相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Engineering, Electrical & Electronic
Lin Bai et al.
Summary: This article proposes a novel SAR ship detection network called FEPS-Net, which aims to solve the challenges in ship detection in optical remote sensing images. The network utilizes a feature enhancement pyramid and a shallow feature reconstruction module to enhance weak signals and detect small ships. Experimental results demonstrate the advantages of FEPS-Net in SAR ship detection.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Chemistry, Analytical
Yuanzhou Zheng et al.
Summary: In this study, a Sine chaos mapping-based improved sparrow search algorithm (SSA) is proposed to optimize the BP neural network for trajectory prediction of inland river vessels. The Sine-SSA-BP model effectively improves the initialized population of uniform distribution and reduces premature convergence. The test results show that the Sine-SSA-BP neural network has higher prediction accuracy and better stability compared to conventional LSTM and SVM, especially in predicting corners, which aligns well with real ship navigation trajectories.
Article
Environmental Sciences
Muhammad Yasir et al.
Summary: Synthetic aperture radar (SAR) imaging is crucial for ship identification in maritime industry. However, challenges such as complex background interferences, ship feature variations, and indistinct characteristics can hamper accuracy improvements. This study proposes an upgraded YOLOv5s technique with enhanced backbone and neck sections to achieve high identification rates. Experimental results using SAR ship detection datasets and satellite images demonstrate the superior performance of the suggested model compared to benchmark models, indicating its applicability for maritime surveillance.
FRONTIERS IN MARINE SCIENCE
(2023)
Review
Computer Science, Artificial Intelligence
Muhammad Yasir et al.
Summary: This study presents a systematic literature review on ship detection by SAR images, highlighting the current research status, limitations, and challenges in the field. It emphasizes the need for further research on deep learning approaches and the development of an authentic process for ship detection using SAR data.
Article
Multidisciplinary Sciences
Yuanzhou Zheng et al.
Summary: This paper proposes a ship target detection algorithm MC-YOLOv5s based on YOLOv5s to tackle the problems of large parameters, high computation quantity, poor real-time performance, and high requirements for memory and computing power in the current ship detection model. Experimental results show that compared with the original YOLOv5s algorithm, MC-YOLOv5s reduces the number of parameters by 6.98 MB and increases the mAP by about 3.4%, and it also outperforms other lightweight detection models.
Article
Environmental Sciences
Nanjing Yu et al.
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
Green & Sustainable Science & Technology
Ananya Sonkar et al.
Summary: In this study, Sentinel-1 and Sentinel-2 datasets are used to detect vessels in the Gulf of Suez and assess the usefulness of dual-pol spaceborne SAR datasets in ship detection. The results show that Sentinel-1 images are more effective than Sentinel-2 images due to their all-weather capability, and ship detection accuracy is improved with dual polarization.
Article
Engineering, Electrical & Electronic
Zhengjie Jiang et al.
Summary: With the development of deep learning technology, convolutional neural networks have made significant progress in SAR ship detection, but still face challenges posed by background noise interference and inadequate appearance features of small-scale objects. To address these issues, a small ship detection algorithm for SAR images is proposed, which combines a coordinate-aware mixed attention mechanism and a spatial semantic joint context method. The experiments conducted on the LS-SSDD-v1.0 and the HRSID dataset demonstrate the effectiveness of the proposed methods, achieving average precisions of 77.23% and 90.85% respectively.
Article
Engineering, Electrical & Electronic
Yicheng Gong et al.
Summary: Synthetic aperture radar images have become the latest high-resolution imaging equipment for monitoring the Earth 24/7. The proposed SSPNet utilizes small-target-augmentation strategies and modules such as CAM, SEM, and SSM to improve ship detection in complex environments. The model achieves a superior performance with an average precision (AP(50)) of 91.57% on the SSDD dataset.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Jindong Zhang et al.
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)
Proceedings Paper
Computer Science, Artificial Intelligence
Chien-Yao Wang et al.
