Skip to content

tanishq20/Live-i

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

48 Commits
 
 
 
 
 
 

Repository files navigation

License: MIT Maintenance Ask Me Anything ! GitHub forks GitHub stars GitHub issues Open Source Love svg1

HackX'21 SPS VIT

Live-i

TEAM HASH

Domain Name

Voice and Image Processing

Problem Statement

According to the most recent published World Health Organization (WHO) report, it was estimated that nearly 1.25 million people were killed on the roads worldwide, making road traffic injuries a leading cause of death globally. Distracted driving is a serious and growing threat to road safety. Collisions caused by distracted/inattentive driving have captured the attention of the US Government and professional medical organizations during the last years. They have estimated that distraction and inattention account for somewhere between 25% and 75% of all or near crashes.

Abstract

Driver distraction, defined as the diversion of attention away from activities-critical for safe driving, is increasingly recognized as a significant source of injuries and fatalities on the roadway. With an aim to minimize accidents due to distraction, we have developed this live-i which would beep anytime the system detected that the driver had crossed the threshold for unsafe driving. Activities such as looking away, using electronics, improper grip of steering, drowsiness are detectable using this device. Developed as a software/hardware design that could be retrofitted to any vehicle and uses only camera input to alert drivers at times when they are too distracted.

Functionalities

Detects

  • Using electronics like texting, being on a call or operating the radio
  • Improper grip of steering
  • Drowsiness
  • Looking away for too long
  • Eating,Drinking etc.
  • Talking to the passenger
  • Reaching behind

Tech Stack

  • Computer Vision:
    • Mediapipe
    • OpenCv
    • Python
  • Web:
    • HTML
    • CSS
    • JAVASCRIPT
    • BOOTSTRAP
    • FLASK

Methodology & Algorithms

  • CNN
  • YOLO
  • MobileNet Model

Accuracy & Graphs

  • Mobile Net Accuracy
    • 89.99%
    • alt text
  • Epoch Accuracy alt text
  • Epoch Loss alt text
https://bit.ly/ppt-link

Website Interface

alt text alt text alt text alt text

Team HASH

Naman Garg

Naman Garg

Mudit Jindal

Mudit Jindal

Tanishq Kumar

Breenda Das

Amisha Jaiswal

Amisha Jaiswal

Dhanya Sri Aravapalli

Dhanya Sri Aravapalli

Made with ❤️ by Team HASH