检索结果-内蒙古大学图书馆

LHSDNet: A Lightweight and High-Accuracy SAR ship object detection Algorithm

REMOTE SENSING 2024年第23期16卷 4527-4527页

作者： Dai, Dahai Wu, Hao Wang, Yue Ji, Penghui Natl Univ Def Technol Coll Elect Sci State Key Lab Complex Electromagnet Environm Effec Changsha 410073 Peoples R China Inst Dataspace Hefei 230000 Peoples R China

At present, the majority of deep learning-based ship object detection algorithms concentrate predominantly on enhancing recognition accuracy, often overlooking the complexity of the algorithm. These complex algorithms demand significant computational resources, making them unsuitable for deployment on resource-constrained edge devices, such as airborne and spaceborne platforms, thereby limiting their practicality. With the purpose of alleviating this problem, a lightweight and high-accuracy synthetic aperture radar (SAR) ship image detection network (LHSDNet) is proposed. Initially, GhostHGNetV2 was utilized as the feature extraction network, and the calculation amount of the network was reduced by GhostConv. Next, a lightweight feature fusion network was designed to combine shallow and deep features through lightweight convolutions, effectively preserving more information while minimizing computational requirements. Lastly, the feature extraction module was integrated through parameter sharing, and the detection head was lightweight to save computing resources further. The results from our experiments demonstrate that the proposed LHSDNet model increases mAP50 by 0.7% in comparison to the baseline model. Additionally, it illustrates a pronounced decrease in parameter count, computational demand, and model file size by 48.33%, 51.85%, and 41.26%, respectively, when contrasted with the baseline model. LHSDNet achieves a balance between precision and computing resources, rendering it more appropriate for edge device implementation.

关键词： remote sensing images synthetic aperture radar (SAR) lightweight model deep learning ship object detection

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention-enabled ship object detection with Electro-optical Image 22

Coordinate Attention-enabled Ship Object Detection with Elec...

引用

Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition

作者： Hongbin Xu Xiantao Jiang Tao Yin Qi Cen Zhijian Zhang Tian Song F.Richard Yu Dept.Information Engineering Shanghai Maritime University China Ningbo Special Equipment Inpection and Research Institute China Dept. Electrical and Electronics Engineering Tokushima University Japan Dept. Systems and Computer Engineering Carleton University Canada

ISBN: (纸本)9781450397056

shipping safety is one of the factors restricting the development of navigation. In particular, the route near the shore is prone to unknown risks due to the existence of multiple types of ships, the density of ships, the shielding between ships, and other reasons. This paper presents a method for detecting medium-range ships, which can improve security for ships. This method is based on the You Only Look Once Version 5 network (YOLOv5). To improve the accuracy, the coordinate attention model is integrated into the detection network. The main research content and experimental work of this paper are as follows. Firstly, the YOLOv5 network and spatial attention mechanism are analyzed. Then, detection experiments were carried out based on YOLOv5 and Singapore Maritime Data Set (SMD). Then, the coordinate attention model was used to improve the network. Finally, by adjusting training parameters and improving attention, the mAP of test results of the object detection network reaches 73%, and the feasibility of object detection of the YOLOv5 algorithm with coordinate attention is confirmed.

关键词： ship object detection Coordinate Attention Mechanism You Only Look Once Version 5 (YOLOv5)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cascade R-CNN for Multiscale object detection in Dense Scenes From SAR Images

引用

IEEE SENSORS JOURNAL 2024年第12期24卷 20143-20153页

作者： Chai, Bosong Nie, Xuan Zhou, Qifan Zhou, Xingyu Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China Northwestern Polytech Univ Sch Software Xian 710072 Peoples R China

A synthetic aperture radar (SAR) has the characteristics of all-weather and all-time operation, which can achieve uninterrupted detection of targets on the sea surface. Currently, small-sized ship targets in SAR images are difficult to detect in complex backgrounds due to limited pixel information, unclear azimuth information, and weak signals after imaging. This makes it challenging to detect small-scale ship targets in SAR images. In this article, we proposed an enhanced Cascade R-CNN algorithm for detecting small-sized ship targets in complex backgrounds of SAR images. To enhance the multiscale expression ability of the network, we introduce Res2Net with richer multiscale information and establish a spatial enhancement module to increase the weight of the ship target in the aspect map. In addition, a bidirectional feature pyramid structure is constructed to fuse the feature maps output at numerous stages, making the semantic information contained in the feature maps more abundant. To improve the accuracy of the target boundary in dense areas, we introduce a generalized focal loss (GFL) function and improve the output layer prediction network. Experiments conducted on the SAR-ship-Dataset show that our algorithm achieves precision, recall, F1, and mAP of 92.6%, 92.4%, 92.8%, and 92.5%, respectively. The proposed method exhibits significant advantages over previous advanced methods in ship detection of varying scales in dense scenes. The code will be made available on GitHub.

