BREIZHCROPS: A TIME SERIES DATASET FOR CROP TYPE MAPPING

@article{Ruwurm2019BREIZHCROPSAT,
  title={BREIZHCROPS: A TIME SERIES DATASET FOR CROP TYPE MAPPING},
  author={Marc Ru{\ss}wurm and Charlotte Pelletier and Maximilian Zollner and S{\'e}bastien Lef{\`e}vre and Marco Korner},
  journal={arXiv: Learning},
  year={2019}
}
We present Breizhcrops, a novel benchmark dataset for the supervised classification of field crops from satellite time series. We aggregated label data and Sentinel-2 top-of-atmosphere as well as bottom-of-atmosphere time series in the region of Brittany (Breizh in local language), north-east France. We compare seven recently proposed deep neural networks along with a Random Forest baseline. The dataset, model (re-)implementations and pre-trained model weights are available at the associated… Expand
EuroCrops: A Pan-European Dataset for Time Series Crop Type Classification
TLDR
EUROCROPS is presented, a dataset based on self-declared field annotations for training and evaluating methods for crop type classification and mapping, together with its process of acquisition and harmonisation, and a new taxonomy scheme, HCAT-ID, that aspires to capture all the aspects of reference data originating from administrative and agency databases. Expand
TimeSen2Crop: A Million Labeled Samples Dataset of Sentinel 2 Image Time Series for Crop-Type Classification
TLDR
TimeSen2Crop, a pixel-based dataset made up of more than 1 million samples of Sentinel 2 time series associated to 16 crop types, is presented along with a benchmark comparison of deep learning models for crop type mapping. Expand
A Discriminative Long Short Term Memory Network with Metric Learning Applied to Multispectral Time Series Classification
TLDR
This article proposes an end-to-end deep network for the classification of multi-spectral time series and apply them to crop type mapping that minimizes classification error, but enforces the sub-networks to produce more discriminative deep features. Expand
Learning to predict crop type from heterogeneous sparse labels using meta-learning
TLDR
This work investigates the utility of model-agnostic meta-learning (MAML) to learn from diverse global datasets and improve performance in data-sparse regions and finds MAML outperforms other methods for a wide range of training set sizes and positive to negative label ratios, indicating its general suitability for land use and crop type mapping. Expand
Context-self contrastive pretraining for crop type semantic segmentation
TLDR
This paper proposes a fully-supervised pretraining scheme based on contrastive learning particularly tailored to dense classification tasks and presents a process for semantic segmentation at super-resolution for obtaining crop classes at a more granular level. Expand
Rapid Response Crop Maps in Data Sparse Regions
TLDR
A method for rapid mapping of croplands in regions where little to no ground data is available is presented, and a successful transition of machine learning applications research to operational rapid response in a real humanitarian crisis is demonstrated. Expand
Robust low-rank covariance matrix estimation with a general pattern of missing values
This paper tackles the problem of robust covariance matrix estimation when the data is incomplete. Classical statistical estimation methodologies are usually built upon the Gaussian assumption,Expand

References

SHOWING 1-10 OF 45 REFERENCES
Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France
TLDR
A better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques is provided and it is found that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series. Expand
Using long short-term memory recurrent neural network in land cover classification on Landsat and Cropland data layer time series
TLDR
A long short-term memory (LSTM) recurrent neural network (RNN) model is built to take advantage of the temporal pattern of crops across image time series to improve the accuracy and reduce the complexity of land cover maps. Expand
Deep Recurrent Neural Networks for Winter Vegetation Quality Mapping via Multitemporal SAR Sentinel-1
TLDR
Analysis of Sentinel-1 radar images for winter vegetation quality mapping through the use of deep learning techniques revealed that the results of the proposed RNN models clearly outperformed classical machine learning approaches. Expand
Temporal Vegetation Modelling Using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-spectral Satellite Images
  • M. Rußwurm, M. Körner
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2017
TLDR
This work employs long short-term memory (LSTM) networks to extract temporal characteristics from a sequence of SENTINEL 2A observations and results show the effectiveness of dynamic temporal feature extraction. Expand
MULTI-TEMPORAL LAND COVER CLASSIFICATION WITH LONG SHORT-TERM MEMORY NEURAL NETWORKS
Abstract. Land cover classification (LCC) is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based onExpand
Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks
TLDR
RNNs are competitive compared with the state-of-the-art classifiers, and may outperform classical approaches in the presence of low represented and/or highly mixed classes, and it is shown that the alternative feature representation generated by LSTM can improve the performances of standard classifiers. Expand
SEN12MS - A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion
TLDR
This work exploits the freely available data acquired by the Sentinel satellites of the Copernicus program implemented by the European Space Agency, as well as the cloud computing facilities of Google Earth Engine to provide a dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patch, and MODIS land cover maps. Expand
Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks
TLDR
This paper presents the new change detection dataset that was used for training the proposed networks, and proposes two architectures to detect changes, Siamese and Early Fusion, which are trained from scratch using the provided dataset. Expand
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
TLDR
The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification, and some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size are provided. Expand
Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding
TLDR
Experimental results obtained in the framework of RS image scene classification problems show that a shallow Convolutional Neural Network architecture trained on the BigEarthNet provides much higher accuracy compared to a state-of-the-art CNN model pre-trained on the ImageNet. Expand
...
1
2
3
4
5
...