检索结果-内蒙古大学图书馆

A Review of Intrusion Detection for Railway Perimeter Using deep learning-Based Methods

IEEE ACCESS 2024年 12卷 184142-184157页

作者： Wang, Jin Zhai, Hongyang Yang, Yang Xu, Niuqi Li, Hao Fu, Di Beijing Univ Technol Beijing Key Lab Traff Engn Beijing 100124 Peoples R China Beijing Univ Technol Beijing Engn Res Ctr Urban Transport Operat Guaran Beijing 100124 Peoples R China

Efficiently detecting intrusions on a railway perimeter is crucial for ensuring the safety of railway transportation. With the development of computer vision, researchers have been actively exploring methods for detecting foreign object intrusion via image recognition technology. This article reviews the background and importance of detecting railway perimeter intrusion, summarizes the limitations of traditional detection methods, and emphasizes the potential of improving detection accuracy and efficiency in image recognition with deep learning models. Further, it introduces the development of deep learning in image recognition, focusing on the principles and progress of key technologies such as convolutional neural networks (CNNs) and vision transformers (ViTs). In addition, the application status of semantic segmentation and object detection algorithms based on deep learning in detecting railway perimeter intrusion is explored, including the classification, principles, and performance of the algorithms in practical applications. Finally, it highlights the primary challenges faced in railway perimeter intrusion detection and projects future research directions to resolve these challenges, including multisource data fusion, large-scale dataset construction, model compression, and end-to-end multitask learning networks. These studies support the accuracy and real-time detection of railway perimeter intrusion, and provide technical guarantees for railway transportation monitoring tasks.

关键词： Rail transportation Convolutional neural networks deep learning Monitoring Feature extraction Accuracy Kernel Accidents Computer architecture Computational modeling Railway semantic segmentation object detection foreign object intrusion railway safety

来源：评论

学校读者我要写书评

暂无评论

An effective IoT interface considering an eye-tracking method for autonomous vehicle

INTERNET OF THINGS

引用

INTERNET OF THINGS 2025年 31卷

作者： Park, Junghoon Ajou Univ Coll Comp & Informat Dept Appl Artificial Intelligence WorldCup Ro 206 Suwon 16499 Gyeonggi Do South Korea

The number of Internet-connected devices is steadily increasing, exceeding 25 billion globally and projected to surpass 50 billion about 6.5 times the world population. At the core of IoT is data collection via sensors, forming big data for AI-driven analysis, optimization, and visualization. A convenient control environment is essential for devices like autonomous vehicles, requiring new interfaces such as touchless eye movement. This research proposes a real-time eye-tracking method using a single web camera, easily installed in cars and integrated with IoT. The system detects gaze by recognizing iris shape, enabling software-only tracking without extra hardware. Experiments show a mean absolute error (MAE) of 3.49 degrees, ensuring accuracy even with head movement. Unlike existing infrared (IR) LED or head-mounted methods, this approach offers a cost-effective, real-time solution. Using lightweight image processing instead of deep learning, the system achieves real-time tracking with low latency, making it ideal for low-power IoT and autonomous vehicles. It is expected to become a next-generation input interface for these applications.

关键词： Autonomous system Eye gaze tracking IoT image processing Interpolation real-time processing

来源：评论

学校读者我要写书评

暂无评论

RT-CBAM: Refined Transformer Combined with Convolutional Block Attention Module for Underwater image Restoration

引用

SENSORS 2024年第18期24卷 5893页

作者： Ye, Renchuan Qian, Yuqiang Huang, Xinming Jiangsu Univ Sci & Technol Sch Ocean Engn Dept Elect Informat Engn Zhenjiang 212003 Peoples R China

Recently, transformers have demonstrated notable improvements in natural advanced visual tasks. In the field of computer vision, transformer networks are beginning to supplant conventional convolutional neural networks (CNNs) due to their global receptive field and adaptability. Although transformers excel in capturing global features, they lag behind CNNs in handling fine local features, especially when dealing with underwater images containing complex and delicate structures. In order to tackle this challenge, we propose a refined transformer model by improving the feature blocks (dilated transformer block) to more accurately compute attention weights, enhancing the capture of both local and global features. Subsequently, a self-supervised method (a local and global blind-patch network) is embedded in the bottleneck layer, which can aggregate local and global information to enhance detail recovery and improve texture restoration quality. Additionally, we introduce a multi-scale convolutional block attention module (MSCBAM) to connect encoder and decoder features;this module enhances the feature representation of color channels, aiding in the restoration of color information in images. We plan to deploy this deep learning model onto the sensors of underwater robots for real-world underwater image-processing and ocean exploration tasks. Our model is named the refined transformer combined with convolutional block attention module (RT-CBAM). This study compares two traditional methods and six deep learning methods, and our approach achieved the best results in terms of detail processing and color restoration.

关键词： deep learning transformer image restoration

来源：评论

学校读者我要写书评

暂无评论

An Online Digital Imaging Excitation Sensor for Wind Turbine Gearbox Wear Condition Monitoring Based on Adaptive deep learning Method

引用

SENSORS 2024年第8期24卷 2481页

作者： Tao, Hui Zhong, Yong Yang, Guo Feng, Wei South China Univ Technol Shien Ming Wu Sch Intelligent Engn Guangzhou 510640 Peoples R China Natl & Local Joint Engn Res Ctr Ind Tribol & Lubri Guangzhou 510535 Peoples R China Univ Hong Kong Dept Ind & Mfg Syst Engn Hong Kong 999077 Peoples R China Guangzhou Mech Engn Res Inst Co Ltd Guangzhou 510535 Peoples R China

This paper designed and developed an online digital imaging excitation sensor for wind power gearbox wear condition monitoring based on an adaptive deep learning method. A digital imaging excitation sensing image information collection architecture for magnetic particles in lubricating oil was established to characterize the wear condition of mechanical equipment, achieving the real-time online collection of wear particles in lubricating oil. On this basis, a mechanical equipment wear condition diagnosis method based on online wear particle images is proposed, obtaining data from an engineering test platform based on a wind power gearbox. Firstly, a foreground segmentation preprocessing method based on the U-Net network can effectively eliminate the interference of bubbles and dark fields in online wear particle images, providing high-quality segmentation results for subsequent image processing, A total of 1960 wear particle images were collected in the experiment, the average intersection union ratio of the validation set is 0.9299, and the accuracy of the validation set is 0.9799. Secondly, based on the foreground segmentation preprocessing of wear particle images, by using the watered algorithm to obtain the number of particles in each size segment, we obtained the number of magnetic particle grades in three different ranges: 4-38 mu m, 39-70 mu m, and >70 mu m. Thirdly, we proposed a method named multidimensional transformer (MTF) network. Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) are used to obtain the error, and the maintenance strategy is formulated according to the predicted trend. The experimental results show that the predictive performance of our proposed model is better than that of LSTM and TCN. Finally, the online real-time monitoring system triggered three alarms, and at the same time, our offline sampling data analysis was conducted, the accuracy of online real-time monitoring alarms was verified, and the g

关键词： digital imaging excitation sensor magnetic particles lubricating oil U-Net network watered algorithm MTF network

来源：评论

学校读者我要写书评

暂无评论

Robust weapon detection in dark environments using Yolov7-DarkVision

引用

DIGITAL SIGNAL processing 2024年 145卷

作者： Yadav, Pavinder Gupta, Nidhi Sharma, Pawan Kumar Natl Inst Technol Dept Math & Sci Comp Hamirpur 177005 Himachal Prades India Natl Inst Technol Dept Comp Applicat Kurukshetra 136119 Haryana India

Currently, weapon detection through video surveillance has been extensively studied using deep learning techniques by researchers. However, limited attention has been given to the detection of weapons in night time or dark scenarios. This paper aims to address this gap by proposing a novel approach for weapon detection specifically modified for low-light conditions. The authors demonstrate accurate and robust detection of weapons in challenging nighttime environments by modifying the deep learning model YOLOv7. The YOLOv7-DarkVision model has been developed by combining a brightening algorithm with the advanced image processing techniques and architecture of YOLOv7. A dataset of 15,367 images were collected for training of the model, along with five dark videos from various sources for performance evaluation. The derived detection model, which has a precision score of 95.50% and an F1-Score of 93.41%, performs absolutely well as a weapon detector.

关键词： CCTV surveillance Convolutional neural networks Dark image enhancement deep learning Weapon detection

来源：评论

学校读者我要写书评

暂无评论

A systematic review of hyperspectral imaging in precision agriculture: Analysis of its current state and future prospects

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 222卷

作者： Ram, Billy G. Oduor, Peter Igathinathane, C. Howatt, Kirk Sun, Xin North Dakota State Univ Dept Agr & Biosyst Engn Fargo ND 58102 USA North Dakota State Univ Dept Earth Environm & Geospatial Sci Fargo ND 58102 USA North Dakota State Univ Dept Plant Sci Fargo ND 58102 USA

Hyperspectral sensor adaptability in precision agriculture to digital images is still at its nascent stage. Hyperspectral imaging (HSI) is data rich in solving agricultural problems like disease detection, weed detection, stress detection, crop monitoring, nutrient application, soil mineralogy, yield estimation, and sorting applications. With modern precision agriculture, the challenge now is to bring these applications to the field for real-time solutions, where machines are enabled to conduct analyses without expert supervision and communicate the results to users for better management of farmlands;a necessary step to gain complete autonomy in agricultural farmlands. Significant advancements in HSI technology for precision agriculture are required to fully realize its potential. As a wide-ranging collection of the status of HSI and analysis in precision agriculture is lacking, this review endeavors to provide a comprehensive overview of the recent advancements and trends of HSI in precision agriculture for real-time applications. In this study, a systematic review of 163 scientific articles published over the past twenty years (2003-2023) was conducted. Of these, 97 were selected for further analysis based on their relevance to the topic at hand. Topics include conventional data preprocessing techniques, hyperspectral data acquisition, data compression methods, and segmentation methods. The hardware implementation of fieldprogrammable gate arrays (FPGAs) and graphics processing units (GPUs) for high-speed data processing and application of machine learning and deep learning technologies were explored. This review highlights the potential of HSI as a powerful tool for precision agriculture, particularly in real-time applications, discusses limitations, and provides insights into future research directions.

关键词： Hyperspectral Precision agriculture Data analysis real-time image analysis

来源：评论

学校读者我要写书评

暂无评论

Advanced optimization-based weighted features for ensemble deep learning smart occupancy detection network for road traffic parking

引用

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 2024年 230卷

作者： Padmavathi, B. Selvaraj, Vanaja Easwari Engn Coll Comp Sci & Engn Chennai 600089 Tamil Nadu India Easwari Engn Coll Comp Sci & Engn AI & ML Chennai 600089 Tamil Nadu India

In day-to-day activities, the advanced technology like Internet of Things (IoT) emerges to improve the lifestyle of people. In metropolitan cities, real-time parking is the long-lasting problem that we face in our daily life activities. Urban parking regulation gained more attention because of its capability to diminish energy consumption, congested traffic, and manifestation. The parking space detection for vehicles in real-time is a crucial role for on-street parking control models where the data is delivered to the drivers through internet with the help of Global Positioning System (GPS). Hence, the network congestion gets increased, where the existing model does not performed well in the parking space effectively. This research paper recommends a novel strategy for detecting occupancy in road traffic parking by IoT and deep networks to overcome these difficulties. At first, the required information is gathered from the standard datasets as CNRPark + EXT for further processing. After the data collection process, the preprocessing phase is executed, where the data cleaning and data transformation approaches are done with a multi-scale retinex network. The pre-processing technique is effectively performed to reduce background noise. Further, the feature extraction is progressed through the Residual Attention Network, where the relevant features are extracted from the pre-processed data. Subsequently, the optimal features and weights are selected by the novel Advanced Pelican Optimization Algorithm (APOA) to get the optimal weighted feature selection. This optimal weighted feature is further given to the Ensemble deep Networks (EDN) by integrating the deep Conditional Random Field (DCRF), and Extreme deep learning (EDL) model. In final process, the detection of occupancy in road traffic parking is determined by averaging both classifiers outcomes. Finally, the results are compared with numerous optimization algorithms and classifiers to ensure the developed system's

关键词： Occupancy detection Road traffic parking Ensemble deep networks Advanced pelican optimization algorithm deep conditional random field Extreme deep learning

来源：评论

学校读者我要写书评

暂无评论

Construction and real time Update Mechanism of a Multi User Personalized Electricity Consumption Behavior Model Under deep learning 2

Construction and Real Time Update Mechanism of a Multi User ...

