A Semi-Supervised Hybrid Approach for Multitemporal Multi-Region Multisensor Landsat Data Classification

Pencue-Fierro, Edgar Leonairo; Solano‐Correa, Yady Tatiana; Corrales, Juan Carlos; Casas, Apolinar Figueroa

doi:10.1109/jstars.2016.2623567

Cited by 21 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The accessibility of multitemporal satellite images could reduce the impact on classification caused by the complexity of surfaces and, to some Remote Sens. 2022, 14, 501 2 of 21 extent, the similarity between the spectrum of different vegetation [13]. However, part of the image is occluded by clouds and fog, resulting in missing data values [14,15], and the inconsistency of the input data dimensions makes it difficult to apply conventional classifiers, which need consistent data dimensions.…”

Section: Introductionmentioning

confidence: 99%

Wetland Vegetation Classification through Multi-Dimensional Feature Time Series Remote Sensing Images Using Mahalanobis Distance-Based Dynamic Time Warping

Wan

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Efficient methodologies for vegetation-type mapping are significant for wetland’s management practices and monitoring. Nowadays, dynamic time warping (DTW) based on remote sensing time series has been successfully applied to vegetation classification. However, most of the previous related studies only focused on Normalized Difference Vegetation Index (NDVI) time series while ignoring multiple features in each period image. In order to further improve the accuracy of wetland vegetation classification, Mahalanobis Distance-based Dynamic Time Warping (MDDTW) using multi-dimensional feature time series was employed in this research. This method extends the traditional DTW algorithm based on single-dimensional features to multi-dimensional features and solves the problem of calculating similarity distance between multi-dimensional feature time series. Vegetation classification experiments were carried out in the Yellow River Delta (YRD). Compared with different classification methods, the results show that the K-Nearest Neighbors (KNN) algorithm based on MDDTW (KNN-MDDTW) has achieved better classification accuracy; the overall accuracy is more than 90%, and kappa is more than 0.9.

show abstract

Section: Introductionmentioning

confidence: 99%

Wetland Vegetation Classification through Multi-Dimensional Feature Time Series Remote Sensing Images Using Mahalanobis Distance-Based Dynamic Time Warping

Wan

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, the developed model was only suitable for minimum class classification, not for maximum class classification, and the developed model showed poor performance in some conditions like cloud cover and regional fog error. Pencue-Fierro et al [36] presented a new hybrid framework for multi-region, multi-sensor and multi-temporal satellite image classification. In this study, land-cover classification was assessed for the Cauca river region, located in the south-west part of Colombia.…”

Section: Literature Surveymentioning

confidence: 99%

Land-Use and Land-Cover Classification Using a Human Group-Based Particle Swarm Optimization Algorithm with an LSTM Classifier on Hybrid Pre-Processing Remote-Sensing Images

et al. 2020

View full text Add to dashboard Cite

Land-use and land-cover (LULC) classification using remote sensing imagery plays a vital role in many environment modeling and land-use inventories. In this study, a hybrid feature optimization algorithm along with a deep learning classifier is proposed to improve the performance of LULC classification, helping to predict wildlife habitat, deteriorating environmental quality, haphazard elements, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosat datasets. After the selection of remote-sensing images, normalization and histogram equalization methods are used to improve the quality of the images. Then, a hybrid optimization is accomplished by using the local Gabor binary pattern histogram sequence (LGBPHS), the histogram of oriented gradient (HOG) and Haralick texture features, for the feature extraction from the selected images. The benefits of this hybrid optimization are a high discriminative power and invariance to color and grayscale images. Next, a human group-based particle swarm optimization (PSO) algorithm is applied to select the optimal features, whose benefits are a fast convergence rate and ease of implementation. After selecting the optimal feature values, a long short-term memory (LSTM) network is utilized to classify the LULC classes. Experimental results showed that the human group-based PSO algorithm with a LSTM classifier effectively well differentiates the LULC classes in terms of classification accuracy, recall and precision. A maximum improvement of 6.03% on Sat 4 and 7.17% on Sat 6 in LULC classification is reached when the proposed human group-based PSO with LSTM is compared to individual LSTM, PSO with LSTM, and Human Group Optimization (HGO) with LSTM. Moreover, an improvement of 2.56% in accuracy is achieved, compared to the existing models, GoogleNet, Visual Geometric Group (VGG), AlexNet, ConvNet, when the proposed method is applied.

