An improved land cover classification using polarization signatures for PALSAR 2 data

Phartiyal, Gopal Singh; Kumar, Krishan; Singh, Dharmendra

doi:10.1016/j.asr.2020.02.028

Cited by 13 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coherent and incoherent methods have their advantages and disadvantages. Coherent decomposition is usually suitable for analysing natural targets like water, vegetation etc., while incoherent decomposition is usually suitable for analysis man-made targets like buildings (Zhang et al, 2008;Aghababaee et al, 2013;Parida & Mandal, 2020;Phartiyal et al, 2020;Ramya & Kumar, 2021). In this experiment we chose the Pauli coherent decomposition method because it is expected to present a better distinction of the various vegetation classes and water.…”

Section: Discussionmentioning

confidence: 99%

Deep support vector machine for PolSAR image classification

Okwuashi

Ndehedehe

Olayinka

et al. 2021

International Journal of Remote Sensing

View full text Add to dashboard Cite

The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets. Emphasis has shifted from the use of conventional classifiers to modern non-parametric classifiers such as the Artificial Neural Network (ANN) and Support Vector Machine (SVM); and most recently the hybrid Deep Neural Network (DNN) which is a fusion of Deep Learning (DL) and ANN. This research therefore presents the novel application of Deep Support Vector Machine (DSVM) which is a fusion of DL and SVM to PolSAR image classification. Two PolSAR images of Flevoland region in Netherlands, and Winnipeg in Canada are used as test beds for the experiment. The Lee filter is used to filter the images to suppress the speckle noise in the images. The Pauli decomposition is applied to decompose the images into |𝑆𝑆 𝐻𝐻𝐻𝐻 + 𝑆𝑆 𝑉𝑉𝑉𝑉 |, |𝑆𝑆 𝐻𝐻𝐻𝐻 − 𝑆𝑆 𝑉𝑉𝑉𝑉 |, |𝑆𝑆 𝐻𝐻𝑉𝑉 | polarimetric channels. Then the Gray Level Co-occurrence Matrix (GLCM) texture feature for |𝑆𝑆 𝐻𝐻𝐻𝐻 + 𝑆𝑆 𝑉𝑉𝑉𝑉 |, |𝑆𝑆 𝐻𝐻𝐻𝐻 − 𝑆𝑆 𝑉𝑉𝑉𝑉 |, |𝑆𝑆 𝐻𝐻𝑉𝑉 | are extracted based on correlation, contrast, energy, and homogeneity statistics, using GLCM directions 0 0 , 45 0 , 90 0 , and 135 0 with an offset distance of 60. To enhance the efficiency of the model 8, 16, 32, 64, 128, and 256 quantization levels are explored. The DSVM classifier is implemented with four kernel function: Exponential Radial Basis Function (ERBF), Gaussian Radial Basis Function (GRBF), neural, and polynomial. The first set of results is a comparison of the DSVM and SVM.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep support vector machine for PolSAR image classification

Okwuashi

Ndehedehe

Olayinka

et al. 2021

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…S x is the standard deviation of x, S y is the standard deviation of y, and S xy is the covariance between x and y. CC is the correlation coefficient between x and y. This paper refers to Reference [17] to obtain the PSCF solution and establish the feature correlation coefficients between a single target and four standard targets, which are Corr_co_Di, Corr_co_FP, Corr_co_HD, Corr_co_VD, Corr_cross_Di, Corr_ cross _FP, Corr_ cross_HD, and Corr_ cross _VD. Among them, the co is for the co-polarization while the cross is for cross-polarization.…”

Section: Freeman-durden Decompositionmentioning

confidence: 99%

“…While SVM classifies samples by finding hyperplanes, decision trees classify samples by selecting the optimal components and dividing the subset into the corresponding leaf nodes based on the features. Phartiyal et al [17] used an evolutionary genetic algorithm to optimize the empirical model to maximize the classification performance. They constructed a decision tree based on the best class boundary and obtained satisfactory classification results.…”

Section: Introductionmentioning

confidence: 99%

Feature-Level Fusion of Polarized SAR and Optical Images Based on Random Forest and Conditional Random Fields

et al. 2021

View full text Add to dashboard Cite

In terms of land cover classification, optical images have been proven to have good classification performance. Synthetic Aperture Radar (SAR) has the characteristics of working all-time and all-weather. It has more significant advantages over optical images for the recognition of some scenes, such as water bodies. One of the current challenges is how to fuse the benefits of both to obtain more powerful classification capabilities. This study proposes a classification model based on random forest with the conditional random fields (CRF) for feature-level fusion classification using features extracted from polarized SAR and optical images. In this paper, feature importance is introduced as a weight in the pairwise potential function of the CRF to improve the correction rate of misclassified points. The results show that the dataset combining the two provides significant improvements in feature identification when compared to the dataset using optical or polarized SAR image features alone. Among the four classification models used, the random forest-importance_ conditional random fields (RF-Im_CRF) model developed in this paper obtained the best overall accuracy (OA) and Kappa coefficient, validating the effectiveness of the method.

show abstract

“…Polarization signatures (PSs) are computed from the single look complex PolSAR data with procedure similar to Phartiyal et al (2017). Further, polarization signatures correlation features (PSCFs) are computed from the PSs using procedure similar to as explained in Phartiyal, Kumar, and Singh (2020). PSCFs provide the degree of correlation between canonical/standard target PSs and observed/pixel PSs.…”

Section: Datasetmentioning

confidence: 99%

Permuted Spectral and Permuted Spectral-Spatial CNN Models for PolSAR-Multispectral Data based Land Cover Classification

Singh

Bordu

Singh

et al. 2020

International Journal of Remote Sensing

Self Cite

View full text Add to dashboard Cite

It is a challenge to develop methods which can process the PolSAR and multispectral (MS) data modalities together without losing information from either for remote sensing applications. This paper presents a study which attempts to introduce novel deep learning based remote sensing data processing frameworks that utilizes convolutional neural networks (CNNs) in both spatial and spectral domains to perform land cover (LC) classification with PolSAR-MS data. Also since earth observation remotely sensed data have usually larger spectral depth than normal camera image data, exploiting the spectral information in remote sensing (RS) data is crucial as well. In fact, convolutions in the subspectral space are intuitive and alternative to the process of feature selection. Recently, researchers have gained success in exploiting the spectral information of RS data, especially the hyperspectral data with CNNs. In this paper, exploitation of the spectral information in the PolSAR-MS data via a permuted localized spectral convolution along with localized spatial convolution is proposed. Further, the study in this paper also establishes the significance of performing permuted localized spectral convolutions over non-localized or localized spectral convolutions. Two models are proposed, namely a permuted local spectral convolutional network (Perm-LS-CNN) and a permuted local spectral-spatial convolutional network (Perm-LSS-CNN). These models are trained on ground truth class data points measured directly on the terrain. The evaluation of the generalization performance is done using ground truth knowledge on selected well known regions in the study areas. Comparison with other popular machine learning classifiers shows that the Perm-LSS-CNN model provides better classification results in terms of both accuracy and generalization.

show abstract

An improved land cover classification using polarization signatures for PALSAR 2 data

Cited by 13 publications

References 21 publications

Deep support vector machine for PolSAR image classification

Deep support vector machine for PolSAR image classification

Feature-Level Fusion of Polarized SAR and Optical Images Based on Random Forest and Conditional Random Fields

Permuted Spectral and Permuted Spectral-Spatial CNN Models for PolSAR-Multispectral Data based Land Cover Classification

Contact Info

Product

Resources

About