Method and device for recognizing distractions and dangerous driving behaviors of a driver and storage medium

A technology for dangerous driving and recognition methods, applied in neural learning methods, character and pattern recognition, acquisition/recognition of facial features, etc., can solve driver micro-expression recognition, single sensor mode and position, driver monitoring system recognition accuracy Poor problems, to achieve the effect of reducing traffic accidents, strong generalization and robustness, and improving recognition accuracy

Inactive Publication Date: 2020-12-01
青岛慕容信息科技有限公司
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problems described in the prior art, it is also necessary to solve the problems of insufficient training samples, fewer information patterns used by algorithms, single sensor patterns and positions, false positives in the process of distraction detection and judgment,

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 recognizing distractions and dangerous driving behaviors of a driver and storage medium
  • Method and device for recognizing distractions and dangerous driving behaviors of a driver and storage medium
  • Method and device for recognizing distractions and dangerous driving behaviors of a driver and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Below in conjunction with accompanying drawing, the present invention is further described:

[0051] The present invention provides 1. A method for identifying driver distraction and dangerous driving behavior, characterized in that: the method includes a combination of figure 1 , the specific method includes the following steps:

[0052] Step S1: Obtain RGB images and near-infrared images from multiple angles through the visible light camera and binocular infrared camera installed above the cockpit center console, below the rearview mirror and on the left A-pillar, and convert the acquired image data Perform scaling and data enhancement, and then perform normalization, and use the processed data as the input data of the system algorithm model. When normalizing the image, follow the formula below:

[0053]

[0054] Among them, I and I' represent the original image and the normalized image respectively, μ represents the mean value of all pixels in the image, and σ re...

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 and device for recognizing distractions and dangerous driving behaviors of a driver and a storage medium, and aims to solve the problems that the distractions and dangerous actions of the driver are low in recognition accuracy in the driving process, and early warning cannot be performed in time after recognition. The method mainly comprises the following steps: S1,acquiring image information of a driver; S2, detecting the driving behavior of the driver according to the image obtained in the S1, and judging whether a defined dangerous driving behavior occurs ornot; S3, performing face detection on the image obtained in the step S1; S4, carrying out key point positioning, micro-expression recognition and sight line estimation according to the face area provided in the S3; and S5, judging whether the driver has distractions and dangerous driving behaviors or not according to the information obtained in the S4 and the S2. According to the method, the driving behavior of the driver can be detected in real time in a non-contact mode, the method is easy to implement and high in recognition accuracy, the method can be widely applied to the fields of intelligent driving and the like, and the safety and reliability of the driving behavior are improved.

Description

technical field [0001] The present invention relates to the field of automobile technology and the field of image processing technology, in particular to a method, device and storage medium for identifying driver distraction and dangerous driving behavior. Background technique [0002] With the development of social economy, automobiles have become an indispensable tool for people to travel, but the traffic accidents that follow have become a challenge that must be faced for people's lives and property safety. According to statistics, most of the existing traffic accidents are caused by improper operation, in which the driver's distraction, bad mood and unsafe driving operation in the driving process are the main causes of traffic accidents. For example, the driver's operations such as answering and calling mobile phones during driving will seriously interfere with the driver's attention, so that he cannot concentrate on observing the road conditions ahead and around him. On...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/174G06V40/161G06V40/172G06V20/597G06N3/045
Inventor 王秀政
Owner 青岛慕容信息科技有限公司
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