Comparing six pixel-wise classifiers for tropical rural land cover mapping using four forms of fully polarimetric SAR data
21 Mar 2017-International Journal of Remote Sensing (Taylor & Francis)-Vol. 38, Iss: 11, pp 3274-3293
TL;DR: In this article, four commonly used forms of synthetic aperture radar (SAR) data for land-cover classification in tropical rural areas were evaluated and the backscatter coefficient of linearly polarized L-band was evaluated.
Abstract: This study evaluates four commonly used forms of synthetic aperture radar (SAR) data for land-cover classification in tropical rural areas. The backscatter coefficient of linearly polarized L-band ...
Citations
More filters
TL;DR: This study shows the reliability of fixed-wing UAV imagery for forest monitoring and evidences the importance of planning UAV flights at solar noon to significantly reduce the shadows of trees in the obtained imagery, which is critical for classifying open forest ecosystems such as cork oak woodlands.
Abstract: This paper investigates the reliability of free and open-source algorithms used in the geographical object-based image classification (GEOBIA) of very high resolution (VHR) imagery surveyed by unmanned aerial vehicles (UAVs). UAV surveys were carried out in a cork oak woodland located in central Portugal at two different periods of the year (spring and summer). Segmentation and classification algorithms were implemented in the Orfeo ToolBox (OTB) configured in the QGIS environment for the GEOBIA process. Image segmentation was carried out using the Large-Scale Mean-Shift (LSMS) algorithm, while classification was performed by the means of two supervised classifiers, random forest (RF) and support vector machines (SVM), both of which are based on a machine learning approach. The original, informative content of the surveyed imagery, consisting of three radiometric bands (red, green, and NIR), was combined to obtain the normalized difference vegetation index (NDVI) and the digital surface model (DSM). The adopted methodology resulted in a classification with higher accuracy that is suitable for a structurally complex Mediterranean forest ecosystem such as cork oak woodlands, which are characterized by the presence of shrubs and herbs in the understory as well as tree shadows. To improve segmentation, which significantly affects the subsequent classification phase, several tests were performed using different values of the range radius and minimum region size parameters. Moreover, the consistent selection of training polygons proved to be critical to improving the results of both the RF and SVM classifiers. For both spring and summer imagery, the validation of the obtained results shows a very high accuracy level for both the SVM and RF classifiers, with kappa coefficient values ranging from 0.928 to 0.973 for RF and from 0.847 to 0.935 for SVM. Furthermore, the land cover class with the highest accuracy for both classifiers and for both flights was cork oak, which occupies the largest part of the study area. This study shows the reliability of fixed-wing UAV imagery for forest monitoring. The study also evidences the importance of planning UAV flights at solar noon to significantly reduce the shadows of trees in the obtained imagery, which is critical for classifying open forest ecosystems such as cork oak woodlands.
83 citations
Cites methods from "Comparing six pixel-wise classifier..."
...The GEOBIA paradigm coupled with the use of machine learning classification algorithms is currently considered an excellent “first-choice approach” for the classification of forest tree species and the general derivation of forest information [28,31,41,55,63]....
[...]
TL;DR: Innovative strategies for classifying tree species in subtropical forest areas at a refined legend level are presented, integrating UAV-borne 2D hyperspectral and 3D photogrammetric data and relying on both deep and conventional machine learning approaches.
Abstract: The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. ...
69 citations
Cites background from "Comparing six pixel-wise classifier..."
...On the other hand, RF has generally been found to be robust to parameter settings (RodriguezGaliano et al. 2012; Trisasongko et al. 2017; Trisasongko and Paull 2019; Maxwell, Warner, and Fang 2018)....
[...]
...Conversely, Foody and Mathur (2004) and Trisasongko et al. (2017) found larger impact on classification accuracies, with differences up to 20% when varying the SVM parameters....
[...]
TL;DR: Overall performances of five classifiers suggest Polynomial-SVM has the best potential to improve sugarcane mapping at the regional scale, and the potential of fine-resolution Sentinel-2 images and machine learning approaches in high-accuracy land use management and decision-making is suggested.
42 citations
TL;DR: Advantages, limitations, challenges, and opportunities are identified for understanding the context of improvements, and this will guide the future development of bitemporal and multitemporal CD methods and techniques for understanding land cover dynamics.
Abstract: Satellite images provide an accurate, continuous, and synoptic view of seamless global extent. Within the fields of remote sensing and image processing, land surface change detection (CD) has been amongst the most discussed topics. This article reviews advances in bitemporal and multitemporal two-dimensional CD with a focus on multispectral images. In addition, it reviews some CD techniques used for synthetic aperture radar (SAR). The importance of data selection and preprocessing for CD provides a starting point for the discussion. CD techniques are, then, grouped based on the change analysis products they can generate to assist users in identifying suitable procedures for their applications. The discussion allows users to estimate the resources needed for analysis and interpretation, while selecting the most suitable technique for generating the desired information such as binary changes, direction or magnitude of changes, “from-to” information of changes, probability of changes, temporal pattern, and prediction of changes. The review shows that essential and innovative improvements are being made in analytical processes for multispectral images. Advantages, limitations, challenges, and opportunities are identified for understanding the context of improvements, and this will guide the future development of bitemporal and multitemporal CD methods and techniques for understanding land cover dynamics.
