检索结果-内蒙古大学图书馆

18th IEEE/ASME international conference on Mechatronic and Embedded systems and Applications (MESA)

作者： Huang, Zheng-Jie Lu, Wei-Hao Patel, Brijesh Chiu, Po-Yan Yang, Tz-Yu Tong, Hao Jian Bucinskas, Vytautas Greitans, Modris Lin, Po Ting Natl Taiwan Univ Sci & Technol Dept Mech Engn Taipei Taiwan MATS Univ Dept Aeronaut Engn Raipur Madhya Pradesh India Vilnius Gediminas Tech Univ LT-10223 Vilnius Lithuania Inst Elect & Comp Sci LV-1006 Riga Latvia

ISBN: (纸本)9781665455701

In this era of automation, image processing is an indispensable part of computer vision. Many computer vision approaches in the industry depend on a relatively bright environment. Under low light source conditions, the distribution of image information is too concentrated in specific intensity ranges due to the color factor of the subject itself, resulting in noise and contrast loss. Enhancing contrast is a crucial step in improving the quality of the image and showing visible details. This study proposes a method based on a convolutional neural network (CNN), using the pixel difference between paired images, called a motion matrix, as an annotation for low-contrast images. The image's motion vector is predicted after the neural network model has been trained to produce the low-contrast enhanced image. Then, the proposed model is compared with the Low-Light image Enhancement (LLNet), Multi-Scale Retinex Color Restoration (MSRCR), and Fuzzy Automatic Cluster Enhancement (FACE) approaches. The effectiveness of the proposed method was further evaluated by comparing several quality indicators, including peak signal-to-noise ratio, structural similarity, root-mean-square-error, root-mean-square-contrast and computation time efficiency.

关键词： Low contrast image processing Deep learning Artificial intelligence Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Construction of complex environment speech signal communication system based on 5G and AI driven feature extraction techniques

引用

international JOURNAL OF SPEECH technology 2021年第4期25卷 817页

作者： Jiang, Yi Cheng, ErLi Li, YongHao Zhang, Yali XinYang Vocat & Tech Coll Sch Math & Comp Sci Xinyang 464000 Henan Peoples R China

In daily life, the most direct and important way of human communication is voice. With the rise of the internet and the development of communication technology, the proportion of non voice signals such as image and data in communication system is increasing. However, in most communication systems, voice transmission function is generally required, so it is still one of the necessary functions for many communication systems to transmit voice information effectively. With the rapid development of the internet, especially the recent 5G technology commercial and future civil, human-computer interaction will become more and more intelligent in the future, which also poses a greater challenge to speech recognition as a human-computer interface. Noise interference is one of the biggest obstacles to the practical application of speech system. Although a large number of noisy data based on deep learning can solve part of the noise robustness problem, non-stationary noise interference is still a great challenge for speech recognition system in very low SNR complex scenes. In addition, in the multi information fusion communication system, there are many kinds of data to be transmitted, and there are high requirements for bandwidth and storage space. Hence, this paper studies the construction of voice signal communication system based on the artificial intelligence and 5G technology. The model is designed and implemented considering the complex scenarios. The performance is validated through the simulations compared with the state-of-the-art methods.

关键词： 5G Base Station Artificial Intelligence Speech Recognition Communication System Receiver System

来源：评论

学校读者我要写书评

暂无评论

Medical image encryption based on hyper-chaotic system 2

Medical image encryption based on hyper-chaotic system

引用

2nd international conference on Digital signal and Computer Communications, DSCC 2022

作者： Zhang, Lu Han, Tailin Liu, Xuan Liu, Hong School of Electronic Information and Engineering Changchun University of Science and Technology Jilin Changchun130012 China School of Electro-Optical Engineering Changchun University of Science and Technology Jilin Changchun130012 China

ISBN: (纸本)9781510656734

Medical images contain a large amount of private information like patient's lesions. Theft or destruction of medical images will cause irreparable losses to patients and medical institutions. How to realize the secure transmission of information in the process of telemedicine has become a research hotspot. In this paper, an encryption algorithm for hyper-chaotic systems based on DNA coding is proposed. First, a four-dimensional chaotic system is constructed by adding a dimension to the three-dimensional chaotic system, which improves the dynamic performance of the system, increases the parameters of the chaotic system, and improves the key space. Second, the algorithm complexity is increased by the added DNA encoding. The experimental results show that the key space encrypted by the method in this paper is 2469, and the key sensitivity can reach 10-16. At the same time, in the analysis of histogram, adjacent correlation and information entropy, the algorithm in this paper can achieve good security performance. © 2022 SPIE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

YOLOv10-based Real-Time Pedestrian Detection for Autonomous Vehicles

YOLOv10-Based Real-Time Pedestrian Detection for Autonomous ...

