Scattering Feature Set Optimization and Polarimetric SAR Classification Using Object-Oriented RF-SFS Algorithm in Coastal Wetlands

Chen, Yuanyuan; He, Xiufeng; Xu, Jun; Zhang, Rongchun; Lu, Yao

doi:10.3390/rs12030407

Cited by 22 publications

(14 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The position of the various types of elementary scattering mechanisms are shown on the unit circle represented in Figure 1 along with the regions on the unit disk which are considered as belonging to these scattering mechanisms. Evidently, and according to the values of z given in Table 1, all elementary scatterers lie on the diameter of the unit disk except for the 1 /4 wave devices which lie on the imaginary axis [18]. Cameron in order to determine the scattering behavior of an unknown scattering target z considered the following distance metric:…”

Section: Methods-cameron's Decomposition and The Symmetric Scatterer ...mentioning

confidence: 99%

“…In [17] the elementary scatterers obtained from Cameron CTD are used as the states of Markov chain models to characterize polarimetric SAR land cover. More than 20 polarimetric decompositions techniques, without including Cameron's, were used in [18] to extract a set of polarimetric scattering features, which was optimized in order to improve land cover classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PolSAR Cell Information Representation by a Pair of Elementary Scatterers

Karachristos¹,

Κούκιου²,

Anastassopoulos³

2022

Remote Sensing

View full text Add to dashboard Cite

This study exploits Cameron’s decomposition for polarimetric data analysis and presents an information extraction process so that each PolSAR cell (pixel) is interpreted by two dominating elementary scattering mechanisms each one contributing to the scattering behavior of the SAR pixel with its own weight. The co-distance matrix is introduced to depict the metric distances between these two nearest scattering mechanisms. For most of the scattering mechanisms in each resolution cell, the strength between the first and the second nearest elementary scatterer usually differs slightly. This indicates that the interpretation of the available information in a PolSAR pixel by a single dominant scatterer, as most methods employ, is not adequate. The proposed method presents an alternative to Cameron’s spherical topology by taking advantage of the elementary scattering mechanisms complementary nature and inspired by the philosophy of principal component analysis. According to the introduced topology four elementary scatterers, which are in pairs complementary to each other, are adequate to characterize each PolSAR pixel. The aim of this research is to present a new feature-toοl with a more stochastic nature that could fit a variety of techniques that utilize fully polarimetric data. To prove the strength of the proposed method, the double-scatterer model is applied for interpreting each pixel on a variety of land cover types presenting a richer feature extraction capability, effective in detection and classification procedures.

show abstract

Section: Methods-cameron's Decomposition and The Symmetric Scatterer ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

PolSAR Cell Information Representation by a Pair of Elementary Scatterers

Karachristos¹,

Κούκιου²,

Anastassopoulos³

2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Most studies have successfully used one decomposition technology in wetlands mapping and monitoring [7,34,35]. One or a few polarimetric decomposition features, however, may restrict the provision of sufficient information to achieve high identification accuracy for the wetlands and their surrounding objects [36,37]. Therefore, it is necessary to search some suitable decomposition methods and extract and integrate multiple polarimetric features to improve the ability to determine the heterogeneity of the objects.…”

Section: Introductionmentioning

confidence: 99%

“…The pixel-based methods just analyze the spectral characteristics of each pixel in an image and may be easily affected by isolated pixels, so that the classification results may appear fragmented and discontinuous in their spatial distribution [44]. By contrast, object-based image analysis (OBIA) methods segment the image into numerous homogeneous objects [20,21,37]. The classification accuracy may increase by applying OBIA methods due to the spatial relation features of adjacent objects and the spectral, textural, and geometrical features of individual objects that are used for identifying different land covers [44][45][46].…”

Section: Introductionmentioning

confidence: 99%

Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery

Liu

Jiang

et al. 2022

Water

View full text Add to dashboard Cite

The development of advanced and efficient methods for mapping and monitoring wetland regions is essential for wetland resources conservation, management, and sustainable development. Although remote sensing technology has been widely used for detecting wetlands information, it remains a challenge for wetlands classification due to the extremely complex spatial patterns and fuzzy boundaries. This study aims to implement a comprehensive and effective classification scheme for wetland land covers. To achieve this goal, a novel object-based multigrained cascade forest (OGCF) method with multisensor data (including Sentinel-2 and Radarsat-2 remote sensing imagery) was proposed to classify the wetlands and their adjacent land cover classes in the wetland National Natural Reserve. Moreover, a hybrid selection method (ReliefF-RF) was proposed to optimize the feature set in which the spectral and polarimetric decomposition features are contained. We obtained six spectral features from visible and shortwave infrared bands and 10 polarimetric decomposition features from the H/A/Alpha, Pauli, and Krogager decomposition methods. The experimental results showed that the OGCF method with multisource features for land cover classification in wetland regions achieved the overall accuracy and kappa coefficient of 88.20% and 0.86, respectively, which outperformed the support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The accuracy of the wetland classes ranged from 75.00% to 97.53%. The proposed OGCF method exhibits a good application potential for wetland land cover classification. The classification scheme in this study will make a positive contribution to wetland inventory and monitoring and be able to provide technical support for protecting and developing natural resources.

show abstract

“…For example, Millard et al combined SAR and Lidar data to achieve higher accuracy [ 28 ]. Chen et al integrated 20 polarimetric decomposition algorithms and proposed a feature set optimization method to select the optimal polarimetric features for wetland classification [ 29 ]. However, these studies only improved the feature optimization method from a statistical perspective and did not consider the applicability of the features to wetland identification.…”

Section: Introductionmentioning

confidence: 99%

Coastal Wetland Classification with GF-3 Polarimetric SAR Imagery by Using Object-Oriented Random Forest Algorithm

Zhang

Chen

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

When the use of optical images is not practical due to cloud cover, Synthetic Aperture Radar (SAR) imagery is a preferred alternative for monitoring coastal wetlands because it is unaffected by weather conditions. Polarimetric SAR (PolSAR) enables the detection of different backscattering mechanisms and thus has potential applications in land cover classification. Gaofen-3 (GF-3) is the first Chinese civilian satellite with multi-polarized C-band SAR imaging capability. Coastal wetland classification with GF-3 polarimetric SAR imagery has attracted increased attention in recent years, but it remains challenging. The aim of this study was to classify land cover in coastal wetlands using an object-oriented random forest algorithm on the basis of GF-3 polarimetric SAR imagery. First, a set of 16 commonly used SAR features was extracted. Second, the importance of each SAR feature was calculated, and the optimal polarimetric features were selected for wetland classification by combining random forest (RF) with sequential backward selection (SBS). Finally, the proposed algorithm was utilized to classify different land cover types in the Yancheng Coastal Wetlands. The results show that the most important parameters for wetland classification in this study were Shannon entropy, Span and orientation randomness, combined with features derived from Yamaguchi decomposition, namely, volume scattering, double scattering, surface scattering and helix scattering. When the object-oriented RF classification approach was used with the optimal feature combination, different land cover types in the study area were classified, with an overall accuracy of up to 92%.

show abstract

Scattering Feature Set Optimization and Polarimetric SAR Classification Using Object-Oriented RF-SFS Algorithm in Coastal Wetlands

Cited by 22 publications

References 52 publications

PolSAR Cell Information Representation by a Pair of Elementary Scatterers

PolSAR Cell Information Representation by a Pair of Elementary Scatterers

Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery

Coastal Wetland Classification with GF-3 Polarimetric SAR Imagery by Using Object-Oriented Random Forest Algorithm

Contact Info

Product

Resources

About