Summary: Real-time object detection is an important research topic in computer vision, and the development of new approaches in architecture optimization and training optimization has led to two related research topics. To address these topics, a trainable solution combining flexible and efficient training tools, proposed architecture, and compound scaling method is proposed. YOLOv7 outperforms all known object detectors in terms of speed and accuracy, achieving the highest AP accuracy of 56.8% among real-time object detectors with 30 FPS or higher on GPU V100.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR
(2023)
Article
Geochemistry & Geophysics
Shuang Yang et al.
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, Marine
Chengjie Zong et al.
Summary: This paper presents an efficient method for cell guide accuracy inspection in cargo holds using a 3D scanner. The method uses an improved 3D point cloud segmentation model for segmentation and fitting of the container ship's cell guide structure. The accuracy of the method is verified by comparing it with measured data.
Article
Engineering, Civil
Miao Yang et al.
Summary: This article reports a convolutional neural network (CNN)-based inception-attention network (IA-Net) model for classifying underwater images from natural images. By simulating the visual correlation mechanism of images taken from special environments, the importance of context background in addition to salient objects is demonstrated. The IA-Net achieves high accuracy in underwater image classification and outperforms other networks in distinguishing underwater images from similar nonunderwater images.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2022)
Article
Environmental Sciences
Nan Su et al.
Summary: In this paper, a novel ship detection method called SII-Net is proposed to enhance the detection performance of small ships in SAR images. The method utilizes a channel-location attention mechanism and a high-level features enhancement module to improve the accuracy of detection. Experimental results on public datasets show that the proposed method outperforms state-of-the-art detectors, especially for small-sized targets.
Article
Chemistry, Multidisciplinary
Marzena Malyszko
Summary: The article discusses methods of ships assessment for search and rescue action at sea. It explores the use of Multi-Criteria Decision Analysis (MCDA) and fuzzy logic to evaluate and rank ships based on various parameters and data. The author develops fuzzy rules and presents a simulation of ship study using fuzzy logic. The article also introduces the main principles of a decision support system (DSS) for ship selection in search and rescue operations.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Syed Sahil Abbas Zaidi et al.
Summary: This article introduces the task of object detection and explores recent developments in deep learning-based object detectors. The article also provides a concise overview of benchmark datasets, evaluation metrics, and prominent backbone architectures used in detection, as well as lightweight classification models used on edge devices. Lastly, the article compares the performances of these architectures on multiple metrics.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Environmental Sciences
Runfan Xia et al.
Summary: This paper proposes a visual transformer framework based on contextual joint-representation learning for improving the accuracy of SAR image target detection. The framework combines the global contextual information perception of transformers and the local feature representation capabilities of CNNs. It introduces new modules and network designs to enhance the characterizability of multiscale SAR targets. Experimental results show that the proposed method achieves state-of-the-art accuracy.
Article
Chemistry, Multidisciplinary
Long Qian et al.
Summary: This paper introduces the use of deep long short-term memory network framework and genetic algorithm to predict the trajectory of inland water ships. The experimental results show that this method can effectively improve the accuracy and speed of trajectory prediction.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
Xiuqin Li et al.
Summary: In this paper, a novel deep learning network for SAR ship detection, named attention-guided balanced feature pyramid network (A-BFPN), is proposed to better exploit semantic and multilevel complementary features. Experimental results show that the proposed method is superior to the existing algorithms, especially for multi-scale small ship targets under complex background.
Article
Construction & Building Technology
Zijie Lin et al.
Summary: This paper presents a novel method based on Transformer and self-supervised learning for pavement anomaly detection. Experimental results show that self-supervised learning improves performance and Transformer is applicable in this field. By building a facial recognition-like framework, performance can be enhanced without retraining.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Engineering, Civil
Jing Chen et al.
Summary: In this study, a DMF method based on disparity depths is proposed to address the low accuracy issue in transportation detection of long-distance small objects. By mapping different disparity regions to 2D candidate regions, the small-object detection problem is solved. The method clusters disparity maps of different depths and performs feature fusion of different scales. Experimental results on two datasets demonstrate that the DMF method can improve the detection accuracy of small objects.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Analytical
Nana Li et al.
Summary: This study proposes a SAR ship target detection CFAR algorithm based on the attention contrast mechanism of intensity and texture feature fusion, which effectively enhances targets and suppresses background, as well as adapts well to clutter background with an adaptive CFAR method based on generalized Gamma distribution. Experimental results demonstrate that the method has a relatively high detection rate and low false alarm rate in complex marine environments, improving target-to-clutter ratio significantly.
