Method for detecting fatigue driving around clock

A fatigue driving and detection method technology, applied in the field of computer vision and machine learning, can solve problems such as driver interference, achieve detection accuracy and speed improvement, improve accuracy, and have strong adaptability

Inactive Publication Date: 2013-08-28
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Previous fatigue detection methods are based on brain waves and electrocardiograms, and the sensors need to be worn on the driver's body, which interferes to a certain extent with the driver

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 for detecting fatigue driving around clock
  • Method for detecting fatigue driving around clock
  • Method for detecting fatigue driving around clock

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In this paper, Adaboost (Adaptive Boost) classifier, local binary mode LBP (Local Binary Pattern) feature, Haar-like feature, Gabor feature, Gaussian difference filter DOG, active appearance model AAM (Active Appearance Models), PERCOLS (percentage of eyelid closure over the pupil over time, the percentage of eyelid closure time in a specific time) are mature existing technologies in the field of computer vision and image processing, and will not be repeated here.

[0031] Realize the positioning and tracking of human eyes under complex lighting, and finally make a fatigue judgment, such as figure 1 shown, including the following steps:

[0032] Step 1. Create a human eye database:

[0033] This step is to prepare for the subsequent training of the human eye classifier. Since there is no ready-made human eye bank, we need to build it ourselves. Here, the standard human eye pictures are mainly intercepted from the face database. The positive samples include eyes under...

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 provides a method for detecting fatigue driving around the clock. A camera is used for acquiring a human face image to primarily position the eyes of a person; afterwards, a human eye image which is well processed by light is obtained through light preprocessing, then the human eye image is matched with a trained human eye template, and therefore the state of opening and closing of human eyes is acquired; at last, a driver is judged whether to be fatigue or not through a PERCLOS fatigue judging criterion. A light preprocessing method with the contrast ratio balanced is provided, variation of image light and dark areas is used, a convolution operation is conducted according to a convolution operation function and a Gaussian difference function, and therefore contrast ratio balance is achieved. Furthermore, the invention provides a human eye positioning method with multi-feature fusion. The advantages of various features are used, fused features can more effectively present a detected object, detecting is more accurate, and adaptability is stronger.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and machine learning, and relates to driver fatigue detection technology. technical background [0002] In 1998, the US Federal Highway Administration test confirmed that PERCLOS (percentage of human eye closure per unit time) is highly correlated with driver fatigue, and proposed a highly reliable fatigue driving detection method. Previous fatigue detection methods are based on brain waves and electrocardiograms, and the sensors need to be worn on the driver's body, which interferes to a certain extent with the driver. The vision-based fatigue driving detection method only needs to place the camera in the car and aim it at the driver's head, which is non-interfering to the driver and has low cost. [0003] In terms of key technologies such as face detection and human eye positioning, some technical solutions have been explored at home and abroad: [0004] 1. An identification method ba...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
Inventor 解梅熊池亮谢建锋毛河朱伟
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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