capturing module that is configured to obtain a plurality of images related to a head portion of the driver during the preset time period,
the method further comprising, after obtaining the occurrence period, storing a portion of the plurality of images in the storage medium, where the portion of the plurality of images are obtained during the occurrence period.

### Claim 11 (depends on 10)

The method as claimed in claim 10, further comprising, after obtaining the occurrence period:
determining whether a number of instances of the occurrence of the abnormal activity during a predetermined period is greater than a predetermined value; and
in response to determining that the number of instances of the occurrence of the abnormal activity during the predetermined period is greater than the predetermined value, increasing an amount of the portion of the plurality of images that are stored in the storage medium.

### Claim 12 (depends on 11)

The method as claimed in claim 11, further comprising:
in response to determining that the number of instances of the occurrence of the abnormal activity during the predetermined period is greater than the predetermined value, determining a type of the abnormal activity based on a portion of the base angle signal that corresponds to the occurrence period and a plurality of preset head rotation patterns;
in response to determining that the type of the abnormal activity is distraction, generating a distraction marker for the portion of the plurality of images; and
in response to determining that the type of the abnormal activity is fatigue, generating a fatigue marker for the portion of the plurality of images.

### Claim 13 (depends on 10)

The method as claimed in claim 10, further comprising, after obtaining the occurrence period:
determining whether a change in the base angle signal during a determination time period conforms with a preset waveform;
in response to determining that the change in the base angle signal conforms with the preset waveform, determining that a type of the abnormal activity of the driver is one of fatigue and distraction.