41 citations
TL;DR: This review presents a comprehensive overview of existing research articles that apply spaceborne L-band SAR data for geoscientific analyses that are relevant for coastal land applications.
Abstract: The coastal zone offers among the world’s most productive and valuable ecosystems and is experiencing increasing pressure from anthropogenic impacts: human settlements, agriculture, aquaculture, trade, industrial activities, oil and gas exploitation and tourism. Earth observation has great capability to deliver valuable data at the local, regional and global scales and can support the assessment and monitoring of land- and water-related applications in coastal zones. Compared to optical satellites, cloud-cover does not limit the timeliness of data acquisition with spaceborne Synthetic Aperture Radar (SAR) sensors, which have all-weather, day and night capabilities. Hence, active radar systems demonstrate great potential for continuous mapping and monitoring of coastal regions, particularly in cloud-prone tropical and sub-tropical climates. The canopy penetration capability with long radar wavelength enables L-band SAR data to be used for coastal terrestrial environments and has been widely applied and investigated for the following geoscientific topics: mapping and monitoring of flooded vegetation and inundated areas; the retrieval of aboveground biomass; and the estimation of soil moisture. Human activities, global population growth, urban sprawl and climate change-induced impacts are leading to increased pressure on coastal ecosystems causing land degradation, deforestation and land use change. This review presents a comprehensive overview of existing research articles that apply spaceborne L-band SAR data for geoscientific analyses that are relevant for coastal land applications.
30 citations
References
More filters
Journal Article•
TL;DR: Copyright (©) 1999–2012 R Foundation for Statistical Computing; permission is granted to make and distribute verbatim copies of this manual provided the copyright notice and permission notice are preserved on all copies.
Abstract: Copyright (©) 1999–2012 R Foundation for Statistical Computing. Permission is granted to make and distribute verbatim copies of this manual provided the copyright notice and this permission notice are preserved on all copies. Permission is granted to copy and distribute modified versions of this manual under the conditions for verbatim copying, provided that the entire resulting derived work is distributed under the terms of a permission notice identical to this one. Permission is granted to copy and distribute translations of this manual into another language, under the above conditions for modified versions, except that this permission notice may be stated in a translation approved by the R Core Team.
272,030 citations
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
"Comparing six pixel-wise classifier..." refers background in this paper
...This approach, known as Random Forests (RFs), was introduced by Breiman (2001) and has been exploited in remote sensing....
[...]
...This approach, known as Random Forests (RFs), was introduced by Breiman (2001) and has been exploited in remote sensing. For instance, Clewley et al. (2015) reported that significant accuracy was...
[...]
Book•
01 Jan 1995TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Abstract: Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.
40,147 citations
"Comparing six pixel-wise classifier..." refers methods in this paper
...Support Vector Machine (SVM) Another classifier that has been widely utilized in remote sensing is SVM (Vapnik 2000)....
[...]
TL;DR: A general gradient descent boosting paradigm is developed for additive expansions based on any fitting criterion, and specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification.
Abstract: Function estimation/approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest-descent minimization. A general gradient descent “boosting” paradigm is developed for additive expansions based on any fitting criterion.Specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification. Special enhancements are derived for the particular case where the individual additive components are regression trees, and tools for interpreting such “TreeBoost” models are presented. Gradient boosting of regression trees produces competitive, highly robust, interpretable procedures for both regression and classification, especially appropriate for mining less than clean data. Connections between this approach and the boosting methods of Freund and Shapire and Friedman, Hastie and Tibshirani are discussed.
17,764 citations
28 Mar 1993
TL;DR: A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed that performs a local adaptation of the weight-updates according to the behavior of the error function to overcome the inherent disadvantages of pure gradient-descent.
Abstract: A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed. To overcome the inherent disadvantages of pure gradient-descent, RPROP performs a local adaptation of the weight-updates according to the behavior of the error function. Contrary to other adaptive techniques, the effect of the RPROP adaptation process is not blurred by the unforeseeable influence of the size of the derivative, but only dependent on the temporal behavior of its sign. This leads to an efficient and transparent adaptation process. The capabilities of RPROP are shown in comparison to other adaptive techniques. >
4,319 citations
"Comparing six pixel-wise classifier..." refers background in this paper
...However, for the sake of efficiency, RPROP may be the primary choice as the backpropagation algorithm is usually computationally inefficient (Riedmiller and Braun 1993)....
[...]