Article
Engineering, Electrical & Electronic
Xin Zhang, Chunlei Huo, Nuo Xu, Hangzhi Jiang, Yong Cao, Lei Ni, Chunhong Pan
Summary: This study introduces a multitask learning-based object detector (MTL-Det) to improve ship detection performance in SAR images by modeling the problem as three cooperative tasks and utilizing auxiliary subtasks to enhance feature learning. The approach effectively addresses the challenges posed by speckle noise in SAR images and outperforms traditional single-task-based object detectors.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Biao Hou, Zitong Wu, Bo Ren, Zhonghua Li, Xianpeng Guo, Shuang Wang, Licheng Jiao
Summary: A semisupervised SAR ship detection network, SCLANet, is proposed in this study, which improves the algorithm performance by utilizing unlabeled data. SCLANet trains the unlabeled data through consistency learning and achieves high accuracy in ship detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Nanjing Yu, Haohao Ren, Tianmin Deng, Xiaobiao Fan
Summary: A lightweight object detection framework called MHASD is proposed for ship detection in SAR imagery. It utilizes multiple hybrid attention mechanisms to reduce complexity without sacrificing detection precision. Experimental results demonstrate that MHASD achieves a good balance between detection speed and precision.
Article
Remote Sensing
Kai Zhao, Yan Zhou, Xin Chen, Bing Wang, Yong Zhang
Summary: Research on ship detection in Synthetic Aperture Radar (SAR) images has led to the development of a detector that does not require pre-training, using a unique network structure and feature handling strategy to successfully address the detection of small and multi-scale targets.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2021)
Article
Environmental Sciences
Hao Shi, Zhonghao Fang, Yupei Wang, Liang Chen
Summary: An adaptive sample assignment strategy is proposed to select high-quality positive samples based on knowledge learned from regression and classification branches, and a regression guided loss is introduced to further guide the detector in selecting high-quality positive samples. Additionally, a feature aggregation enhancement pyramid network is proposed to enhance feature representations and reduce false alarms.
Article
Engineering, Aerospace
Zhaocheng Wang, Ruonan Wang, Jiaqiu Ai, Huanxin Zou, Jun Li
Summary: Due to the large sizes of SAR images, traditional sliding window-based ship detection methods suffer from high computation redundancy and numerous false alarms. To address this issue, a novel ship detection method called global and local context-aware ship detector is proposed. This method utilizes global and local context information to select necessary subimages and suppress false alarms. Experimental results demonstrate that the proposed method outperforms traditional deep learning methods in terms of precision and efficiency.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Qi Hu, Shaohai Hu, Shuaiqi Liu, Shuwen Xu, Yu-Dong Zhang
Summary: Deep learning-based ship detection methods have achieved great success in SAR images, but still face challenges from imaging mechanism interference, speckle noise, and clutter. Existing algorithms often overlook pixel-level information. To improve detection accuracy, we propose a novel ship detection method based on FINet, which integrates object-level and pixel-level information.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Min Huang, Tianen Liu, Yazhou Chen
Summary: In this study, a novel two-stage detector called CViTF-Net is proposed to detect small ship targets in complex SAR images. The detection performance of CViTF-Net is enhanced through the design of a pyramid structured CViT backbone, a Gaussian prior discrepancy assigner, and a level synchronized attention mechanism. Experimental results show that CViTF-Net achieves the highest comprehensive evaluation results for the LS-SSDD-v1.0 dataset, demonstrating its effectiveness in enhancing the detection performance for small ship targets in complex scenes.
Article
Computer Science, Artificial Intelligence
Xueqian Wang, Dong Zhu, Gang Li, Xiao-Ping Zhang, You He
Summary: This paper proposes a new method for fusion of spaceborne and airborne SAR images based on the target proposal and the copula theory (TPCT), which improves the target-to-clutter ratios of composite images and enhances ship detection performance. Experiment results using measured SAR data show that the TPCT fusion method outperforms other commonly used image fusion methods in ship detection tasks.
INFORMATION FUSION
(2022)
Article
Environmental Sciences
Peder Heiselberg, Kristian A. Sorensen, Henning Heiselberg, Ole B. Andersen
Summary: Maritime surveillance of the Arctic region is increasingly important, and this study successfully detects and classifies ships and icebergs using SAR satellite data. A large annotated dataset is constructed, and a new convolutional neural network achieves state-of-the-art performance.
