Attribute Learning for SAR Image Classification

He, Chu; Liu, Xinlong; Kang, Chenyao; Chen, Dong; Liao, Mingsheng

doi:10.3390/ijgi6040111

Cited by 7 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BOVW is a well-known mid-level representation model which is originally inspired from Bag of Words model in text mining [23]- [25]. Bag of Words model represents each document with a histogram, corresponding to the frequency of each key word in the document [26], [27]. The resulting histograms can be utilized for various applications, including document categorization and subject detection.…”

Section: A Bag Of Visual Words (Bovw)modelmentioning

confidence: 99%

Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach

Asiyabi

Datcu

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recent advances in remote sensing technology have provided (very) high spatial resolution Earth Observation (EO) data with abundant latent semantic information. Conventional data processing algorithms are not capable of extracting the latent semantic information form these data and harness their full potential. As a result, semantic information discovery methods, based on data mining techniques, such as Latent Dirichlet Allocation (LDA) and Bag of Visual Words (BOVW) models, can discover the latent information. Despite their crucial rule, there are only a few studies in the field of semantic data mining for remote sensing applications. This study is focused on this shortage. Three different scenarios are used to evaluate the semantic information discovery in various remote sensing applications, including both optical and Synthetic Aperture Radar (SAR) data with different spatial resolutions. In the first scenario, semantic discovery method correlated the semantic perception of the user and machine to correct and enhance the user defined Ground Truth (GT) map in very high-resolution RGB data. The potential of the semantic discovery is evaluated for wildfire affected area detection in Sentinel-2 data in the second scenario. Finally, in the third scenario, the semantic discovery method is utilized to detect the misclassifications as well as the patches with ambiguous or multiple semantic labels in a Sentinel-1 SAR patch-based benchmark dataset, to enhance the robustness and accuracy of the annotation in the dataset. Our results in these three scenarios demonstrated the capability of the data mining-based semantic information discovery methods for various remote sensing applications.

show abstract

Section: A Bag Of Visual Words (Bovw)modelmentioning

confidence: 99%

Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach

Asiyabi

Datcu

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Gabor Wavelet filters works effectively on removing rotational and other motion effects from SAR images [6]. The features can be extracted based on two dimensional Gabor filters [7].These descriptors can be obtained from the convolution process of input image with Gabor wavelet filters. Then, the image patch obtained from the Gabor filter can be represented as histogram based on region level [8].…”

Section: Figure 2 Architecture Of Proposed Model Gabor Wavelet Featumentioning

confidence: 99%

Disaster management using Remote Sensing on Unsupervised Data

Kathiresan*,

Sayana

2019

IJITEE

View full text Add to dashboard Cite

One of the biggest challenges in real-world applications is recognizing various objects and the conditions of the land based on the natural disasters in a remote sensing image. Object recognition in remote sensing images is used to locate various geographical locations for monitoring and observing GIS information, but the accuracy is not satisfactory. This research considers it as a base problem and analyzes, and it is motivated to provide a better solution regarding classification accuracy. The main objective of this study is to design and implement a framework named Natural Disaster detection on Remote Sensing data (NDRSD) for detecting and classifying the objects from remote sensing images. The efficiency of the framework increased by applying various image processing stages such as Pre-processing, Image Enhancement, Object Detection, Bag-of-Words creation, and Training – Testing process. The bag-of-words process enables the user to maintain ground truth values for classifying the objects and improves the accuracy of classification. From the entire process, it notices that NDRSD is suitable for processing any RSD. The proposed framework experiments and results verified. By comparing the obtained results with the state-of-the-art methods and the performance is evaluated

show abstract

“…With the rapid increase in remote sensing imaging techniques over the past decade, a large amount of very high-resolution (VHR) remote sensing images are now accessible, thereby enabling us to study ground surfaces in greater detail [1][2][3][4][5]. Recent studies often adopt the bag-of-visual-words (BOVW) [6][7][8] or deep convolutional neural networks (DCNN) representation [9][10][11][12][13][14][15][16][17][18] associated with AdaBoost classifiers or support vector machine (SVM) classifiers to learn scene class models.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification

Deng

Sun

Zhou

2018

IJGI

View full text Add to dashboard Cite

Currently, huge quantities of remote sensing images (RSIs) are becoming available. Nevertheless, the scarcity of labeled samples hinders the semantic understanding of RSIs. Fortunately, many ground-level image datasets with detailed semantic annotations have been collected in the vision community. In this paper, we attempt to exploit the abundant labeled ground-level images to build discriminative models for overhead-view RSI classification. However, images from the ground-level and overhead view are represented by heterogeneous features with different distributions; how to effectively combine multiple features and reduce the mismatch of distributions are two key problems in this scene-model transfer task. Specifically, a semi-supervised manifold-regularized multiple-kernel-learning (SMRMKL) algorithm is proposed for solving these problems. We employ multiple kernels over several features to learn an optimal combined model automatically. Multi-kernel Maximum Mean Discrepancy (MK-MMD) is utilized to measure the data mismatch. To make use of unlabeled target samples, a manifold regularized semi-supervised learning process is incorporated into our framework. Extensive experimental results on both cross-view and aerial-to-satellite scene datasets demonstrate that: (1) SMRMKL has an appealing extension ability to effectively fuse different types of visual features; and (2) manifold regularization can improve the adaptation performance by utilizing unlabeled target samples.

show abstract

Attribute Learning for SAR Image Classification

Cited by 7 publications

References 26 publications

Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach

Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach

Disaster management using Remote Sensing on Unsupervised Data

Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification

Contact Info

Product

Resources

About