Semantic segmentation on multi-resolution optical and microwave data using deep learning

TL;DR

This paper demonstrates the effectiveness of deep learning models, specifically modified U-Net and VGG-UNet, in accurately classifying and detecting objects such as buildings, ships, and trees from high-resolution optical and microwave satellite imagery.

Contribution

The study introduces the application of modified U-Net and VGG-UNet models for multi-resolution satellite data classification and object detection, achieving over 95% accuracy.

Findings

Achieved over 95% accuracy in detecting buildings and ships from optical data.

Achieved over 96% accuracy in detecting ships and trees from microwave data.

Obtained multi-label classification IoU of better than 95%.

Abstract

Presently, deep learning and convolutional neural networks (CNNs) are widely used in the fields of image processing, image classification, object identification and many more. In this work, we implemented convolutional neural network based modified U-Net model and VGG-UNet model to automatically identify objects from satellite imagery captured using high resolution Indian remote sensing satellites and then to pixel wise classify satellite data into various classes. In this paper, Cartosat 2S (~1m spatial resolution) datasets were used and deep learning models were implemented to detect building shapes and ships from the test datasets with an accuracy of more than 95%. In another experiment, microwave data (varied resolution) from RISAT-1 was taken as an input and ships and trees were detected with an accuracy of >96% from these datasets. For the classification of images into multiple-classes, deep learning model was trained on multispectral Cartosat images. Model generated results were then tested using ground truth. Multi-label classification results were obtained with an accuracy (IoU) of better than 95%. Total six different problems were attempted using deep learning models and IoU accuracies in the range of 85% to 98% were achieved depending on the degree of complexity.