show abstract

“…La percepción remota ha adquirido mayor importancia en los últimos años debido al surgimiento de algoritmos avanzados para la adquisición y procesamiento de imágenes [4], estos avances permiten generar herramientas de apoyo a la toma de decisiones, que incluyen el monitoreo operacional de los cultivos [5], lo cual se basa principalmente en índices de vegetación provenientes de datos ópticos, combinados con métricas agrometeorológicas como precipitación, temperatura, radiación solar y humedad del suelo [6]. Estas aplicaciones se han centrado en estudiar las interacciones sociedad naturaleza, analizando la relación existente entre el ser humano y la deforestación, la pérdida de la biodiversidad, el cambio climático [7] y otros procesos de transformación ocasionados por el desarrollo sociocultural y las actividades de apropiación y producción.…”

Section: Trabajos Relacionadosunclassified

“…En las regiones propensas a nubes como la CARC, es frecuente tener meses sin una escena Landsat sin nubosidad [7]. Las investigaciones recientes han aprovechado los sistemas de detección activa como el radar de apertura sintética (SAR), que además de su alta sensibilidad a las características superficiales y subsuperficiales funciona independientemente de la iluminación solar [17], lo que facilita cartografiar las coberturas presentes sobre las diferentes regiones.…”

Section: Trabajos Relacionadosunclassified

“…Normalized difference water index (NDVI), Soil adjusted vegetation index (SAVI), Enhanced vegetation index (EVI), Normalized dif-ference water index (NDWI), Simple ratio (SR), Transformed vegetation index (TVI), Atmospheric resistance vegetation index (ARVI), Structure in-sensitive pigment index (SIPI), Carotenoid reflectance index (CRI) además, de las bandas 2,3,4,5,6,7 del satélite los cuales han demostrado utilidad en la cartografía de la biomasa (coberturas vegetales) y condiciones superficiales, compensando el brillo del suelo y los artefactos de fondo[7].…”

unclassified

See 1 more Smart Citation

Mapeo de cobertura terrestre utilizando aprendizaje máquina

Muñoz-Ordóñez

Muñoz

Pencue-Fierro

et al. 2020

Investigación e Innovación en Ingenierías

View full text Add to dashboard Cite

Objetivo: Determinar las dinámicas de evolución de la cobertura terrestre sobre la Cuenca Alta del Río Cauca. Metodología: Esta investigación, presenta un proceso de clasificación de coberturas sobre la CARC utilizando imágenes Landsat-8 y Sentinel-1. Este análisis se realizó mediante la clasificación de características de imágenes satelitales ópticas y de radar, utilizando algoritmos de aprendizaje máquina. Resultados y conclusiones: se identificaron regiones que presentan afectación en sus coberturas vegetales mostrando la importancia de la utilización conjugada de satélites ópticos y de radar. La clasificación tuvo una precisión del 88.9% y un coeficiente kappa de 0.86

show abstract

A Semi-Supervised Hybrid Approach for Multitemporal Multi-Region Multisensor Landsat Data Classification

Cited by 21 publications

References 36 publications

Wetland Vegetation Classification through Multi-Dimensional Feature Time Series Remote Sensing Images Using Mahalanobis Distance-Based Dynamic Time Warping

Wetland Vegetation Classification through Multi-Dimensional Feature Time Series Remote Sensing Images Using Mahalanobis Distance-Based Dynamic Time Warping

Land-Use and Land-Cover Classification Using a Human Group-Based Particle Swarm Optimization Algorithm with an LSTM Classifier on Hybrid Pre-Processing Remote-Sensing Images

Mapeo de cobertura terrestre utilizando aprendizaje máquina

Contact Info

Product

Resources

About