Article
Geochemistry & Geophysics
Leonardo De Laurentiis, Cathleen E. Jones, Benjamin Holt, Giovanni Schiavon, Fabio Del Frate
Summary: This study uses uninhabited aerial vehicle SAR data to investigate oil slick classification within a deep learning framework, evaluating the capabilities of deep architectures to provide a reliable and accurate three-state classifier for separating mineral oil films from biogenic slicks and clean sea. By exploiting parameters sensitive to dielectric constant and ocean wave damping properties, as well as leveraging CNNs' capability for learning nonlinear features and patterns, significant classification accuracy is achieved, with values up to 0.91, 0.94, 0.98, and 0.99 under real-world spill acquisition conditions.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
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
Engineering, Electrical & Electronic
Yu Zhang, Xueqian Wang, Zhizhuo Jiang, Gang Li, You He
Summary: This article proposes a lightweight center-based detector for multiscale ship detection in SAR images. The detector utilizes a multilevel auxiliary supervision (MLAS) structure and combines semantic features with different levels. Experimental results demonstrate that the proposed detector achieves comparable detection accuracy while significantly reducing the computation burden.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Shuang Yang, Wentao An, Shibao Li, Shuaiying Zhang, Bin Zou
Summary: This letter proposes an anchor-free ghost feature extraction and cross-scale interaction network (GFECSI-Net) for ship detection in synthetic aperture radar (SAR) images. It achieves improved detection performance without increasing the number of parameters or network complexity. The use of a multiscale adaptive feature pyramid network (MSAFPN), a selective efficient channel attention module (SECAM), and a GPU-efficient backbone contributes to the superior detection performance of GFECSI-Net.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Jindong Zhang, Weixing Sheng, Hairui Zhu, Shanhong Guo, Yubing Han
Summary: A new marine SAR ship detection network called MLBR-YOLOX is proposed in this article, which includes a standalone spatial patch detector module for pre-detecting ship positions and filtering sea backgrounds, and a deep spatial feature detector module for reducing computational cost. Experimental results show that MLBR-YOLOX achieves comparable detection performance to YOLOX, but with much lower computational complexity.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Shaohua Qiu, Gongjian Wen, Zhipeng Deng, Yaxiang Fan, Bingwei Hui
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2017)
Article
Geography, Physical
Zhipeng Deng, Hao Sun, Shilin Zhou, Juanping Zhao, Lin Lei, Huanxin Zou
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2018)
Article
Computer Science, Information Systems
Zhipeng Deng, Hao Sun, Shilin Zhou
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2018)
Article
Computer Science, Information Systems
Juanping Zhao, Weiwei Guo, Zenghui Zhang, Wenxian Yu
SCIENCE CHINA-INFORMATION SCIENCES
(2019)
Article
Geochemistry & Geophysics
Juanping Zhao, Mihai Datcu, Zenghui Zhang, Huilin Xiong, Wenxian Yu
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2019)
Article
Biochemistry & Molecular Biology
Lei Yuan, Juanping Zhao, Songkun Zhao, Tianyi Dong, Ruitong Dong, Dongyue Liu, Enlong Ma, Yanchun Li
Summary: This study synthesized a novel CATs inhibitor, ASPER-29, and demonstrated its ability to block the metastasis of pancreatic cancer cells by inhibiting the activity of CAT-L and CAT-S.
CHEMICO-BIOLOGICAL INTERACTIONS
(2022)
Article
Chemistry, Medicinal
Haoqiang Huang, Yi Zhang, Xiaohong Xu, Yongzheng Liu, Juanping Zhao, Lili Ma, Jie Lei, Wentao Ge, Ning Li, Enlong Ma, Yanchun Li, Lei Yuan
Summary: Currently, the migration and invasion of cancer cells remain the main factors of poor prognosis in the majority of cancer patients. Developing an effective antimetastatic agent is crucial for cancer therapy. Our recent research revealed that a compound B1a derived from asperphenamate showed the strongest inhibitory activity against Cat L and S in metastatic pancreatic cancer cells, indicating its potential as an antimetastatic agent.
BIOORGANIC & MEDICINAL CHEMISTRY LETTERS
(2023)
Article
Geochemistry & Geophysics
Mihai Datcu, Zhongling Huang, Andrei Anghel, Juanping Zhao, Remus Cacoveanu
Summary: This article proposes a new paradigm for explainability in SAR data, using explainable data transformations and AI methods to gain a better understanding and knowledge feedback.
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoxing Wang, Jiale Lin, Juanping Zhao, Xiaokang Yang, Junchi Yan
Summary: This paper introduces an efficient framework, EAutoDet, which can discover practical network architectures for object detection in a relatively short time. By constructing a supernet and using differentiable methods, the discovered architectures are shown to be effective and efficient through extensive experiments on multiple datasets.
COMPUTER VISION, ECCV 2022, PT XX
(2022)
Article
Engineering, Electrical & Electronic
Ning Liao, Mihai Datcu, Zenghui Zhang, Weiwei Guo, Juanping Zhao, Wenxian Yu
Summary: This study focuses on recognizing unknown classes and analyzing the separability of SAR datasets in open set conditions. The SAR separability analyzer (SAR-SA) and datasetwise separability index (DSI) and classwise separability index (CSI) are proposed as effective indicators of the difficulty of SAR classification datasets. Experimental results show that datasets in open set conditions are more challenging, with lower separability between classes.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Noman Mustafa, Juanping Zhao, Zeyu Liu, Zenghui Zhang, Wenxian Yu
IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
(2020)
Article
Engineering, Electrical & Electronic
Juanping Zhao, Zenghui Zhang, Wei Yao, Mihai Datcu, Huilin Xiong, Wenxian Yu
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2020)
Proceedings Paper
Geosciences, Multidisciplinary
Juanping Zhao, Mihai Datcu, Zenghui Zhang, Huilin Xiong, Wenxian Yu
2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)
(2019)