SAR sea-ice texture classification using discrete wavelet transform based methods

Yu, Qihao; Moloney, Cecilia; Williams, Felisha M.

doi:10.1109/igarss.2002.1026863

Cited by 13 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there was no representative dataset, and only several scenes were used in the early stage. Some machine learning methods such as wavelet transforms [47], [48], Bayes classifier [19], and Maximum likelihood [49] are introduced to classify sea ice and open water. With the completeness of dataset, methods based on Neural Network (NN) and Support Vector Machine (SVM) further improve the accuracy of classification.…”

Section: B Machine Learning Methodsmentioning

confidence: 99%

A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images

Zhang,

Deng,

Luo

et al. 2024

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

View full text Add to dashboard Cite

Automatic classification of sea ice and open water plays a vital role in climate change research, polar shipping, and other applications. Many deep learning-based methods are proposed to automatically classify sea ice and open water to address this issue. Even though these methods have achieved remarkable success, the noise phenomenon in SAR images still causes considerable limitations in the model performance.Meanwhile, these existing methods ignore multi-scale global information from large-scale SAR images which tends to produce misclassification. In this paper, we propose a novel Multi-scale Dual Attention Network (MSDA-Net) for the task. To tackle the first drawback, we introduce the information of relative position and high-pass filtering as two extra channels to reduce the noisy effects. Moreover, we propose a patch dual attention mechanism (PDAM) and embed it into the ConvNeXt blocks to capture the multi-channel and spatial features. To address the second problem, we propose a multi-scale spatial attention (MSSA) module to capture multi-scale global spatial information. The experiments show that the proposed method significantly outperforms state-of-the-art methods. In addition, comprehensive case studies are conducted, which verify the effectiveness of MSDA-Net in different SAR scenes.

show abstract

Section: B Machine Learning Methodsmentioning

confidence: 99%

A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images

Zhang,

Deng,

Luo

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…It consists of a single McCulloch-Pitts neuron with adjustable synaptic weights and bias (threshold), proved that if the patterns (vectors) used to train the perceptron are drawn from linearly separable classes, then the perceptron algorithm converges and positions the decision surface in the form of a hyper plane between the classes [6,8,9]. The proof of convergence of the algorithm is known as the perceptron convergence theorem.…”

Section: Bmentioning

confidence: 99%

Neural Network based classification for orthopedic conditions diagnosis using grey level co-occurrence probabilities

Jagapriya

Annapoorani

2011

2011 3rd International Conference on Electronics Computer Technology

View full text Add to dashboard Cite

Medical imaging has become a major tool in clinical experiments due to its ability in rapid diagnosis with visualization and quantitative assessment. Fractal and texture analysis are the computer techniques used to discriminate between the orthopedic conditions such as broken, dislocated and injured bones. The main focus is to perform texture segmentation and classification for the medical images. The textural features are extracted based on the grey level cooccurrence probabilities generated. In this paper, we have used the Back Propagation Algorithm of Artificial Neural Networks for segmentation and classification of the medical images. Neural Networks classification saves the radiologist time, increases accuracy and yield of diagnosis.

show abstract

“…Soh and Tsatsoulis, 1999;Clausi and Yue, 2004), wavelet transforms (e.g. Yu et al, 2002), and neural networks (e.g. Zakhvatkina et al, 2013;Ressel et al, 2015).…”

Section: Deep Learning For Sea Ice Problemsmentioning

confidence: 99%

Morphological approaches to understanding Antarctic Sea ice thickness

Mei¹

2020

View full text Add to dashboard Cite

SAR sea-ice texture classification using discrete wavelet transform based methods

Cited by 13 publications

References 2 publications

A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images

A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images

Neural Network based classification for orthopedic conditions diagnosis using grey level co-occurrence probabilities

Morphological approaches to understanding Antarctic Sea ice thickness

Contact Info

Product

Resources

About