Proceedings Paper
Imaging Science & Photographic Technology
V. Ganesh et al.
Summary: Automatic ship classification and detection is an interesting research field that plays an important role in maritime security. This study presents a novel Deep Learning method using satellite images and TensorFlow object detection API for ship detection. The research also utilizes Transfer Learning technique with a specific algorithm to train the model using MASATI-v2 dataset.
THIRD INTERNATIONAL CONFERENCE ON IMAGE PROCESSING AND CAPSULE NETWORKS (ICIPCN 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Weihao Yu et al.
Summary: Recent research has shown that transformers can be replaced with spatial MLPs in computer vision tasks and still perform well. The proposed PoolFormer model achieved competitive performance using a simple spatial pooling operator and emphasized the importance of MetaFormer in achieving superior results.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhuang Liu et al.
Summary: The development of visual recognition has gone through stages from ConvNets to ViTs and then to hybrid approaches. In this work, the design of a pure ConvNet is reexamined and several key components are discovered, resulting in the construction of the ConvNeXt model series. These models compete with Transformers in terms of accuracy and performance while maintaining the simplicity and efficiency of ConvNets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Engineering, Electrical & Electronic
Shuang Yang et al.
Summary: This paper introduces an improved fully convolutional one-stage object detector (Improved-FCOS) to address ship detection in synthetic aperture radar (SAR) images. The method proposes a multilevel feature attention mechanism, a feature refinement and reuse module, and a head improvement module to enhance the accuracy and robustness of ship detection. Experimental results demonstrate that Improved-FCOS achieves the best detection performance on multiple datasets.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Engineering, Aerospace
Jiaqiu Ai et al.
Summary: Proposed BTS-RCFAR detector improves detection performance in complex ocean scenes by reducing false alarm rate and increasing detection rate through bilateral-trimmed statistics.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2021)
Article
Environmental Sciences
Tianwen Zhang et al.
Summary: A novel quad feature pyramid network (Quad-FPN) is proposed for ship detection from synthetic aperture radar (SAR) imagery, with extensive ablation studies conducted to confirm its effectiveness. Experiments on five datasets show Quad-FPN's optimal performance compared to other 12 competitive CNN-based SAR ship detectors. Additionally, satisfactory detection results in actual ship detection further demonstrate Quad-FPN's practical application value in marine surveillance.
Review
Environmental Sciences
Tianwen Zhang et al.
Summary: SSDD is the first open dataset widely used for research on ship detection from SAR imagery based on deep learning, with 46.59% of public reports confidently choosing it. However, the initial version's coarse annotations and ambiguous usage standards hinder fair methodological comparisons and effective academic exchanges. To address these challenges, SSDD will be officially released in three versions to cater to different research needs.
Article
Engineering, Electrical & Electronic
Wei Bao et al.
Summary: Deep learning methods have made significant progress in ship detection in SAR images. Pretraining techniques are adopted to support deep neural networks-based SAR ship detectors due to scarce labeled SAR images. However, directly leveraging ImageNet pretraining is hard to obtain a good ship detector because of different imaging perspectives and geometry. Proposed methods, including an optical ship detector (OSD) pretraining technique and an optical-SAR matching (OSM) pretraining technique, aim to address these issues and improve ship detection results. Combining predictions from these two detectors through weighted boxes fusion further enhances detection performance, achieving state-of-the-art results in ship detection in SAR images.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Shunjun Wei et al.
Article
Environmental Sciences
Tianwen Zhang et al.
Article
Geochemistry & Geophysics
Zhao Lin et al.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2019)
Article
Chemistry, Analytical
Wensheng Chang et al.
Article
Chemistry, Analytical
Yamin Wang et al.
Article
Engineering, Electrical & Electronic
Tao Liu et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2019)
Article
Engineering, Electrical & Electronic
Shiyuan Chen et al.
SIGNAL IMAGE AND VIDEO PROCESSING
(2019)
Article
Remote Sensing
Yuanyuan Wang et al.
REMOTE SENSING LETTERS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jifeng Dai et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)