Generalization of Convolutional LSTM Models for Crop Area Estimation

Macedo, Maysa M. G.; Mattos, Andréa Britto; Oliveira, Dário Augusto Borges

doi:10.1109/jstars.2020.2973602

Cited by 25 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we will only consider the latter case as it is similar to the approach followed in this work. Previous studies have incorporated recurrent neural networks (RNNs) in their pipeline, such as the long short-term memory (LSTM) model [18], which are fed pixel vectors of multiple time steps [19]- [22]. In [23], a 2-branch model is proposed (DuPLO) whose first branch is a CNN spatial feature extractor, whereas the second branch is a gated recurrent unit (GRU) [24] temporal feature extractor.…”

Section: Crop Type Classification With Deep Learningmentioning

confidence: 99%

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Sykas

Sdraka

Zografakis

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this work, we introduce Sen4AgriNet, a Sentinel-2-based time series multicountry benchmark dataset, tailored for agricultural monitoring applications with machine and deep learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the land parcel identification system (LPIS) for harmonizing country-wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardize a new crop type taxonomy across Europe that addresses common agriculture policy (CAP) needs, based on the Food and Agriculture Organization (FAO) indicative crop classification scheme. Sen4AgriNet is the only multicountry, multiyear dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two subdatasets to highlight its value for diverse deep learning applications-the object aggregated dataset (OAD) and the patches assembled dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries. 1

show abstract

Section: Crop Type Classification With Deep Learningmentioning

confidence: 99%

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Sykas

Sdraka

Zografakis

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Here we will only consider the latter case as it is similar to the approach followed in this work. Previous studies have incorporated recurrent neural networks (RNNs) in their pipeline, such as the Long Short-Term Memory (LSTM) model [18], which are fed pixel vectors of multiple time steps [19,20,21,22]. In [23] a 2-branch model is proposed (DuPLO) whose first branch is a CNN spatial feature extractor, whereas the second branch is a Gated Recurrent Unit (GRU) [24] temporal feature extractor.…”

Section: Crop Type Classification With Deep Learningmentioning

confidence: 99%

A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning

Sykas¹,

Sdraka²,

Zografakis³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this work we introduce Sen4AgriNet, a Sentinel-2 based time series multi country benchmark dataset, tailored for agricultural monitoring applications with Machine and Deep Learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the Land Parcel Identification System (LPIS) for harmonizing country wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardise a new crop type taxonomy across Europe that address Common Agriculture Policy (CAP) needs, based on the Food and Agriculture Organization (FAO) Indicative Crop Classification scheme. Sen4AgriNet is the only multi-country, multi-year dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two sub-datasets to highlight its value for diverse Deep Learning applications; the Object Aggregated Dataset (OAD) and the Patches Assembled Dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful labelto-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries. The dataset can be accessed in: https://sen4agrinet.space.noa.gr

show abstract

“…These models utilize various deep learning method which are suited for multiple band classifications, while reducing redundancies during feature extraction for different applications. Efficiency of these models is further improved via Convolutional Neural Networks with two sampling strategies (CNN TSS) [14], long-short-term memory (LSTM) [15], Multitemporal polarimetric deep learning [16], spatiotemporal deep learning Models [17], and Multitemporal deep learning models for Rice classification [18] are used. These models aim at improving feature representation via use of multiple layers of convolution, thereby maximizing feature variance, and minimizing error rate during classification operations.…”

Section: Literature Reviewmentioning

confidence: 99%

Design of a high-efficiency temporal engine for real-time satellite image classification using augmented incremental transfer learning for crop analysis

Dhande

Malik

2022

Preprint

View full text Add to dashboard Cite

Satellite image processing is a multidomain task which involves design of image capturing, denoising, segmentation, feature extraction, feature reduction, classification, and post-processing tasks. A wide variety of satellite image processing models are proposed by researchers, and each of them have different data & process requirements. For instance, image capturing module Might obtain Images in layered form, while feature extraction module might require data in 2D or 3D forms. Moreover, performance of these models also varies due to changes in internal process parameters & dataset parameters, which limits their accuracy and scalability when applied to real-time scenarios. To reduce the probability of these limitations, a novel high-efficiency temporal engine for real-time satellite image classification using augmented incremental transfer learning is proposed & discussed in this text. The model initially captures real-time satellite data using Google’s Earth Engine and processes it using a transfer learning-based convolutional neural network (CNN) via backscatter coefficient analysis. These coefficients indicate average intensity value of Precision Image (PRI) when evaluated over a distributed target. Due to extraction of backscattering coefficients, the model is capable of representing crop images in VV (vertical transmit, vertical receive), and HV (horizontal transmit vertical receive) modes. Thereby assisting the CNN model to extract a wide variety of features from input satellite image, which classifies these datasets (original, VV, and VH) into different crop categories. The classified images are further processed via an incremental learning layer, which assists in visual identification of affected regions. Due to use of incremental learning and CNN for classification, the proposed TRSAITL model is capable of achieving an average accuracy of 97.8% for crop type & severity of damage detection, with an average PSNR of 29.6 dB for different image types. The model was tested on different regions around our local geographical area, and consistent performance was observed. This performance was also compared with various state-of-the-art approaches, and it was observed that the proposed TRSATL model has 5% better accuracy, 4.6% better precision, and 7.9% better recall when compared with them, which makes it highly useful for real-time satellite-based crop classification applications.

show abstract

Generalization of Convolutional LSTM Models for Crop Area Estimation

Cited by 25 publications

References 25 publications

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning

Design of a high-efficiency temporal engine for real-time satellite image classification using augmented incremental transfer learning for crop analysis

Contact Info

Product

Resources

About