BenchCloudVision: A Benchmark Analysis of Deep Learning Approaches for Cloud Detection and Segmentation in Remote Sensing Imagery (2024-02-21T00:00:00.000000Z)

TL;DR

This research tries to produce machine learning algorithms that can perform cloud segmentation using only a few spectral bands, including RGB and RGBN-IR combinations, including RGB and RGBN-IR combinations.

Abstract

Satellites equipped with optical sensors capture high-resolution imagery, providing valuable insights into various environmental phenomena. In recent years, there has been a surge of research focused on addressing some challenges in remote sensing, ranging from water detection in diverse landscapes to the segmentation of mountainous and terrains. Ongoing investigations goals to enhance the precision and efficiency of satellite imagery analysis. Especially, there is a growing emphasis on developing methodologies for accurate water body detection, snow and clouds, important for environmental monitoring, resource management, and disaster response. Within this context, this paper focus on the cloud segmentation from remote sensing imagery. Accurate remote sensing data analysis can be challenging due to the presence of clouds in optical sensor-based applications. The quality of resulting products such as applications and research is directly impacted by cloud detection, which plays a key role in the remote sensing data processing pipeline. This paper examines seven cutting-edge semantic segmentation and detection algorithms applied to clouds identification, conducting a benchmark analysis to evaluate their architectural approaches and identify the most performing ones. To increase the model's adaptability, critical elements including the type of imagery and the amount of spectral bands used during training are analyzed. Additionally, this research tries to produce machine learning algorithms that can perform cloud segmentation using only a few spectral bands, including RGB and RGBN-IR combinations. The model's flexibility for a variety of applications and user scenarios is assessed by using imagery from Sentinel-2 and Landsat-8 as datasets. This benchmark can be reproduced using the material from this github link: https://github.com/toelt-llc/cloud_segmentation_comparative.

References43 items

A YOLO-NL object detector for real-time detection

Robust clinical applicable CNN and U-Net based algorithm for MRI classification and segmentation for brain tumor

Real-time object detection and segmentation technology: an analysis of the YOLO algorithm

Real-Time Flying Object Detection with YOLOv8

A survey on recent trends in deep learning for nucleus segmentation from histopathology images

Semantic segmentation of clouds in satellite images based on U-Net++ architecture and attention mechanism

Towards a guideline for evaluation metrics in medical image segmentation

E-Res U-Net: An improved U-Net model for segmentation of muscle images

Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art

Atrous Convolutions and Residual GRU Based Architecture for Matching Power Demand with Supply

CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images

Pooling Methods in Deep Neural Networks, a Review

A cloud detection algorithm for satellite imagery based on deep learning

Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery

A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation

On the Convergence of Adam and Beyond

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Rethinking Atrous Convolution for Semantic Image Segmentation

Cloud detection algorithm comparison and validation for operational Landsat data products

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns

DSSD : Deconvolutional Single Shot Detector

Beyond Skip Connections: Top-Down Modulation for Object Detection

Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation

Feature Pyramid Networks for Object Detection

Densely Connected Convolutional Networks

The Importance of Skip Connections in Biomedical Image Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections

Learning to Refine Object Segments

U-Net: Convolutional Networks for Biomedical Image Segmentation

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Object-based cloud and cloud shadow detection in Landsat imagery

Rectified Linear Units Improve Restricted Boltzmann Machines

A Theoretical Analysis of Feature Pooling in Visual Recognition

Statistical validation of image segmentation quality based on a spatial overlap index.

The use of the area under the ROC curve in the evaluation of machine learning algorithms

Dual-Branch Network for Cloud and Cloud Shadow Segmentation

A Method for Stochastic Optimization

Deep convolutional symmetric encoder—decoder neural networks to predict students’ visual attention

Sentinel-2 global-scale