Repository files navigation

A Python and Flask based REST API that serves a Keras/TensorFlow Convolutional Neural Network (CNN) modeltrained to classify satellite image tiles into 17 different possible labels.This API currently interfaces with aReact and Leaflet front-end.

When the user clicks on an area selected on the map, a POST request, containing the center latitude/longitude coordinatefor the area selected, is sent to the REST API. The API then searches a PostgreSQL database for the file location of a satellite image tilecontaining the selected area. This image is then processed, in real time, through a Keras/TensorFlow ResNet50model. This model makes a multilabel classification over 17 different labels returning a score between 0 and 1 for each label.The resultant scores are filtered based on a cutoff value, and then returned as JSON to the front-end.

The model was trained using the publicdatasetfromPlanet that was part of their Kaggle competition in 2017.This dataset consisted of ~42,000 image tiles of the amazon rainforest, all labeled.The main labels that appear in the current implementation are defined as the following:

There are many more labels which can be foundhere.

AResNet architecture was chosen for the CNN due to it'sfast inference time, good accuracy and smaller model size. See thispaperfor a comparison on all of these traits for the most common CNN architectures.