Eyes-in-the-Sky: A Jupyter Notebook repository from VedPDubey

Eyes in the Sky

Team Skywalkers - NSAC 2021

-------------------------------------

Satellite and Drones for Urban Development
View Demo · Report Bug · Request Feature . Deployed Instance

About The Project

Land cover data documents how much of a region is covered by forests, wetlands, impervious surfaces, agriculture, and other land and water types. The different types of land cover can be managed or used quite differently. This can be determined by analyzing satellite and drone imagery and that is what we have done. We have created an accessible and robust website made using ReactJS that will perform land cover segmentation and classification from satellites and drones at the click of a button powered by powerful deep learning models served by FastAPI. We have also showed how drastically land cover changes have occurred due to environmental calamities such as thunderstorms and floods.

Tech Stack

Getting Started

To get a local copy up and running follow these simple steps.

Installation

Setting up the FastAPI local endpoint:
1. cd to the FastAPI server folder
```
cd
cd server/fastapidrone
```
2. Install prerequisite packages
```
activate your virtualenv
pip install -r requirements.txt
```
3. Run FastAPI server at a deployable localhost endpoint
```
python app.py
```
Setting up the web application :
1. Clone the repo
```
git clone https://github.com/Lucifer8729/NSAC-Team-Skywalkers-2021.git
```
2. cd to the Flask folder
```
cd client
```
3. Install dependencies and create React app
```
npm install
npm start
```

Application in Use

Salient Features

Implementing deep learning models to perform land cover segmentation and classification and serving them at an endpoint using FastAPI.
Annotating and segmenting out images of flood affected areas from satellite images.
Accessible, interactive and robust web application built on ReactJS and FastAPI.