Detectron2 FPN + PointRend Model for amazing Satellite Image Segmentation

Objective

Data Preparation for Modeling

Fig 1: Sample image with corresponding annotated RGB mask from the training dataset

Model understanding

Basic FPN Model

Fig 2: Feature Pyramid Network (FPN) mode process flow (Image Source [1])

PointRend Model

Points Selection Strategy

Fig 3: Point selection strategy demonstration (Image source [2])

Point-Wise Predictions

Combined Model (FPN + PointRend) Flow

Fig 4: PointRend model process flow (Image source [2])
Fig 5: PointRend model upsampling and point-wise prediction demo for 4*4 course prediction vector (Image source [2])

Results

Fig 6: Sample predictions from UNet and Detectron2 model. Per image left is the prediction from UNet model, the middle is original RGB image and right is the prediction from Detectron2 model

Summary

Reference

--

--

--

Affine is a provider of analytics solutions, working with global organizations solving their strategic and day to day business problems www.affineanalytics.com

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Unifying visual embeddings for visual search at Pinterest

The Ultimate Guide on Choosing the Right Neural Network Architecture For the Right Data

Deploying Your Machine Learning Model as a REST API Using Flask

NLP has arrived!!!

Why do Neural Networks Need an Activation Function?

How do computers see?

PCA : EigenValue & Vector Calculation

NVIDIA Deepstream Quickstart

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Affine

Affine

Affine is a provider of analytics solutions, working with global organizations solving their strategic and day to day business problems www.affineanalytics.com

More from Medium

Crop Monitoring using Satellite Imagery — Part I — An Introduction.

Figure that depicts Satellite Imagery

Area Monitoring: How to train a binary classifier for built-up areas

Detecting Agricultural Croplands from Sentinel-2 Satellite Imagery

Annotating Imagery at Scale with GeoVisual Search