Multitemporal Classification of Agricultural Crops Using the Spectral-Temporal Response Surface

Vieira, Carlos Antônio Oliveira; Mather, Paul M.; Aplin, Paul

doi:10.1142/9789812777249_0032

Cited by 8 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Multitemporal satellite images are widely used in land-cover classification [49]. Because using single-date imagery to identity land-cover types with similar spectral features can be challenging [50,51], multitemporal images have been employed to make use of the phenological variation which is a valuable information source for improving the accuracy of land-cover classification [52]. However, in terms of land-cover classification, the usefulness of information does not always increase in proportion to the number of multitemporal images [53].…”

Section: Effect Of Feature Combinations and Training-sample Sizementioning

confidence: 99%

“…Multitemporal satellite images are widely used in land-cover classification [49]. Because using single-date imagery to identity land-cover types with similar spectral features can be challenging [50,51], multitemporal images have been employed to make use of the phenological variation which In this section, the effect of feature combination on classification accuracy is fully explored for the two types of feature input based on the RF classifier. Features were randomly combined based on the mathematical principles of permutation and combination (i.e., C m n equals the number of combinations when m features are taken from n features).…”

Section: Effect Of Feature Combinations and Training-sample Sizementioning

confidence: 99%

See 1 more Smart Citation

Automatic Land-Cover Mapping using Landsat Time-Series Data based on Google Earth Engine

et al. 2019

View full text Add to dashboard Cite

The Google Earth Engine (GEE) has emerged as an essential cloud-based platform for land-cover classification as it provides massive amounts of multi-source satellite data and high-performance computation service. This paper proposed an automatic land-cover classification method using time-series Landsat data on the GEE cloud-based platform. The Moderate Resolution Imaging Spectroradiometer (MODIS) land-cover products (MCD12Q1.006) with the International Geosphere–Biosphere Program (IGBP) classification scheme were used to provide accurate training samples using the rules of pixel filtering and spectral filtering, which resulted in an overall accuracy (OA) of 99.2%. Two types of spectral–temporal features (percentile composited features and median composited monthly features) generated from all available Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) data from the year 2010 ± 1 were used as input features to a Random Forest (RF) classifier for land-cover classification. The results showed that the monthly features outperformed the percentile features, giving an average OA of 80% against 77%. In addition, the monthly features composited using the median outperformed those composited using the maximum Normalized Difference Vegetation Index (NDVI) with an average OA of 80% against 78%. Therefore, the proposed method is able to generate accurate land-cover mapping automatically based on the GEE cloud-based platform, which is promising for regional and global land-cover mapping.

show abstract

Section: Effect Of Feature Combinations and Training-sample Sizementioning

confidence: 99%

“…Multitemporal satellite images are widely used in land-cover classification [49]. Because using single-date imagery to identity land-cover types with similar spectral features can be challenging [50,51], multitemporal images have been employed to make use of the phenological variation which In this section, the effect of feature combination on classification accuracy is fully explored for the two types of feature input based on the RF classifier. Features were randomly combined based on the mathematical principles of permutation and combination (i.e., C m n equals the number of combinations when m features are taken from n features).…”

Section: Effect Of Feature Combinations and Training-sample Sizementioning

confidence: 99%

Automatic Land-Cover Mapping using Landsat Time-Series Data based on Google Earth Engine

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The spectral-temporal response surface (STRS) of each pixel was created using a polynomial function parameterized for the 28 control points (MODIS 7 dates and 4 bands), using the "collocation" interpolation method (Watson, 1992;Vieira et al, 2002), which allows an accurate representation of the surface adherence to the control points (Rudorff et al, 2007). All procedures of fi tting surfaces were done using an executable algorithm developed by Vieira (2000).…”

Section: Methodsmentioning

confidence: 99%

“…Instead of using refl ectance values, this methodology uses parameterized polynomial coeffi cients of each STRS, for each pixel of a spectral-temporal data series. Each pixel is represented in a tridimensional space with control points spatially distributed in the spectral, temporal and refl ectance components disposed in the X, Y and Z axes respectively, and each class of the studied area has a specifi c STRS (Vieira et al, 2002).…”

Section: Introductionmentioning

confidence: 99%

Estimating soybean crop areas using spectral-temporal surfaces derived from MODIS images in Mato Grosso, Brazil

Epiphanio

Formaggio

Rudorff

et al. 2010

Pesq. agropec. bras.

