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

Fatigue driving automatic detection method and device

An automatic detection and fatigue driving technology, applied in the field of artificial intelligence, can solve problems such as model redundancy and slow algorithm detection speed

Pending Publication Date: 2021-10-08
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a fatigue driving automatic detection method and device based on SSD algorithm, which has solved the problems of too slow algorithm detection speed and model redundancy in existing devices

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
  • Fatigue driving automatic detection method and device
  • Fatigue driving automatic detection method and device
  • Fatigue driving automatic detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The overall design of the software system and hardware implementation is as follows: figure 2 shown, which includes the following steps:

[0018] Step 1: Configure the Anaconda version as Anaconda3 and the python version as 3.8.5 on the PC. Pytorch version torch-1.7.0 and other required installation packages.

[0019] Step 2: Preprocess the training set of images of faces of drivers during driving.

[0020] Step 3: Input the processed dataset into the modified VGG16 neural network model.

[0021] Step 4: After multiple convolutions, obtain feature layers of different pixel scales and perform corresponding pooling processing to obtain effective feature layers of different pixel sizes.

[0022] Step 5: Set prior prediction frames of different scales on each pixel of each effective feature layer according to formula 1, and perform two convolutions on each effective feature layer to adjust the prior frame to obtain the prediction frame .

[0023] Step 6: Sorting and n...

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 fatigue driving automatic detection method and device. The fatigue driving automatic detection method and device belong to the field of artificial intelligence application. The fatigue driving automatic detection method comprises two parts, namely the training of a fatigue driving target detection model and hardware deployment of the model. The training of the model comprises the following steps of: performing training by using a training set image of a face of a driver during driving and using an algorithm model improved based on a deep learning SSD model, and obtaining a target position and a corresponding category on feature maps of different scales by using a direct regression mode; and combining the obtained results through methods such as non-maximum suppression to generate a final target detection classification result. In the aspect of the hardware implementation, the method is operated on a Raspberry Pi 3b + platform, the waking / fatigue state of the driver is displayed in real time through a display screen, and data are uploaded and stored in a remote server database. The invention mainly aims to improve the accuracy of a fatigue driving detection system and make the deployment of a fatigue driving device lighter.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and relates to a target detection-facial fatigue state judgment and positioning technology and its realization on a mobile hardware platform. Background technique [0002] With the improvement of people's living standards, the number of cars is increasing year by year, and driving safety has become a hot topic that has attracted more and more attention. The on-board fatigue driving detection system has been paid more and more attention in the field of driving because it can monitor and detect the driving fatigue of drivers, prevent dangerous driving behaviors, and greatly reduce the risk of driving. [0003] The current fatigue driving detection system mainly consists of the following types: First, record the driver’s behavior on the steering wheel and pedals through physical sensors, and analyze the behavior to make a judgment. The logic of this method is simple and cannot adapt to the driv...

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): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08G07C5/00G07C5/08H04L29/08
CPCG06N3/08G07C5/0866G07C5/008H04L67/12H04L67/5683G06N3/045G06F18/214
Inventor 李春晓
Owner CHENGDU UNIVERSITY OF TECHNOLOGY