With the advancements in AI and the development of computing capabilities in the 21st century, millions of processes around the globe are being automated like never before. The automobile industry is transforming, and the day isn't far when fully autonomous vehicles would make transportation extremely inexpensive and effective. But to reach this ambitious goal, which aims to change the very foundations of transportation as an industry, we need to first solve a few challenging problems which will help a vehicle make decisions by itself. Problem of Traffic Sign Recognition is one such problem and solving it would take us one step closer to L5 autonomy.
In this task, we had to create a web app for training, visualizing and evaluating any neural network. This model is scalable, user-friendly and tranparent in it's funcitoning.
You can see the whole Problem statement here
The contingent won Bronze Medal 🥉 in the Bosch Traffic Sign Recognition Problem Statement in Inter IIT Tech Meet 9.0 while IIT Bombay won Silver Medal 🥈 in the Tech Meet overall.
This project was generated with Angular CLI version 9.1.1.
Read the flow of code here
We need Node v14.5.0. To install it, follow the installation instructions here. Make sure you use 14.x instead of 10.x
npm install -g @angular/cli to install angular CLI.
Navigate to traffic-sign-recognition directory and run npm install. This will install required dependencies specific to the project.
Navigate to traffic-sign-recognition/backend folder and run pip install -r requirements.txt
- Navigate to traffic-sign-recognition/backend and run
python3 manage.py migrate. - Run
python3 manage.py runserver - Proceed to running frontend
- Navigate to traffic-sign-recognition directory and run
ng serve - Navigate to
localhost:4200on your browser to view the webpage.
Run ng serve for a dev server. Navigate to http://localhost:4200/. The app will automatically reload if you change any of the source files.
Run ng generate component component-name to generate a new component. You can also use ng generate directive|pipe|service|class|guard|interface|enum|module.
Run ng build to build the project. The build artifacts will be stored in the dist/ directory. Use the --prod flag for a production build.
Run ng test to execute the unit tests via Karma.
Run ng e2e to execute the end-to-end tests via Protractor.
To get more help on the Angular CLI use ng help or go check out the Angular CLI README.
Download the dataset from the official site INI and convert all .ppm images to .png images
Else, download the dataset from here: Kaggle link (already converted to .png)
Place the downloaded dataset in backend/Data/Train folder
Thanks goes to these wonderful people (emoji key):
 Pranav Deo 📆 🤔 🖋 🎨 |
 Gurnoor Singh Khurana 💻 📖 |
 Jayesh Singla 💻 |
 Anuj Agrawal 💻 🧑🏫 |
 Mitali Meratwal 💻 📖 |
 Omkar Ghugarkar 💻 🔣 |
 Atharva Diwan 💻 🔣 |
 Nihal Barde 💻 🧑🏫 |
 Gagan Jain 💻 🤔 |
This project follows the all-contributors specification. Contributions of any kind welcome!
Special thanks to Anirudh Mittal, General Secretary - Technical Affairs, IIT Bombay (2020-21), and Aryan Agal and Manthan Dhisale as the Contingent Leaders of the IIT Bombay Contingent, Bombay76, for the 9th Inter-IIT Tech Meet.