# MTCNN_CNN_DangerDrivingDetection

**Repository Path**: halfskywalker/MTCNN_CNN_DangerDrivingDetection

## Basic Information

- **Project Name**: MTCNN_CNN_DangerDrivingDetection
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-12-03
- **Last Updated**: 2024-12-11

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

本项目是用于判断是否闭眼或者张开嘴哈欠和吸烟打电话等手势行为，
功能涵盖7类情绪识别，眨眼判断，哈欠判断，吸烟，打电话等，
达到危险驾驶检测的功能。
项目描述可以看https://blog.csdn.net/Aristochi/article/details/105655810
有问题可以私信
```
The project was designed to determine gestures such as closing eyes or yawning and smoking or talking on the phone.
The functions cover 7 categories of emotion recognition, blinking judgment, yawning judgment, smoking, telephone, etc. to achieve the function of dangerous driving detection.
```

数据集：闭眼、睁眼、闭嘴、哈欠、打电话、吸烟数据集
        口罩数据集
        fer2013表情数据集

Data set: closed eyes, open eyes, yawn, telephone, smoking data set
Mask data set
Fer2013 Emoji Data Set
```
眨眼数据集http://parnec.nuaa.edu.cn/xtan/data/ClosedEyeDatabases.html
数据集
链接：https://pan.baidu.com/s/1FLfWZix-vsY5XSaV1oi-pA
提取码：pmh0
```
Done:
眨眼判断
哈欠判断
打电话识别
吸烟识别
预测准确率：93.46%

Done:
Blink of an eye to judge
Yawn judgment
Telephone identification
Smoking is to identify
Prediction accuracy: 93.46%
```
TODO：
PERCLOS疲劳指标判断
将项目移植到树莓派
TODO:
PERCLOS fatigue index judgment
Port the project to raspberry pie
Thanks for https://github.com/ipazc/mtcnn/tree/master/mtcnn MTCNN module
感谢https://github.com/ipazc/mtcnn/tree/master/mtcnn的MTCNN模块
```
如果有问题可以发邮箱aristochi@qq.com。