Article
Remote Sensing
Jinjie Wang, Xiaoqing Wang, Lingxi Guo, Yanlang Xu, Zheng Lu, Bing Chen
Summary: In this paper, a parallel dual-branch SAR image change detection network based on clustering and segmentation was proposed to address the challenges in SAR image change detection. By combining the clustering and segmentation branches and using the double sparse dictionary discrimination algorithm, the influence of speckle noise can be suppressed while maintaining high accuracy.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Review
Environmental Sciences
Kazuo Ouchi, Takero Yoshida
Summary: In 1978, the SEASAT satellite launched the first civilian synthetic aperture radar (SAR) for monitoring oceans and studying land applications. Despite its short operational time, SEASAT-SAR provided valuable information on land and sea, paving the way for future spaceborne SAR programs and new technologies such as InSAR and PolSAR. This article reviews the imaging processes and analyses of oceanic data using SAR, InSAR, PolSAR, and AI, covering various phenomena including ocean waves, oil slicks, ship detection, and sea ice.
Article
Geochemistry & Geophysics
Fei Ma, Deliang Xiang, Kun Yang, Qiang Yin, Fan Zhang
Summary: As flood occurrences are unpredictable, labeling data in practice becomes difficult. To address this, a new assignment strategy called soft association is introduced for clustering in single-polarization SAR images to make the process differentiable. This enables the establishment of an end-to-end trainable semi-supervised clustering network for SAR flood detection, achieving similar performance with fewer labeled samples compared to existing methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Qihan Xu, Yunfan Xiang, Zhixiong Di, Yibo Fan, Quanyuan Feng, Qiang Wu, Jiangyi Shi
Summary: An end-to-end SAR image compression convolutional neural network (CNN) model based on a variational autoencoder is proposed in this study, leveraging joint transforms and residual blocks to enhance feature learning efficiency and improve reconstructed image quality, while optimizing compression quality with a conditioned entropy model and hyperprior network.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Ying-gang Zheng, Kai-tuo Qi, Hong-sheng Zhang
Summary: The development of deep learning and remote sensing has enabled the extraction of information about oceanic internal waves from massive data. A stripe segmentation algorithm based on Mask R-CNN is proposed to identify and locate the light and dark stripes of the waves. The width, direction angle, and polarity conversion time of the stripes can be efficiently obtained through the sector region separation and matching method.
GEOCARTO INTERNATIONAL
(2022)
Article
Engineering, Electrical & Electronic
Fatemeh Mahmoudi, Shahriar Baradaran Shokouhi, Gholamreza Akbarizadeh
Summary: This article explores the use of SAR imaging and deep neural networks for oil spill detection, finding that the U-NET network is the most accurate in identifying oil spills in SAR images. The authors increased the number of input images and trained two convolutional neural networks to achieve their results.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Jarrod Haas, Bernhard Rabus
Summary: This study examines the application of DL models in the SAR field, compares the effectiveness of different uncertainty estimation methods, and demonstrates the effectiveness of certain methods under specific circumstances through experiments. The approach of including predictions with lower softmax scores in the road prediction set to improve prediction quality is proposed, providing guidance for the development of deep learning systems in remote sensing.
Article
Engineering, Biomedical
Osama S. Faragallah, Heba M. El-Hoseny, Hala S. El-sayed
Summary: Image segmentation technology is important for computer-aided diagnostic systems to identify the area to be treated. This paper proposes an efficient approach using OTSU segmentation and K-means clustering segmentation in different transform domains to localize brain tumor area. The proposed enhanced segmentation approaches show high precision and reliability in brain tumor localization.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Jason M. Merlo, Jeffrey A. Nanzer
Summary: This article presents a low-frequency SAR radar for automotive use and showcases the opportunity to infer landmarks through measurements of co-polarized and cross-polarized scattering.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Geochemistry & Geophysics
Junjun Yin, Tao Wang, Yanlei Du, Xiyun Liu, Liangjiang Zhou, Jian Yang
Summary: In this study, the SLIC clustering function was modified to adapt to the characteristics of polarimetric SAR images, with a new initialization method and the embedding of four classic statistical distances. Comparison with other algorithms showed significant improvements in segmentation results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Cao Zeng, Jun Zhang, Shidong Li, Shengqi Zhu, Jingwei Xu
Summary: This article introduces the phase error problem caused by high-frequency vibrations in rotating synthetic aperture radar (ROSAR) imaging, and proposes a new ROSAR imaging procedure to compensate for this phase error.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Yuri Alvarez Lopez, Jaime Laviada, Ana Arboleya, Fernando Las-Heras
Summary: Synthetic aperture radar (SAR)-based microwave imaging systems are widely used in various applications. The scanning speed is a crucial factor in SAR imaging systems, and widening the distance between measurements can increase it. However, this causes the presence of grating lobes that degrade the quality of microwave SAR images. To address this issue, a novel methodology is proposed in this study, which incorporates the amplitude and phase of the field radiated by the transmitting and receiving antennas in the backpropagation imaging algorithm. This method exploits the directive pattern of the antennas to reduce the level of grating lobes in SAR images.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Arnold D. Kim, Chrysoula Tsogka
Summary: In this study, we propose a dispersive point target model based on scattering and develop a synthetic aperture imaging method to identify and recover the positions and frequency dependent reflectivities of these targets. Results show that we can detect, recover the approximate locations, and acquire the radar cross-section of dispersive point targets, providing opportunities to classify important differences between multiple targets.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2023)
Article
Computer Science, Artificial Intelligence
Wenhua Zhang, Licheng Jiao, Fang Liu, Shuyuan Yang, Jia Liu
Summary: In this paper, a novel unsupervised change detection method based on adaptive Contourlet fusion and fast non-local clustering is proposed for multi-temporal SAR images. The method uses Contourlet fusion and fuzzy clustering to generate a binary image indicating changed regions, and then applies fast non-local clustering to classify the fused image.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Geochemistry & Geophysics
Lapo Miccinesi, Alberto Michelini, Massimiliano Pieraccini
Summary: This article proposes an acquisition modality and image processing technique to mitigate blurring in GBSAR images caused by moving clutter. By filtering out high-frequency clutter and using high-frequency sampling, the authors have demonstrated the effectiveness of these methods in a realistic quarry scenario.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)