RouteAble Python Machine Learning Backend

RouteAble is a map-based application that uses crowd-sourced data to help disabled people determine accessible areas. Our technology uses ML for image similarities and tag generation, blockchain to incentivize users, and React Native for hosting on Android and iOS devices. We hope to promote a more inclusive space by helping users upload, share, and idenitfy areas with stairs, ramps, asphalt roads, concrete roads, and guard rails.

This repo is a proxy to access python ML functions via our main nest js backend.
Explore the docs »

View Demo · Report Bugs

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Contributing
5. License
6. Contact

About The Project

We were inspired by fellow UMass Amherst students who identified the lack of accessibility here on campus including dangerous ramps, hidden entrances, and unsafe roads. Students have the option to wait for "Classroom Access Assistants" and Accessible Van Services provided by the university, which are not always the most consistent and can cause frustration. Our application ensures that disabled people know ahead of time which buildings have accessible entrances and where they are using other user's images. Using machine learning, we identified exact matches between images above a certain threshold and automatically generate tags for our users. For quality control, we additionally have an edit tag function to manually edit generated tags. We also identified the challenge of incentivizing users. Hence, we developed a cryptocurrency wallet that allows users to collect tokens if their image is unique enough.

(back to top)

Built With

• TensorFlow
• PyTorch
• FastAPI

(back to top)

Getting Started

Instructions on setting up our project locally. To get a local copy up and running follow these simple example steps.

Setup

Download the weights for object detection

https://drive.google.com/file/d/1a-cHfvOgHT_W8empBxhk9NvY-7g71Q4p/view?usp=sharing

put it in root directory of main.py

start the server using uvicorn

uvicorn main:app --workers 1 --host 0.0.0.0 --port 5000

Docker start

• make sure you have gpu at index 0 available
• make sure weights are downloaded
• make sure docker installed
• start as such

docker compose up -d

Prerequisites

This is an example of how to list things you need to use the software and how to install them.

• npm

  npm install npm@latest -g

Installation

1. Get a free API Key at https://mapsplatform.google.com/
2. Clone the repos individually

   git clone [https://github.com/github_username/repo_name.git](https://github.com/RouteAble)

3. Install NPM packages

   npm install

4. Enter your API in config.js

   const API_KEY = 'ENTER YOUR API';

(back to top)

Usage

• server starts at http://localhost:5000
• endpoint 1: /sim
  • given image checks similarity using ML
    • returns a similarity score double from 0 to 1 inclusive
  • post endpoint
  • encoding must be
    • jpeg
    • png
    • jpg
  • body:

    {
        "image": <insert base64 string>;
    }
    

  • returns
    • on sucess:

      {
          "similarity_score": string;
      }
      

    • on error:

      {
          "message": <some error message>;
      }
      

• endpoint 2: /detection
  • given image checks if stairs, ramps, and guard rails are present
  • post endpoint
  • encoding must be
    • jpeg
    • png
    • jpg
  • body:

    {
        "image": <insert base64 string>
    }
    

  • returns
    • on sucess:

      {
          "stairs": boolean;
          "ramps": boolean;
          "guard_rails": boolean;
      }
      

    • on error:

      {
          "message": <some error message>;
      }
      

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Contact

Divyansh Shivashok - [email protected]
Shishir Pai - [email protected]
Ayush Ravi Chandran - [email protected]
Zara Nip - [email protected]

Project Link: https://github.com/RouteAble

(back to top)