关键词： Radar polarimetry Marine vehicles Feature extraction Convolution Sensors Detectors Synthetic aperture radar Hybrid attention ship object detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

object detection of inland waterway ships based on improved SSD model

引用

shipS AND OFFSHORE STRUCTURES 2023年第8期18卷 1192-1200页

作者： Yang, Yang Chen, Pengyu Ding, Kaifa Chen, Zhuang Hu, Kaixuan Dalian Univ Technol Sch Naval Architecture & Ocean Engn Dalian Peoples R China

To realise the rational utilisation of inland waterway resources, the intelligent identification method based on Convolutional Neural Network (CNN) is used to track and monitor the ships. Introducing the Repulsion Loss function and Soft-NMS algorithm to improve model, improve the detection precision of the partially occluded ships. The Feature Pyramid Networks (FPN) is used to realise the fusion of semantic information and spatial information of feature map to solve the problem of difficult detection of small object ships. Three up-sampling methods are used to extend and smooth the feature map. Through the above multiple algorithm improvements, the partial occlusion ships and small object ships in inland waterways are effectively detected.

关键词： ship object detection loss function Soft-NMS feature pyramid up-sampling

来源：评论

学校读者我要写书评

暂无评论

Stepwise Attention-Guided Multiscale Fusion Network for Lightweight and High-Accurate SAR ship detection

引用

REMOTE SENSING 2024年第17期16卷 3137页

作者： Wang, Chunyuan Cai, Xianjun Wu, Fei Cui, Peng Wu, Yang Zhang, Ye Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201602 Peoples R China Shanghai Inst Satellite Engn Shanghai 200240 Peoples R China Dongshin Univ Dept Comp Engn Naju 58245 South Korea Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China

Many exceptional deep learning networks have demonstrated remarkable proficiency in general object detection tasks. However, the challenge of detecting ships in synthetic aperture radar (SAR) imagery increases due to the complex and various nature of these scenes. Moreover, sophisticated large-scale models necessitate substantial computational resources and hardware expenses. To address these issues, a new framework is proposed called a stepwise attention-guided multiscale feature fusion network (SAFN). Specifically, we introduce a stepwise attention mechanism designed to selectively emphasize relevant information and filter out irrelevant details of objects in a step-by-step manner. Firstly, a novel LGA-FasterNet is proposed, which incorporates a lightweight backbone FasterNet with lightweight global attention (LGA) to realize expressive feature extraction while reducing the model's parameters. To effectively mitigate the impact of scale and complex background variations, a deformable attention bidirectional fusion network (DA-BFNet) is proposed, which introduces a novel deformable location attention (DLA) block and a novel deformable recognition attention (DRA) block, strategically integrating through bidirectional connections to achieve enhanced features fusion. Finally, we have substantiated the robustness of the new framework through extensive testing on the publicly accessible SAR datasets, HRSID and SSDD. The experimental outcomes demonstrate the competitive performance of our approach, showing a significant enhancement in ship detection accuracy compared to some state-of-the-art methods.

关键词： ship object detection multiscale feature fusion synthetic aperture radar (SAR) attention mechanism lightweight model FasterNet

来源：评论

学校读者我要写书评

暂无评论

SP-YOLOX:A lightweight ship target detection algorithm based on remote sensing images

SP-YOLOX:A lightweight ship target detection algorithm based...

