Supercharge Your Innovation With Domain-Expert AI Agents!

Driver abnormal posture detection method

A detection method and driver's technology, applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of high precision, high computing resource occupation, and high computing resource occupation

Active Publication Date: 2020-09-15
DALIAN UNIV OF TECH
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The problem to be solved by the present invention is to invent a method for detecting abnormal posture of a driver that can maintain high detection accuracy and save computing resources in view of the contradiction between high precision and high computing resource occupation in the existing driver monitoring system
That is, on the basis of the original global monitoring method, the abnormal driving posture judgment criterion is added as the basis for whether to enable the behavior classifier to solve the problem of excessive computing resources occupied by the global monitoring method; combined with the driving behavior classifier trained by the deep neural network to ensure higher detection accuracy

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
  • Driver abnormal posture detection method
  • Driver abnormal posture detection method
  • Driver abnormal posture detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The content of the present invention will be further described below in combination with specific embodiments and accompanying drawings.

[0054] As one of the important in-vehicle systems of automobiles, the advanced driving assistance system of automobiles plays a key role in ensuring the safety of occupants and preventing traffic accidents. Driver's driving posture monitoring, as an emerging function in advanced driver assistance systems, plays an important role in preventing traffic accidents. With the rapid development of computer vision technology in recent years, the recognition accuracy of the driver attitude monitoring system has been significantly improved, but it needs to occupy a lot of computing resources to achieve higher accuracy. The current driver monitoring system solutions are all global monitoring, that is, using a behavior classifier to continuously monitor the driver's driving posture throughout the driver's driving process. However, the vast majo...

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 invention discloses a driver abnormal posture detection method and belongs to the field of automobile advanced auxiliary driving systems. The driver abnormal posture detection method is used for preventing traffic accidents caused by abnormal postures of a driver in the driving process and comprises the steps that when the behavior postures of the driver are monitored, whether the driver is inthe abnormal driving posture or not is distinguished through an abnormal posture judgment criterion, and then whether a behavior classifier is started or not is determined according to the judgment result, wherein the abnormal driving posture comprises actions of making a call, drinking water, smoking, playing a mobile phone and leaving the steering wheel by one hand or two hands. Compared with amethod for monitoring driver behaviors by globally using a behavior classifier, the driver abnormal posture detection method has the advantage that more limited computing resources can be saved on the premise of ensuring the same detection precision.

Description

technical field [0001] The invention belongs to the technical field of advanced automobile driving assistance systems, and in particular relates to a method for detecting abnormal posture of a driver. Background technique [0002] With the rapid development of computer vision technology, many driver monitoring systems with superior performance have emerged in the automotive field. These driver monitoring systems can monitor all kinds of abnormal driving behaviors of drivers in the driving process and take real-time warnings to prevent traffic accidents. However, in real driving conditions, the driver will maintain the correct driving posture for a long time, and will only be in an abnormal posture for a short time. If the global classification detection is carried out throughout the entire driving section, it will undoubtedly occupy more limited computing resources and affect the normal operation of other on-board systems. Chinese patent application number CN109063586A, th...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/10G06V40/20G06V20/597G06N3/045G06F18/24765G06F18/23G06F18/24G06F18/214
Inventor 杨姝亓昌陈辉
Owner DALIAN UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More