A method for detecting fatigue driving based on face features

A face feature, fatigue driving technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of unsatisfactory detection effect and low accuracy without considering the driver wearing glasses, and achieve accuracy High, improve accuracy, reduce the effect of misjudgment probability

Inactive Publication Date: 2019-03-01
HARBIN UNIV OF SCI & TECH
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods can achieve a certain detection effect, most of them do not take into account the situation that the driver wears glasses, and generally only detect and identify a single part of the eyes or mouth, especially the

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
  • A method for detecting fatigue driving based on face features
  • A method for detecting fatigue driving based on face features
  • A method for detecting fatigue driving based on face features

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0051] Embodiment 1: The method for detecting fatigued driving based on facial features in this embodiment is performed according to the following steps:

[0052] 1. Image collection;

[0053] 2. Image processing: use the adaptive median filtering method to denoise the collected images, and use the adaptive threshold method to equalize the illumination of the collected images;

[0054] 3. Face localization based on the improved Adboost algorithm classifier; in which, only when the weight of the sample is smaller than the update threshold at this time, and the sample is classified incorrectly, the weight will be adjusted accordingly. weight; in addition, the weight will be reduced;

[0055] 4. Go to the next step if a face is detected, go to step one if no face is detected;

[0056] 5. Face Feature Recognition

[0057] 5.1 Human eye positioning: The Gaboreye model combines the radial symmetry algorithm to locate the position of the eyes;

[0058] 5.2 Discrimination of human...

Example Embodiment

[0069] Embodiment 2: The difference between this embodiment and Embodiment 1 is that: in step 2, the adaptive median filtering method adopts a 3×3 median filtering template, δ=0.8, the Gaussian template of and The mean filter template of . Other steps and parameters are the same as in the first embodiment.

Example Embodiment

[0070] Embodiment 3: The difference between this embodiment and Embodiment 1 is that the minimum window of the adaptive median filtering method in step 2 is 3, and the maximum window is 19. Other steps and parameters are the same as in the first embodiment.

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 method for detecting fatigue driving based on face features, and relates to a method for detecting fatigue driving through artificial intelligence. The fatigue state of the driver can be judged by jointly detecting the characteristics of the eyes and the mouth, and the problem that accurate detection cannot be carried out due to wearing of glasses is avoided. The detection method comprises the steps of 1, image acquisition; 2, image processing; 3, carrying out face positioning based on an improved Adaboost algorithm classifier; 4, carrying out the next step when the human face is detected, and carrying out the step 1 when the human face is not detected; 5, face feature recognition; 6, determining a fatigue state;. Compared with a traditional monitoring method, themethod has the advantages that the eye and mouth states are combined for fatigue state feature extraction, the judgment accuracy is improved, and the misjudgment probability of fatigue driving detection is reduced.

Description

technical field [0001] The invention relates to a method for artificial intelligence detecting fatigue driving. Background technique [0002] Traffic safety is an important issue facing the world at present. Relevant studies have shown that traffic accidents account for the largest proportion of human unnatural deaths. Many people have lost their precious lives as a result, and have brought great economic losses to the country. negative impact. In order to solve a series of problems caused by fatigue driving, with the efforts of many experts and scholars at home and abroad, many novel and effective methods have emerged. Today, fatigue detection algorithms can basically be divided into two categories, objective and subjective. In terms of subjective aspects, most of the real-time status is judged by the driver's own feeling or observation by others. However, due to differences in personal physique and carefulness of observation, there is no uniform standard and the accuracy...

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): G06K9/00
CPCG06V20/597
Inventor 兰朝凤毛秀欢刘春东赵宏运刘岩
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap