检索结果-内蒙古大学图书馆

Towards real-time Detection of Wakes for Various Sea States with Lightweight deep learning Model in Synthetic Aperture Radar images

引用

REMOTE SENSING 2024年第24期16卷

作者： Zhou, Xixuan Zheng, Fengjie Wang, Haoyu Yang, Haitao Space Engn Univ Dept Grad Management Beijing 101400 Peoples R China Space Engn Univ Dept Aerosp Informat Beijing 101400 Peoples R China

Synthetic aperture radar (SAR) is an essential tool for monitoring and managing maritime traffic and ensuring safety. It is particularly valuable because it can provide surveillance in all weather conditions. Ship wake detection has attracted considerable attention in offshore management as it has potential for widespread use in ship positioning and motion parameter inversion, surpassing conventional ship detection methods. Traditional wake detection methods depend on linear feature extraction through image transformation processing techniques, which are often ineffective and time-consuming when applied to large-scale SAR data. Conversely, deep learning (DL) algorithms have been infrequently utilized in wake detection and encounter significant challenges due to the complex ocean background and the effect of the sea state. In this study, we propose a lightweight rotating target detection network designed for detecting ship wakes under various sea states. For this purpose, we initially analyzed the features of wake samples across various frequency domains. In the framework, a YOLO structure-based deep learning is implemented to achieve wake detection. Our network design enhances the YOLOv8's structure by incorporating advanced techniques such as deep separation convolution and combined frequency domain-spatial feature extraction modules. These modules are used to replace the usual convolutional layer. Furthermore, it integrates an attention technique to extract diverse features. By conducting experiments on the OpenSARWake dataset, our network exhibited outstanding performance, achieving a wake detection accuracy of 66.3% while maintaining a compact model size of 51.5 MB and time of 14 ms. This model size is notably less than the existing techniques employed for rotating target detection and wake detection. Additionally, the algorithm exhibits excellent generalization ability across different sea states, addressing to a certain extent the challenge of wake detection b

关键词： ship wake detection deep learning lightweight model SAR image sea state

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning model for real-time rectangle NdFeB surface defect detection with high accuracy on a global scale

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-13页

作者： Huang, Lin Yuan, Heping Chen, Shuixuan Zhou, Bo Guo, Yihuang Xiamen Univ Technol Sch Mech & Automot Engn Xiamen 361024 Fujian Peoples R China Anjierui Robot Co LTD Gen Managers Off Xiamen 361023 Fujian Peoples R China

To solve the problem that it is difficult to detect dynamic tiny square neodymium-iron-boron (NdFeB) surface defects in the case of limited computing resources, this paper proposes a square NdFeB magnet surface defect detection method based on the YOLO (YOLOv8-FCW) lightweight network. Initially, the lightweight global adaptive feature enhancement module (DFNet) network is used as the backbone feature extraction net-work. By customizing the depth of the feature matrix and reducing unnecessary branch structures, the model complexity is reduced while enhancing the network's ability to extract multi-scale feature information. Subsequently, the deformable convolution module (DCNv3) is utilized to acquire twice downsampling feature maps without information loss, aiming to expand the receptive field for small-sized defects. Finally, to further improve detection accuracy, the Wise-IOU (WIOU) v3 bounding box loss function is introduced to focus on the samples that are difficult to identify and reduce the gradient penalty for low-quality samples. The experimental results show that the YOLOv8-FCW algorithm achieves a mean Average Precision (mAP@0.5) of 78.6% on the rectangle NdFeB magnet dataset, with a model parameter quantity and computational cost reduction of 33.2% and 24.7%, respectively compared with the baseline, and requires less computational resources for higher detection accuracy compared to other mainstream object detection algorithms. Finally, the model was deployed to industrial Automated Optical Inspection (AOI) devices using TensorRT. This deployment reduced the inference time for a single image to 2.7 ms and increased speed by 6.6 times, enabling dynamic micro-detection of surface defects in square NdFeB.

关键词： Defect detection NdFeB magnet YOLOv8 Lightweight network DFNet TensoRT

来源：评论

学校读者我要写书评

暂无评论

deep learning based insulator fault detection algorithm for power transmission lines

引用

JOURNAL OF real-time image processing 2024年第4期21卷 1-16页

作者： Wang, Han Yang, Qing Zhang, Binlin Gao, Dexin Qingdao Univ Sci & Technol Sch Informat Sci & Technol Qingdao 266061 Peoples R China Qingdao Univ Sci & Technol Sch Automat & Elect Engn Qingdao 266061 Peoples R China

Aiming at the complex background of transmission lines at the present stage, which leads to the problem of low accuracy of insulator fault detection for small targets, a deep learning-based insulator fault detection algorithm for transmission lines is proposed. First, aerial images of insulators are collected using UAVs in different scenarios to establish insulator fault datasets. After that, in order to improve the detection efficiency of the target detection algorithm, certain improvements are made on the basis of the YOLOV9 algorithm. The improved algorithm enhances the feature extraction capability of the algorithm for insulator faults at a smaller computational cost by adding the GAM attention mechanism;at the same time, in order to realize the detection efficiency of small targets for insulator faults, the generalized efficient layer aggregation network (GELAN) module is improved and a new SC-GELAN module is proposed;the original loss function is replaced by the effective intersection-over-union (EIOU) loss function to minimize the difference between the aspect ratio of the predicted frame and the real frame, thereby accelerating the convergence speed of the model. Finally, the proposed algorithm is trained and tested with other target detection algorithms on the established insulator fault dataset. The experimental results and analysis show that the algorithm in this paper ensures a certain detection speed, while the algorithmic model has a higher detection accuracy, which is more suitable for UAV fault detection of insulators on transmission lines.

关键词： YOLOv9 Convolutional neural network Object detection Transmission lines

来源：评论

学校读者我要写书评

暂无评论

real-time video anomaly detection for smart surveillance

引用

IET image processing 2023年第5期17卷 1375-1388页

作者： Ali, Manal Mostafa Al Azhar Univ Comp & Syst Engn Cairo 11751 Egypt

Human monitoring of surveillance cameras for anomaly detection may be a monotonous task as it requires constant attention to judge if the captured activities are anomalous or suspicious. This paper exploits background subtraction (BS), convolutional autoencoder, and object detection for a fully automated surveillance system. BS was performed by modelling each pixel as a mixture of Gaussians (MoG) to concatenate only the higher-order learning in the foreground. Next, the foreground objects are fed to the convolutional autoencoders to filter out abnormal events from normal ones and automatically identify signs of threat and violence in real time. Then, object detection is introduced on the entire scene and the region of interest is highlighted with a bounding box to minimize human intervention in video stream processing. At recognition time, the network generates an alarm for the presence of an anomaly to notify of the identification of potentially suspicious actions. Finally, the complete system is validated upon several benchmark datasets and proved to be robust for complex video anomaly detection. The (AUC) average area under the curve for the frame-level evaluation for all benchmarks is 94.94%. The best improvement ratio of AUC between the proposed system and state-of-the-art methods is 7.7%.

关键词： anomaly detection background subtraction computer vision deep learning real-time surveillance

来源：评论

学校读者我要写书评

暂无评论

learning Optimum Binary Color Filter Arrays for Demosaicing with Neural Networks

Learning Optimum Binary Color Filter Arrays for Demosaicing ...

引用

Conference on real-time image processing and deep learning

作者： Ayna, Cemre Omer Gurbuz, Ali Cafer Mississippi State Univ Mississippi State MS 39762 USA

ISBN: (纸本)9781510673878;9781510673861

Modern digital color cameras depend on Color Filter Arrays (CFA) for capturing color information. The majority of the commercial CFAs are designed by hand with different physical and application-specific considerations. The available machine learning (ML)-based CFA learning architectures dismiss the considerations of a physical camera device. This study aims to develop an alternative approach to jointly learn binary Color Filter Arrays (CFA) in a deep learning-based filtering-demosaicing pipeline. The proposed approach provides higher reconstruction performance than the compared hand-designed filters while learning physically applicable CFAs. This paper includes the learned binary CFAs for various color configurations and training data size, their analysis with common reconstruction metrics, and a short discussion on future works.

关键词： color filter array deep learning demosaicing hard thresholding straight through estimator gradient estimation

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning Approach for Enhanced Animal Breed Classification and Prediction

引用

TRAITEMENT DU SIGNAL 2023年第5期40卷 2087-2099页

作者： Khan, Safdar Sardar Doohan, Nitika Vats Gupta, Manish Jaffari, Sakina Chourasia, Ankita Joshi, Kriti Panchal, Bhupendra RKDF Univ Dept Comp Sci & Engn Bhopal 462033 India Medi Caps Univ Dept Comp Sci & Engn Indore 453331 India GLA Univ Dept Elect & Commun Engn Mathura 281406 India VIT Bhopal Univ Sch Comp Sci & Engn Sehore 466114 India

The precise classification of animal breeds from image data is instrumental in real-time animal monitoring within forest ecosystems. Traditional computer vision methods have increasingly fallen short in accuracy due to the rapid progression of technology. To address these limitations, more advanced methodologies have emerged, significantly improving the accuracy of image classification, recognition, and segmentation tasks. The advent of "deep learning" has revolutionized various fields, particularly in object identification and recognition. Animal breed categorization is an important job in the field of image processing, and this research attempts to create a unique deep learning-based model for this purpose. The aim of this research is to devise efficient methodologies for image-based animal breed categorization to achieve superior accuracy levels. A hybrid deep learning model is proposed for animal breed prediction. The animal-10 dataset, obtained from Kaggle, serves as the empirical foundation for this study. The dataset underwent preprocessing, including edge deletion, normalization, and image scaling. Additionally, the animal images were converted into grayscale. Following this preprocessing phase, feature extraction was performed using two deep learning methods, namely VGG-19 and DenseNet121. The performance metrics, including accuracy, F1 score, recall, precision, and loss, were computed for the developed model using the Python simulation tool. Experimental results indicate that the proposed model outperforms existing current models in terms of these metrics. This research outcomes hold promising implications for the advancement of animal breed classification and prediction techniques.

关键词： animal breed prediction image processing classification deep learning VGG-19, densenet-121

来源：评论

学校读者我要写书评

暂无评论

A low-cost IoT-based deep learning method of water gauge measurement for flood monitoring

引用

GEOMATICS NATURAL HAZARDS & RISK 2024年第1期15卷

作者： Hashemi-Beni, Leila Puthenparampil, Megha Jamali, Ali NC A&T State Univ Coll Sci & Technol Dept Built Environm Greensboro NC 27411 USA Simon Fraser Univ Dept Geog Burnaby BC Canada

real-time and accurate measurement of the water level is a critical step in flood monitoring and management of water resources. In recent years, with the advent of the Internet of Things (IoTs) and cloud computing platforms and resources, the surveillance technology for water monitoring has been revolutionized due to the availability of high-resolution and portable cameras, robust image processing techniques, and cloud-enabled data fusion centers. However, despite the potential advantages of online water level monitoring of the rivers and lakes, some technical challenges need to be addressed before they can be fully utilized. Submersible sensor devices are frequently used for measuring water levels but are prone to damage from sediment deposition and many gauge detection techniques are inefficient at nighttime. In response, this paper presents a novel Internet of Things (IoT) based deep learning methodology that uses Mask-RCNN to accurately segment gauges from images even when there are distortions present. An automated and immediate water stage estimate is provided by this simple, low-cost method. The methodology's applicability to water resource management systems and flood disaster prevention engineering opens up new possibilities for the deployment of intelligent IoT-based flood monitoring systems in the future.

关键词： Water level measurement remote sensing image processing deep learning low-cost surveillance system

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning technique for medical image analysis using improved optimizer

引用

HEALTH INFORMATICS JOURNAL 2024年第2期30卷

作者： Agarwal, Vertika Lohani, Mc Bist, Ankur Singh Graph Era Hill Univ Bhimtal India

Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth. Latest preprocessing technique real ESRGAN (Enhanced super resolution generative adversarial network) and GFPGAN (Generative facial prior GAN) are proving their efficacy in providing high resolution dataset. Objective: Optimizer plays a vital role in upgrading the functioning of CNN model. Different optimizers like Gradient descent, Stochastic Gradient descent, Adagrad, Adadelta and Adam etc. are used for classification and segmentation of Medical image but they suffer from slow processing due to their large memory requirement. Stochastic Gradient descent suffers from high variance and is computationally expensive. Dead neuron problem also proves to detrimental to the performance of most of the optimizers. A new optimization technique Gradient Centralization is providing the unparalleled result in terms of generalization and execution time. Method: Our paper explores the next factor which is the employment of new optimization technique, Gradient centralization (GC) to our integrated framework (Model with advanced preprocessing technique). Result and conclusion: Integrated Framework of real ESRGAN and GFPGAN with Gradient centralization provides an optimal solution for deep learning models in terms of Execution time and Loss factor improvement.

关键词： gradient centralization medical image analysis real enhanced super resolution generative adversarial network generative facial prior GAN

来源：评论

学校读者我要写书评

暂无评论

deep learning Approach for a Machine-Human interface based on optical real-time Gesture Recognition for Automated Guided Vehicles

Deep Learning Approach for a Machine-Human interface based o...

引用

Conference on real-time processing of image, Depth, and Video Information

作者： Krishnakumar, Kiran Raj Gersmeier, Laura Harders, Leif Ole Hussmann, Stephan West Coast Univ Appl Sci Fritz Thiedemann Ring 20 D-25746 Heide Germany REINHOLZ Technol GmbH Kirchhoffstr 1A D-25524 Itzehoe Germany

ISBN: (纸本)9781510673199;9781510673182

The intersection of deep learning and programmable logic controllers (PLCs) can lead to innovative applications in automation. One of the exciting application areas are gesture-based control systems for Automated Guided Vehicles (AGVs). AGVs are used in various industries for material handling, logistics, warehouse automation, etc. Traditionally, these vehicles are controlled using predefined routes or remote controls, but with gesture-based control, operators can communicate more naturally and efficiently. The incorporation of YOLO-Pose in YOLO versions 7 and 8 has elevated the YOLO algorithm to a leading tool for creating gesture recognition models. The YOLO algorithm employs convolutional neural networks (CNN) to detect objects in real-time. These latest YOLO models offer significantly improved accuracy, speed, and reduced training times. This paper presents the comparative results of 2D gesture recognition transfer learning models created using the YOLO v5, v7, and v8 models, along with the steps taken to implement the model in a PLC-controlled AGV. Over 14,000 images were collected to build the models. A semi-automated approach was used to annotate them. Five models were created: two Keypoint models and three object detection models using transfer learning techniques with the same hyperparameters.

关键词： real-time image processing machine-human interface gesture recognition convolutional neural networks (CNN) automated guided vehicles machine learning deep-learning networks

来源：评论

学校读者我要写书评

暂无评论

Cutting path planning using reinforcement learning with adaptive sequence adjustment and attention mechanisms

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2025年第11-12期136卷 5599-5612页

作者： Wang, Kaiqi Zhang, Shijin Wu, Yuqiang Jiang, Fengyang Northwestern Polytech Univ Sch Software Xian 710072 Peoples R China NPU Yangtze River Delta Res Inst Suzhou Key Lab Aerosp Ind Software & Data Sci Taicang 215400 Peoples R China AV Informat Technol Co Ltd AVIC United Technol Ctr Multiaxis CNC Machining & Beijing 100020 Peoples R China

In industrial manufacturing, cutting path planning is very important since it directly affects cutting quality and efficiency. However, traditional methods are no longer suitable for large-scale and real-time cutting path planning due to the long computation time needed. Currently, though the deep learning method can be used for cutting path planning, the node number has to be fixed, and a large amount of labeled data is required. Another method is deep reinforcement learning, which can be used for cutting path planning. The node number also has to be fixed. As a result, these two potential methods are unsuitable for practical industrial cutting problems. To solve the above problem, this study provides a new reinforcement learning approach that integrates adaptive sequence adjustment and attention mechanisms. Compared to traditional methods, which took hours or days to finish a complicated cutting path plan, this approach significantly improves processing efficiency, completing tasks in seconds, and also minimizes non-cutting travel paths. And compared to deep learning and deep reinforcement learning provided by others, a variable number of nodes can be processed with this method. Therefore, it is more suitable for practical industrial cutting problems.

关键词： Cutting path planning deep reinforcement learning Attention mechanisms Adaptive sequence adjustment

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：