scholarly journals A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

2021 ◽  
Vol 13 (3) ◽  
pp. 355
Author(s):  
Weixian Tan ◽  
Borong Sun ◽  
Chenyu Xiao ◽  
Pingping Huang ◽  
Wei Xu ◽  
...  
Keyword(s):  
Spectral Clustering ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Feature Vector ◽  
Unsupervised Classification ◽  
Classification Method ◽  
Sandy Land ◽  
Classification Methods ◽  
The Many ◽  
Representative Points

Classification based on polarimetric synthetic aperture radar (PolSAR) images is an emerging technology, and recent years have seen the introduction of various classification methods that have been proven to be effective to identify typical features of many terrain types. Among the many regions of the study, the Hunshandake Sandy Land in Inner Mongolia, China stands out for its vast area of sandy land, variety of ground objects, and intricate structure, with more irregular characteristics than conventional land cover. Accounting for the particular surface features of the Hunshandake Sandy Land, an unsupervised classification method based on new decomposition and large-scale spectral clustering with superpixels (ND-LSC) is proposed in this study. Firstly, the polarization scattering parameters are extracted through a new decomposition, rather than other decomposition approaches, which gives rise to more accurate feature vector estimate. Secondly, a large-scale spectral clustering is applied as appropriate to meet the massive land and complex terrain. More specifically, this involves a beginning sub-step of superpixels generation via the Adaptive Simple Linear Iterative Clustering (ASLIC) algorithm when the feature vector combined with the spatial coordinate information are employed as input, and subsequently a sub-step of representative points selection as well as bipartite graph formation, followed by the spectral clustering algorithm to complete the classification task. Finally, testing and analysis are conducted on the RADARSAT-2 fully PolSAR dataset acquired over the Hunshandake Sandy Land in 2016. Both qualitative and quantitative experiments compared with several classification methods are conducted to show that proposed method can significantly improve performance on classification.

scholarly journals Lead Detection in Polar Oceans—A Comparison of Different Classification Methods for Cryosat-2 SAR Data

2018 ◽  
Vol 10 (8) ◽  
pp. 1190 ◽  
Author(s):  
Denise Dettmering ◽  
Alan Wynne ◽  
Felix Müller ◽  
Marcello Passaro ◽  
Florian Seitz
Keyword(s):  
Unsupervised Classification ◽  
Detection Algorithm ◽  
Classification Method ◽  
Correct Identification ◽  
Polar Regions ◽  
Classification Methods ◽  
Lead Detection ◽  
Radar Echoes ◽  
Polar Oceans ◽  
Sar Data

In polar regions, sea-ice hinders the precise observation of Sea Surface Heights (SSH) by satellite altimetry. In order to derive reliable heights for the openings within the ice, two steps have to be fulfilled: (1) the correct identification of water (e.g., in leads or polynias), a process known as lead classification; and (2) dedicated retracking algorithms to extract the ranges from the radar echoes. This study focuses on the first point and aims at identifying the best available lead classification method for Cryosat-2 SAR data. Four different altimeter lead classification methods are compared and assessed with respect to very high resolution airborne imagery. These methods are the maximum power classifier; multi-parameter classification method primarily based on pulse peakiness; multi-observation analysis of stack peakiness; and an unsupervised classification method. The unsupervised classification method with 25 clusters consistently performs best with an overall accuracy of 97%. Furthermore, this method does not require any knowledge of specific ice characteristics within the study area and is therefore the recommended lead detection algorithm for Cryosat-2 SAR in polar oceans.

Texture Image Segmentation Using Affinity Propagation and Spectral Clustering

2015 ◽  
Vol 29 (05) ◽  
pp. 1555009 ◽  
Author(s):  
Hui Du ◽  
Yuping Wang ◽  
Xiaopan Dong
Keyword(s):  
Image Segmentation ◽  
Spectral Clustering ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Computational Cost ◽  
Affinity Propagation ◽  
Texture Image ◽  
Texture Image Segmentation ◽  
Two Phases ◽  
Representative Points

Clustering is a popular and effective method for image segmentation. However, existing cluster methods often suffer the following problems: (1) Need a huge space and a lot of computation when the input data are large. (2) Need to assign some parameters (e.g. number of clusters) in advance which will affect the clustering results greatly. To save the space and computation, reduce the sensitivity of the parameters, and improve the effectiveness and efficiency of the clustering algorithms, we construct a new clustering algorithm for image segmentation. The new algorithm consists of two phases: coarsening clustering and exact clustering. First, we use Affinity Propagation (AP) algorithm for coarsening. Specifically, in order to save the space and computational cost, we only compute the similarity between each point and its t nearest neighbors, and get a condensed similarity matrix (with only t columns, where t << N and N is the number of data points). Second, to further improve the efficiency and effectiveness of the proposed algorithm, the Self-tuning Spectral Clustering (SSC) is used to the resulted points (the representative points gotten in the first phase) to do the exact clustering. As a result, the proposed algorithm can quickly and precisely realize the clustering for texture image segmentation. The experimental results show that the proposed algorithm is more efficient than the compared algorithms FCM, K-means and SOM.