引用

2nd IEEE International Conference on image processing and Computer Applications, ICIPCA 2024

作者： Gao, Chen Zhan, Shian Lin, Yinrong Zhu, Enguo Liu, Yan Zheng, Xiaohui Hong, Shouli State Grid Info-Telecom Great Power Science and Technology Co. Ltd Fujian Fuzhou350003 China China Electric Power Research Institute Beijing100192 China

ISBN: (纸本)9798350360240

It is a troublesome problem to model the user's electricity consumption behavior and add an update mechanism. Traditional models have challenges in real-time and personalization, so the introduction of real-time update mechanism has become a key method to improve model performance. Based on deep learning technology, this research constructs a multi-user personalized electricity consumption behavior model, and introduces a real-time update mechanism. First, a large number of user electricity consumption behavior data is used for training to establish the predictive power of the model, and then through the introduction of a real-time update mechanism, the model can respond to new data in a timely manner, and perform parameter updates and prediction result generation. Through experiments, it is evaluated that the prediction accuracy rate of this method is between 89% and 98%. The electricity consumption behavior model with a real-time update mechanism is better than the model without a real-time update mechanism in terms of prediction accuracy and real-time performance. © 2024 IEEE.

关键词： Electricity Consumption Behavior Feature Extraction real time Update Mechanism RNN

来源：评论

学校读者我要写书评

暂无评论

Efficient Ship:A Hybrid deep learning Framework for Ship Detection in the River

引用

Computer Modeling in Engineering & Sciences 2024年第1期138卷 301-320页

作者： Huafeng Chen Junxing Xue Hanyun Wen Yurong Hu Yudong Zhang School of Computer Engineering Jingchu University of TechnologyJingmen448000China School of Computer Science Yangtze UniversityJingzhou434023China School of Computing and Mathematic Sciences University of LeicesterLeicesterLE17RHUK

Optical image-based ship detection can ensure the safety of ships and promote the orderly management of ships in offshore *** deep learning researches on optical image-based ship detection mainly focus on improving one-stage detectors for real-time ship detection but sacrifices the accuracy of *** solve this problem,we present a hybrid ship detection framework which is named EfficientShip in this *** core parts of the EfficientShip are DLA-backboned object location(DBOL)and CascadeRCNN-guided object classification(CROC).The DBOL is responsible for finding potential ship objects,and the CROC is used to categorize the potential ship *** also design a pixel-spatial-level data augmentation(PSDA)to reduce the risk of detection model *** compare the proposed EfficientShip with state-of-the-art(SOTA)literature on a ship detection dataset called *** show our ship detection framework achieves a result of 99.63%(mAP)at 45 fps,which is much better than 8 SOTA approaches on detection accuracy and can also meet the requirements of real-time application scenarios.

关键词： Ship detection deep learning data augmentation object location object classification

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in deep-learning-Based SAR image Target Detection and Recognition

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6884-6915页

作者： Lang, Ping Fu, Xiongjun Dong, Jian Yang, Huizhang Yin, Junjun Yang, Jian Martorella, Marco Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China Univ Pisa Dept Informat Engn I-56127 Pisa Italy

Synthetic aperture radar (SAR) image target detection and recognition (SAR-TDR) tasks have become research hot spots in the remote sensing application. These targets include ships, vehicles, aircraft, oil tanks, bridges, and so on. However, with the rapid development of SAR technology and increasingly complex electromagnetic environment, complex characteristics of SAR images bring severe challenges to the accurate SAR-TDR via traditional physical models or manual feature-extraction-based machine learning methods. In recent years, deep learning (DL), as a powerful automatic feature extraction algorithm, has been widely used in the computer vision domain. More specifically, DL has also been introduced into the SAR-TDR tasks and has effectively achieved good performance in terms of accuracy, real-time processing, etc. With the rapid development of DL, SAR image processing, and practical requirements of SAR-TDR in civilian and military domains, it is crucial to conduct a systematic survey on SAR-TDR in the past few years. In this survey article, we mainly conduct a systematic overview of DL-based SAR-TDR literature on two tasks, i.e., target recognition (e.g., ground vehicles, ships, and aircraft) and target detection (e.g., ships, aircraft, change detection, sea surface oil spills, and oil tanks). More specifically, our related works about these topics are also presented to verify the effectiveness of DL-based methods. First, several DL methods (e.g., convolutional neural networks, recurrent neural networks, autoencoders, and generative adversarial networks), commonly used in SAR-TDR, are briefly introduced. Then, a systematic review of DL-based SAR-TDR (including our related works) is presented. Finally, the current challenges and future possible research directions are deeply analyzed and discussed.

关键词： Radar polarimetry Target recognition Synthetic aperture radar Marine vehicles Feature extraction Object detection Aircraft Surveys Accuracy deep learning Automatic target recognition change detection (CD) deep learning (DL) SAR image interpretation target detection

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：