Coder Social home page Coder Social logo

jingyibysutsoftware / yolov5-deepsort-driverdistracted-driving-behavior-detection Goto Github PK

View Code? Open in Web Editor NEW
462.0 5.0 94.0 245.16 MB

基于深度学习的驾驶员分心驾驶行为(疲劳+危险行为)预警系统使用YOLOv5+Deepsort实现驾驶员的危险驾驶行为的预警监测

License: GNU General Public License v3.0

Python 99.58% Dockerfile 0.42%
deepsort yolov5 playsound opencv object-detection tracker driver-behavior tired python deeplearning

yolov5-deepsort-driverdistracted-driving-behavior-detection's Introduction

人物专注性检测

项目快速预览

快速预览

1.0版本

在征得原作者的同意之后,进行了部分修改,得到V1.0版本

主要不同地方为:

1、疲劳检测中去掉了点头行为的检测,仅保留闭眼检测和打哈欠检测。

2、Yolov5的权重进行了重新训练,增加了训练轮次。

3、前端UI进行了修改,精简了部分功能。

项目介绍

该项目为人物专注性检测,分为两个检测部分,疲劳检测和分心行为检测。 疲劳检测部分,使用Dlib进行人脸关键点检测,然后通过计算眼睛和嘴巴的开合程度来判断是存在否闭眼或者打哈欠,并使用Perclos模型计算疲劳程度。 分心行为检测部分,使用Yolov5,检测是否存在玩手机、抽烟、喝水这三种行为。

使用方法

依赖:YoloV5、Dlib、PySide2

直接运行main.py,即可使用本程序,具体效果可以观看演示视频。

bilibili在线观看

各函数的信息,均在代码中写好了注释,如有疑问请联系[email protected]

致谢

十分感谢原作者的支持和帮助,本项目很大部分都基于源项目,项目所使用的数据集也由原作者提

供。

yolov5-deepsort-driverdistracted-driving-behavior-detection's People

Contributors

1647790440 avatar jingyibysutsoftware avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

yolov5-deepsort-driverdistracted-driving-behavior-detection's Issues

Nice code! But there was no DeepSORT invovled.

Guys, That is nice to see this code that experimentally demonstrated how the fatigue and some specific poses can be identified well. However, it seems that there was no DeepSORT code snippet in this project and it might not be helpful but makes it slower to run in light of the original purpose. I was wondering what is the FPS you measured when you are using YOLOv5 based on pytorch as it runs slightly slower than other formats of YOLOv5.

数据集

您好,非常感谢您的项目,我现在想做一些修改,请问能发一下数据集吗 邮箱 [email protected],非常感谢!

数据集

您好,非常感谢您提供的项目,我想做一些学习,请问能发一下数据集吗,十分感谢!邮箱 [email protected]

数据集

请问使用的是什么数据集?

训练自己的模型

请问如何用数据集训练自己的模型?代码里面没有找到训练的代码

YOLOv5改为YOLOv4操作

您好,
请问想将检测从YOLOv5改为YOLOv4,我需要替换那些文件
或是我可能会需要使用YOLOv4从头训练?

数据集问题

希望发一份数据集,感谢![email protected]
另外,希望提供以下requirements.txt,我这个环境有些问题,跑不了,单独yolov5可以运行。

跑不起来,不知道缺什么东西

Fusing layers...
Model Summary: 224 layers, 7062001 parameters, 0 gradients
Traceback (most recent call last):
File "d:\Downloads\Yolov5-deepsort-driverDistracted-driving-behavior-detection\main.py", line 11, in
import myframe
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\Lib\site-packages\shiboken2\files.dir\shibokensupport_feature_.py", line 142, in import
return original_import(name, *args, **kwargs)
File "d:\Downloads\Yolov5-deepsort-driverDistracted-driving-behavior-detection\myframe.py", line 5, in
import myfatigue #疲劳检测
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\Lib\site-packages\shiboken2\files.dir\shibokensupport_feature
.py", line 142, in import
return original_import(name, *args, **kwargs)
File "d:\Downloads\Yolov5-deepsort-driverDistracted-driving-behavior-detection\myfatigue.py", line 4, in
from imutils.video import FileVideoStream
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\Lib\site-packages\shiboken2\files.dir\shibokensupport_feature
.py", line 142, in _import
return original_import(name, *args, **kwargs)
ModuleNotFoundError: No module named 'imutils'
PS D:\Downloads\Yolov5-deepsort-driverDistracted-driving-behavior-detection>

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.