Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for detecting fatigue state based on audio and video

A fatigue state and fatigue detection technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as rear-end collisions and inability to effectively remind drivers.

Active Publication Date: 2022-02-08
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If you simply give voice prompts, it may not be able to effectively remind the driver; if you directly take over the vehicle and let the vehicle slow down or even stop, considering the actual driving environment, it is easy to cause other traffic accidents such as rear-end collisions, etc.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for detecting fatigue state based on audio and video
  • Method and device for detecting fatigue state based on audio and video
  • Method and device for detecting fatigue state based on audio and video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] Such as figure 1 As shown, the audio-video-based fatigue state detection method provided in Embodiment 2 of the present application includes:

[0100] S101: Driver identity recognition: confirm the identity of the target driver in the local driver file database through face recognition technology, if there is no corresponding personnel information, create a new driver file;

[0101] S102: Target driver data collection: during the driving process of the vehicle, collect the audio-video information and physiological information of the target driver during driving, and extract the data related to fatigue detection in the audio-video information and physiological information, and obtain Fatigue detection data; the audio and video information includes: facial video information, overall torso video information and audio information;

[0102] S103: Target driver fatigue state detection: analyze the current state of the target driver according to the fatigue detection data and...

Embodiment 2

[0172] Such as figure 1 As shown, the audio-video-based fatigue state detection method provided in Embodiment 2 of the present application includes:

[0173] S101: Driver identity recognition: confirm the identity of the target driver in the local driver file database through face recognition technology, if there is no corresponding personnel information, create a new driver file;

[0174] In some embodiments, the sample feature sequence is generated by analyzing and extracting the digital features of the driver's face image, and the sample feature sequence is compared with the feature sequence in the local driver file database to identify the driver's identity and assist subsequent based on Fatigue state detection of audio and video;

[0175] S102: Data collection of the target driver: During the driving process of the vehicle, the audio and video information and physiological information of the target driver during the driving process are collected through the face collecti...

Embodiment 3

[0294] Such as Figure 8 As shown, embodiment 3 provides a kind of fatigue state detection device based on audio and video, comprising:

[0295] Identity verification module, information collection module, fatigue analysis module, safety rating module and alarm takeover module; the identity verification module is connected to the information collection module, the information collection module is connected to the fatigue analysis module, and the fatigue analysis module The module is connected to the safety rating module, and the safety rating module is connected to the warning takeover module;

[0296] The identity verification module confirms the identity of the target driver in the local driver file database through face recognition technology, and if there is no corresponding personnel information, a new driver file is created;

[0297] In some embodiments, the device for collecting the face information of the driver can be a camera or other video collector, etc., and the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a fatigue state detection method and device based on audio and video, including: confirming the identity of the target driver in the local driver file database through face recognition technology, and creating a new driver file if there is no corresponding personnel information; In the process, the target driver’s audio and video information and physiological information during driving are collected, and data related to fatigue detection in the audio and video information and physiological information are extracted to obtain fatigue detection data; facial video information, overall torso video information and audio information; analyze the current state of the target driver according to the fatigue detection data and historical fatigue detection data, and obtain the local fatigue state; calculate the comprehensive fatigue of the target driver according to the local fatigue state and the current continuous driving time of the target driver state and perform a safety evaluation according to the mapping relationship, and perform an anti-fatigue driving warning operation on the target driver according to the level of the safety evaluation.

Description

technical field [0001] The invention relates to the field of video image processing and pattern recognition, in particular to an audio-video-based fatigue state detection method and device. Background technique [0002] Fatigue driving is especially common among professional drivers, especially long-distance passenger logistics drivers. Because the driver's sitting posture and movements are fixed and repeated for a long time, his physiological function and psychological state slowly change, resulting in distraction, drowsiness, narrowed vision, missed information, slow response and judgment, driving errors or complete loss of driving ability , resulting in serious traffic accidents such as collision and rushing off the road. If the early warning can be 2 seconds in advance, 92% of traffic accidents will be reduced, and 0.5 seconds in advance, 73% of traffic accidents will be avoided. Therefore, an efficient and rapid early warning system can save tens of thousands of lives...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/59G06V40/70G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 陶建华肖明远刘斌连政
Owner INST OF AUTOMATION CHINESE ACAD OF SCI