https://github.com/aritrosaha10/blindspotdetection

A camera-based solution for checking a blind spot programmatically using machine learning.
https://github.com/aritrosaha10/blindspotdetection

camera jupyter-notebook machine-learning python raspberry-pi raspberry-pi-4 rpi rpi4 tensorflow

Last synced: about 2 months ago
JSON representation

A camera-based solution for checking a blind spot programmatically using machine learning.

• Host: GitHub
• URL: https://github.com/aritrosaha10/blindspotdetection
• Owner: AritroSaha10
• License: gpl-3.0
• Created: 2021-06-03T18:56:22.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-04-25T15:54:32.000Z (8 months ago)
• Last Synced: 2024-04-25T17:00:29.025Z (8 months ago)
• Topics: camera, jupyter-notebook, machine-learning, python, raspberry-pi, raspberry-pi-4, rpi, rpi4, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 10.2 MB
• Stars: 8
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Blind Spot Detection using Machine Learning

A lightweight camera-based solution for checking a blind spot programmatically using TensorFlow and Python on a Raspberry Pi. 

## Repository Contents

This repository contains multiple elements of the project. These elements include:

- Jupyter Notebook going into how the model was made

- The trained model

- Python program that uses the model on two cameras

## Model Info

Using transfer learning on MobileNetV2, an accuracy of ~98% was reached for blind spot detection with an average prediction time of 0.09s on the Raspberry Pi 4 without any machine learning accelerators. Given an ML accelerator such as the [Google Coral USB Accelerator](https://coral.ai/products/accelerator/), it would likely reach prediction times of 0.0026s (2.6ms, [source](https://coral.ai/docs/edgetpu/benchmarks/)).

## Demo Video

Want to skip straight into the details? Check out [this video](https://youtu.be/gVqHdGIRrTY) demoing the machine learning algorithm.

[![Demo Video](https://i.imgur.com/ZLRfkQ5.png)](https://youtu.be/gVqHdGIRrTY)

## License

This project is under the GNU General Public License, version 3. More info is available in [LICENSE](/LICENSE)