scholarly journals Large-Scale Spectral Clustering Based on Representative Points

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Libo Yang ◽  
Xuemei Liu ◽  
Feiping Nie ◽  
Mingtang Liu
Keyword(s):  
Computational Complexity ◽  
Spectral Clustering ◽  
Large Scale ◽  
Cluster Structure ◽  
Original Data ◽  
Representative Point ◽  
Similarity Matrix ◽  
Clustering Methods ◽  
Assignment Method ◽  
Representative Points

Spectral clustering (SC) has attracted more and more attention due to its effectiveness in machine learning. However, most traditional spectral clustering methods still face challenges in the successful application of large-scale spectral clustering problems mainly due to their high computational complexity οn3, where n is the number of samples. In order to achieve fast spectral clustering, we propose a novel approach, called representative point-based spectral clustering (RPSC), to efficiently deal with the large-scale spectral clustering problem. The proposed method first generates two-layer representative points successively by BKHK (balanced k-means-based hierarchical k-means). Then it constructs the hierarchical bipartite graph and performs spectral analysis on the graph. Specifically, we construct the similarity matrix using the parameter-free neighbor assignment method, which avoids the need to tune the extra parameters. Furthermore, we perform the coclustering on the final similarity matrix. The coclustering mechanism takes advantage of the cooccurring cluster structure among the representative points and the original data to strengthen the clustering performance. As a result, the computational complexity can be significantly reduced and the clustering accuracy can be improved. Extensive experiments on several large-scale data sets show the effectiveness, efficiency, and stability of the proposed method.

scholarly journals Quantitative and Qualitative Comparison Study between Classification Methods on normal and abnormal (with a coronavirus ) lung images

2021 ◽  
Vol 26 (3) ◽  
pp. 10-16
Author(s):  
Halaa Kadhim hasan ◽  
Ayad A.AL-Ani ◽  
Noor Z. AlKhazraji
Keyword(s):  
Unsupervised Classification ◽  
Classification Method ◽  
Classification Methods ◽  
Comparison Study ◽  
Qualitative Properties ◽  
Qualitative Comparison ◽  
Different Populations ◽  
Quantitative Properties ◽  
Analysis Of Performance ◽  
Better Than

Classification is concerned with establishing criteria that can be used to identify or distinguish different populations of objects that appear in images. In this paper Supervised and unsupervised classification method applied on normal, abnormal (with a coronavirus) ct- lung images (which it took from Al shaikh zaeid Hospital)  to study the quantitative and qualitative properties of these two categories. The analysis of performance with default quantitative parameters revealed that (kurtosis, skewness, entropy, Stander deviation (STD), mean). We found that: Qualitative (as seen) of   abnormal lung images after applying  Supervisors classification are better than the qualitative of abnormal lung images after applying  unsupervisors classification to detect the virus with white color in the lower lobes of the lung.. from The quantitative Properties such as (kurtosis, skewness) of original lung images are similar in rising to resulted value after applying  Supervisors classification on it, so Supervisors method is better than unSupervisors method to distinguishing between normal and abnormal lung images.

scholarly journals Exploratory Item Classification Via Spectral Graph Clustering

2017 ◽  
Vol 41 (8) ◽  
pp. 579-599 ◽  
Author(s):  
Yunxiao Chen ◽  
Xiaoou Li ◽  
Jingchen Liu ◽  
Gongjun Xu ◽  
Zhiliang Ying
Keyword(s):  
Cluster Analysis ◽  
Spectral Clustering ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Latent Class ◽  
Clustering Algorithms ◽  
Eysenck Personality Questionnaire ◽  
Computationally Efficient ◽  
Computational Overhead ◽  
Spectral Clustering Algorithm

Large-scale assessments are supported by a large item pool. An important task in test development is to assign items into scales that measure different characteristics of individuals, and a popular approach is cluster analysis of items. Classical methods in cluster analysis, such as the hierarchical clustering, K-means method, and latent-class analysis, often induce a high computational overhead and have difficulty handling missing data, especially in the presence of high-dimensional responses. In this article, the authors propose a spectral clustering algorithm for exploratory item cluster analysis. The method is computationally efficient, effective for data with missing or incomplete responses, easy to implement, and often outperforms traditional clustering algorithms in the context of high dimensionality. The spectral clustering algorithm is based on graph theory, a branch of mathematics that studies the properties of graphs. The algorithm first constructs a graph of items, characterizing the similarity structure among items. It then extracts item clusters based on the graphical structure, grouping similar items together. The proposed method is evaluated through simulations and an application to the revised Eysenck Personality Questionnaire.

Sign in / Sign up

Export Citation Format

Share Document