View full text Add to dashboard Cite

-The objective of this work was to evaluate the application of the spectral-temporal response surface (STRS) classifi cation method on Moderate Resolution Imaging Spectroradiometer (MODIS, 250 m) sensor images in order to estimate soybean areas in Mato Grosso state, Brazil. The classifi cation was carried out using the maximum likelihood algorithm (MLA) adapted to the STRS method. Thirty segments of 30x30 km were chosen along the main agricultural regions of Mato Grosso state, using data from the summer season of 2005/2006 (from October to March), and were mapped based on fi eldwork data, TM/Landsat-5 and CCD/ CBERS-2 images. Five thematic classes were considered: Soybean, Forest, Cerrado, Pasture and Bare Soil. The classifi cation by the STRS method was done over an area intersected with a subset of 30x30-km segments. In regions with soybean predominance, STRS classifi cation overestimated in 21.31% of the reference values. In regions where soybean fi elds were less prevalent, the classifi er overestimated 132.37% in the acreage of the reference. The overall classifi cation accuracy was 80%. MODIS sensor images and the STRS algorithm showed to be promising for the classifi cation of soybean areas in regions with the predominance of large farms. However, the results for fragmented areas and smaller farms were less effi cient, overestimating soybean areas.Index terms: Glycine max, accuracy, agricultural statistics, classifi cation, remote sensing, thematic map. Estimativa de áreas de soja usando superfícies espectro-temporais derivadas de imagens MODIS em Mato Grosso, BrasilResumo -O objetivo deste trabalho foi avaliar a aplicação do método de classifi cação por superfícies de resposta espectro-temporal (STRS) em imagens do sensor Moderate Resolution Imaging Spectroradiometer (MODIS, 250 m) para estimar áreas de plantio de soja no Estado de Mato Grosso, Brasil. A classifi cação foi realizada usando o algoritmo de máxima verossimilhança (MLA) adaptado ao algoritmo STRS. Trinta segmentos de 30x30 km foram escolhidos ao longo das principais regiões agrícolas do estado, com dados da safra de verão de 2005/2006 (outubro a março), e mapeados com base em dados de campo e de imagens orbitais TM/Landsat-5 e CCD/CBERS-2. Cinco classes temáticas foram consideradas: Soja, Floresta, Cerrado, Pastagem e Solos Expostos. A classifi cação pelo método das STRS foi feita com base em uma área interseccionada por um subconjunto de segmentos de 30x30 km. O STRS superestimou os valores de referência em 21,31% em regiões com predomínio da cultura da soja e em 132,37% em regiões nas quais a soja era menos predominante. A exatidão global da classifi cação foi de 80%. As imagens MODIS e o algoritmo STRS mostraram-se promissores para a classifi cação da soja em regiões com predominância de grandes fazendas. Entretanto, os resultados para áreas fragmentadas em fazendas menores foram menos efi cientes, superestimando as áreas de soja.Termos para indexação: Glycine max, acurácia, estatísticas agrícolas, classifi cação, sensoriamento r...

show abstract

“…The aim of a systematised and automated process of digital classification is to identify areas of similar features, label them and assign them to a class. Automated classification methods rely on defining the rules of assigning pixels to classes on the basis of their spectral features [13], or in the case of crop detection on spectral and time feature space [14].…”

Section: Introductionmentioning

confidence: 99%

Review on Multitemporal Classification Methods of Satellite Images for Crop and Arable Land Recognition

Pluto-Kossakowska¹

2021

Agriculture

View full text Add to dashboard Cite

This paper presents a review of the conducted research in the field of multitemporal classification methods used for the automatic identification of crops and arable land using optical satellite images. The review and systematization of these methods in terms of the effectiveness of the obtained results and their accuracy allows for the planning towards further development in this area. The state of the art analysis concerns various methodological approaches, including selection of data in terms of spatial resolution, selection of algorithms, as well as external conditions related to arable land use, especially the structure of crops. The results achieved with use of various approaches and classifiers and subsequently reported in the literature vary depending on the crops and area of analysis and the sources of satellite data. Hence, their review and systematic conclusions are needed, especially in the context of the growing interest in automatic processes of identifying crops for statistical purposes or monitoring changes in arable land. The results of this study show no significant difference between the accuracy achieved from different machine learning algorithms, yet on average artificial neural network classifiers have results that are better by a few percent than others. For very fragmented regions, better results were achieved using Sentinel-2, SPOT-5 rather than Landsat images, but the level of accuracy can still be improved. For areas with large plots there is no difference in the level of accuracy achieved from any HR images.

show abstract

Multitemporal Classification of Agricultural Crops Using the Spectral-Temporal Response Surface

Cited by 8 publications

References 0 publications

Automatic Land-Cover Mapping using Landsat Time-Series Data based on Google Earth Engine

Automatic Land-Cover Mapping using Landsat Time-Series Data based on Google Earth Engine

Estimating soybean crop areas using spectral-temporal surfaces derived from MODIS images in Mato Grosso, Brazil

Review on Multitemporal Classification Methods of Satellite Images for Crop and Arable Land Recognition

Contact Info

Product

Resources

About