THRawS: A Novel Dataset for Thermal Hotspots Detection in Raw Sentinel-2
Data
- URL: http://arxiv.org/abs/2305.11891v1
- Date: Fri, 12 May 2023 09:54:21 GMT
- Title: THRawS: A Novel Dataset for Thermal Hotspots Detection in Raw Sentinel-2
Data
- Authors: Gabriele Meoni and Roberto Del Prete and Federico Serva and Alix De
Beussche and Olivier Colin and Nicolas Long\'ep\'e
- Abstract summary: THRawS is the first dataset composed of Sentinel-2 (S-2) raw data containing warm temperature hotspots.
To foster the realisation of robust AI architectures, the dataset gathers data from all over the globe.
- Score: 4.077787659104315
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Nowadays, most of the datasets leveraging space-borne Earth Observation (EO)
data are based on high-end levels products, which are ortho-rectified,
coregistered, calibrated, and further processed to mitigate the impact of noise
and distortions. Nevertheless, given the growing interest to apply Artificial
Intelligence (AI) onboard satellites for time-critical applications, such as
natural disaster response, providing raw satellite images could be useful to
foster the research on energy-efficient pre-processing algorithms and AI models
for onboard-satellite applications. In this framework, we present THRawS, the
first dataset composed of Sentinel-2 (S-2) raw data containing warm temperature
hotspots (wildfires and volcanic eruptions). To foster the realisation of
robust AI architectures, the dataset gathers data from all over the globe.
Furthermore, we designed a custom methodology to identify events in raw data
starting from the corresponding Level-1C (L1C) products. Indeed, given the
availability of state-of-the-art algorithms for thermal anomalies detection on
the L1C tiles, we detect such events on these latter and we then re-project
them on the corresponding raw images. Additionally, to deal with unprocessed
data, we devise a lightweight coarse coregisteration and georeferencing
strategy. The developed dataset is comprehensive of more than 100 samples
containing wildfires, volcanic eruptions, and event-free volcanic areas to
enable both warm-events detection and general classification applications.
Finally, we compare performances between the proposed coarse spatial
coregistration technique and the SuperGlue Deep Neural Network method to
highlight the different constraints in terms of timing and quality of spatial
registration to minimise the spatial displacement error for a specific scene.
Related papers
- Hierarchical Features Matter: A Deep Exploration of GAN Priors for Improved Dataset Distillation [51.44054828384487]
We propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD)
This method systematically explores hierarchical layers within the generative adversarial networks (GANs)
In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation.
arXiv Detail & Related papers (2024-06-09T09:15:54Z) - Rapid Wildfire Hotspot Detection Using Self-Supervised Learning on Temporal Remote Sensing Data [0.12289361708127873]
Leveraging remote sensed data from satellite networks and advanced AI models to automatically detect hotspots is an effective way to build wildfire monitoring systems.
We propose a novel dataset containing time series of remotely sensed data related to European fire events and a Self-Supervised Learning (SSL)-based model able to analyse multi-temporal data and identify hotspots in potentially near real time.
We train and evaluate the performance of our model using our dataset and Thraws, a dataset of thermal anomalies including several fire events, obtaining an F1 score of 63.58.
arXiv Detail & Related papers (2024-05-30T14:31:46Z) - SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised
Learning for Robust Infrared Small Target Detection [53.19618419772467]
Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds.
With the development of Transformer, the scale of SIRST models is constantly increasing.
With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
arXiv Detail & Related papers (2024-03-08T16:14:54Z) - FLOGA: A machine learning ready dataset, a benchmark and a novel deep
learning model for burnt area mapping with Sentinel-2 [41.28284355136163]
Wildfires pose significant threats to human and animal lives, ecosystems, and socio-economic stability.
In this work, we create and introduce a machine-learning ready dataset we name FLOGA (Forest wiLdfire Observations for the Greek Area)
This dataset is unique as it comprises of satellite imagery acquired before and after a wildfire event.
We use FLOGA to provide a thorough comparison of multiple Machine Learning and Deep Learning algorithms for the automatic extraction of burnt areas.
arXiv Detail & Related papers (2023-11-06T18:42:05Z) - Multimodal Dataset from Harsh Sub-Terranean Environment with Aerosol
Particles for Frontier Exploration [55.41644538483948]
This paper introduces a multimodal dataset from the harsh and unstructured underground environment with aerosol particles.
It contains synchronized raw data measurements from all onboard sensors in Robot Operating System (ROS) format.
The focus of this paper is not only to capture both temporal and spatial data diversities but also to present the impact of harsh conditions on captured data.
arXiv Detail & Related papers (2023-04-27T20:21:18Z) - Minimizing the Accumulated Trajectory Error to Improve Dataset
Distillation [151.70234052015948]
We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory.
We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory.
Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
arXiv Detail & Related papers (2022-11-20T15:49:11Z) - A Multi-purpose Real Haze Benchmark with Quantifiable Haze Levels and
Ground Truth [61.90504318229845]
This paper introduces the first paired real image benchmark dataset with hazy and haze-free images, and in-situ haze density measurements.
This dataset was produced in a controlled environment with professional smoke generating machines that covered the entire scene.
A subset of this dataset has been used for the Object Detection in Haze Track of CVPR UG2 2022 challenge.
arXiv Detail & Related papers (2022-06-13T19:14:06Z) - Self-supervised Contrastive Learning for Volcanic Unrest Detection [4.152165675786138]
Ground deformation measured from Interferometric Synthetic Aperture Radar (InSAR) data is considered a sign of volcanic unrest.
Recent studies have shown the potential of using Sentinel-1 InSAR data and supervised deep learning (DL) methods for the detection of volcanic deformation signals.
This letter proposes the use of self-supervised contrastive learning to learn quality visual representations hidden in unlabeled InSAR data.
arXiv Detail & Related papers (2022-02-08T17:54:51Z) - CELESTIAL: Classification Enabled via Labelless Embeddings with
Self-supervised Telescope Image Analysis Learning [0.34998703934432673]
We establish CELESTIAL-a self-supervised learning pipeline for effectively leveraging sparsely-labeled satellite imagery.
This pipeline successfully adapts SimCLR, an algorithm that first learns image representations on unlabelled data and then fine-tunes this knowledge on the provided labels.
Our results show CELESTIAL requires only a third of the labels that the supervised method needs to attain the same accuracy on an experimental dataset.
arXiv Detail & Related papers (2022-01-20T04:59:05Z) - Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using
Meta-Learning [64.92447072894055]
Infrared (IR) cameras are robust under adverse illumination and lighting conditions.
We propose an algorithm meta-learning framework to improve existing UDA methods.
We produce a state-of-the-art thermal detector for the KAIST and DSIAC datasets.
arXiv Detail & Related papers (2021-10-07T02:28:18Z) - SpaceNet 6: Multi-Sensor All Weather Mapping Dataset [13.715388432549373]
We present an open Multi-Sensor All Weather Mapping (MSAW) dataset and challenge.
MSAW covers 120 km2 over multiple overlapping collects and is annotated with over 48,000 unique building footprints labels.
We present a baseline and benchmark for building footprint extraction with SAR data and find that state-of-the-art segmentation models pre-trained on optical data, and then trained on SAR.
arXiv Detail & Related papers (2020-04-14T13:43:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.