引用

第43届中国控制会议

作者： Gang Li Xuanhong Wang Dou Zhang Ziyang Wu Yun Xiao School of Telecommunication and Information Engineering Xi'an University of Posts and Telecommunications School of Information Science and Technology Northwest University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The detection of ships is a crucial and formidable task in remote sensing applications, with the accurate identification of ship targets playing a pivotal role in the advancement of maritime military forces and ensuring the safety of maritime navigation. However, the current ship detection model faces challenges due to its extensive parameter count,substantial computational requirements, and deployment limitations in resource-constrained environmental ***, we propose a novel and efficient lightweight object detection algorithm, SP-YOLOX. Firstly, a novel lightweight feature extraction module, PSCLay, is devised to ensure the efficacy of the feature extraction network while simultaneously reducing the parameter count and computational burden of the backbone network. Secondly, the FOCUS layer in the backbone network head incorporates a PSA attention mechanism to enhance spatial location information retention and capture features at various scales more effectively. Additionally, depth separable convolution is introduced in the detection header to mitigate model complexity. The training and testing were conducted on the remote sensing datasets DIOR and NWPU VHR-10. The experimental results demonstrate that our model, SP-YOLOX, has a size of 3.21M and a computational weight of 3.67 G. In comparison to the original YOLOX baseline model, although there is a reduction in accuracy by 1.8%, we achieve a decrease in parameter count by 36.3% and computational workload by 43.1%.

关键词： lightweight ship object detection YOLOX remote sensing

来源：评论

学校读者我要写书评

暂无评论

An Anchor-Free Method Based on Adaptive Feature Encoding and Gaussian-Guided Sampling Optimization for ship detection in SAR Imagery

引用

REMOTE SENSING 2022年第7期14卷 1738页

作者： He, Bokun Zhang, Qingyi Tong, Ming He, Chu Wuhan Univ Elect Informat Sch Wuhan 430072 Peoples R China

Recently, deep-learning methods have yielded rapid progress for object detection in synthetic aperture radar (SAR) imagery. It is still a great challenge to detect ships in SAR imagery due to ships' small size and confusable detail feature. This article proposes a novel anchor-free detection method composed of two modules to deal with these problems. First, for the lack of detailed information on small ships, we suggest an adaptive feature-encoding module (AFE), which gradually fuses deep semantic features into shallow layers and realizes the adaptive learning of the spatial fusion weights. Thus, it can effectively enhance the external semantics and improve the representation ability of small targets. Next, for the foreground-background imbalance, the Gaussian-guided detection head (GDH) is introduced according to the idea of soft sampling and exploits Gaussian prior to assigning different weights to the detected bounding boxes at different locations in the training optimization. Moreover, the proposed Gauss-ness can down-weight the predicted scores of bounding boxes far from the object center. Finally, the effect of the detector composed of the two modules is verified on the two SAR ship datasets. The results demonstrate that our method can effectively improve the detection performance of small ships in datasets.

关键词： ship object detection deep learning remote sensing imagery feature extraction object sampling

来源：评论

学校读者我要写书评

暂无评论

Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR ship detection Task

引用

SENSORS 2022年第9期22卷 3370-3370页

作者： Xie, Fang Lin, Baojun Liu, Yingchun Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Chinese Acad Sci Sch Optoelect Beijing 100094 Peoples R China Chinese Acad Sci Innovat Acad Microsatellites Shanghai 201210 Peoples R China Shanghai Engn Ctr Microsatellites Shanghai 201304 Peoples R China ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China

The real-time performance of ship detection is an important index in the marine remote sensing detection task. Due to the computing resources on the satellite being limited by the solar array size and the radiation-resistant electronic components, information extraction tasks are usually implemented after the image is transmitted to the ground. However, in recent years, the one-stage based target detector such as the You Only Look Once Version 5 (YOLOv5) deep learning framework shows powerful performance while being lightweight, and it provides an implementation scheme for on-orbit reasoning to shorten the time delay of ship detention. Optimizing the lightweight model has important research significance for SAR image onboard processing. In this paper, we studied the fusion problem of two lightweight models which are the Coordinate Attention (CA) mechanism module and the YOLOv5 detector. We propose a novel lightweight end-to-end object detection framework fused with a CA module in the backbone of a suitable position: YOLO Coordinate Attention SAR ship (YOLO-CASS), for the SAR ship target detection task. The experimental results on the SSDD synthetic aperture radar (SAR) remote sensing imagery indicate that our method shows significant gains in both efficiency and performance, and it has the potential to be developed into onboard processing in the SAR satellite platform. The techniques we explored provide a solution to improve the performance of the lightweight deep learning-based object detection framework.

关键词： synthetic aperture radar ship object detection coordinate attention mechanism YOLOv5 onboard computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：