引用

IEEE international conference on signal and image Processing Applications (ICSIPA)

作者： Yan Li Waiyie Leong Hongli Zhang INTI International University Nilai Malaysia Heilongjiang Institute of Construction Technology Harbin China Faculty of Engineering and Quantity Surveying INTI International University Nilai Malaysia

ISBN: (数字)9798350352368

ISBN: (纸本)9798350352375

Accurate pedestrian detection is increasingly important for safety as autonomous driving technology advances. This paper presents a real-time pedestrian detection method based on YOLOvlO. The technique creates an efficient real-time object detection model by enhancing the backbone network with EfficientNet and C2F-DM modules, integrating the BiFormer module in the neck network, and incorporating a multi-scale feature fusion detection head. Experimental results show that YOLOvlO can achieve efficient multi-scale pedestrian detection, even in complex backgrounds.

关键词： Pedestrians Head Accuracy Object detection Feature extraction Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

Research on Anti-Tampering Method of Convolutional Coding for Power internet of Things Sensing

Research on Anti-Tampering Method of Convolutional Coding fo...

引用

China international conference on Electricity Distribution, CICED

作者： Qilin Li Hui He Qiyue Zhou Taiting Yu Marketing service center State Grid Sichuan Electric Power Company Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350368345

ISBN: (纸本)9798350368352

With the development of internet of Things technology, traditional power grids are gradually integrating with the internet of Things to form the power internet of Things, greatly improving the level of informatisation and intelligence. The terminal sensors in the perception layer of the power internet of Things cannot apply complex security technologies due to device performance limitations, thus facing information security risks. This paper proposes a data tamper proof method for power IoT sensors based on convolutional encoding and decoding. This method can recover erroneous data to correct data when transmission information is disturbed and errors occur. Moreover, terminal devices of the power internet of Things are usually embedded systems, and the communication, storage, and computing capabilities of the devices are limited to a certain extent. Convolutional codes have lower algorithm complexity and less computational overhead, and can adapt to most scenarios.

关键词： Convolutional codes Performance evaluation Embedded systems Information security Interference Encoding Smart grids image restoration internet of Things Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Cost Measure Methods to Calculate Motion Vector in Motion Estimation Algorithms 5th

Performance Analysis of Cost Measure Methods to Calculate Mo...

引用

5th international conference on Energy systems, Drives and Automations, ESDA 2022

作者： Whig, Pawan Bhandari, Rahul Neware, Rahul Raja Sekhar, G.G. Sankhla, Ranveer Singh VIPS Technical Campus New Delhi India Department of CSE UIE Chandigarh University Punjab Mohali India Department of CSE G. H. Raisoni College of Engineering Nagpur India Department of Electrical and Electronics Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Software Management Department Dotsquares Technology India Pvt. Ltd. Rajasthan Jaipur India

ISBN: (纸本)9789819701537

Cost is one factor in deciding video compression quality. In intra-frame prediction, it compares two blocks. It also affects the number of computations required for intra-frame block prediction from the previous frame. The amount of computations needed to estimate the motion between two successive video frames will depend on how efficiently the cost measurements are determined. For motion estimation in video compression, cost metrics between two intra-frames are essential. This article compares three block-based motion estimation methods (ARPS, NCDS, SCDS) for compressing video in relation to computations and peak-signal to noise ratio (PSNR). This article also examines the impact of the searching parameter and size of macro-block on cost measure calculation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

IOT Devices and Control systems Working Together to Improve Security

IOT Devices and Control Systems Working Together to Improve ...

引用

international conference on ICT in Business Industry & Government (ICTBIG)

作者： Rupinder Singh Jaspreet Singh Bajaj Simerjeet Singh Bawa Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Chitkara Business School Chitkara University Punjab India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

The internet of Things (IoT) facilitates seamless integration and interoperability among various networks, devices, technologies, and products by placing emphasis on control schemas. End-users require uninterrupted and precise connectivity, irrespective of the integration node (e.g., tablet, laptop, television, smartphone, or other internet-connected device). Intelligent IoT devices have the capability to function as flexible connections with ever-changing configurations, enabling timely reactions and potentially worldwide *** response to the urgent requirement for secure real-time control operations, this research paper introduces a methodology that integrates intelligent internet of Things (IoT) system functionalities with power system interfaces. The proposed methodology integrates computing, cryptography, signal/image processing, and communication networks to facilitate authentication and authorization operations via gateways and terminals. This results in a real-time performance environment that is not only more secure but also more adaptable and robust in comparison to conventional approaches. Moreover, the researchers delineate a framework for the internet of Things that is applicable to power system inputs in administrative, industrial, transportation, and comprehensive monitoring environments.

关键词： Performance evaluation TV Portable computers Authentication Transportation Control systems Real-time systems Power systems internet of Things Monitoring

来源：评论

学校读者我要写书评

暂无评论

17th international conference on Intelligent Information Hiding and Multimedia signal Processing, IIH-MSP 2021, in conjunction with the 14th international conference on Frontiers of Information technology, Applications and Tools, FITAT 2021

17th International Conference on Intelligent Information Hid...

引用

17th international conference on Intelligent Information Hiding and Multimedia signal Processing, IIH-MSP 2021, in conjunction with the 14th international conference on Frontiers of Information technology, Applications and Tools, FITAT 2021

ISBN: (纸本)9789811910524

The proceedings contain 64 papers. The special focus in this conference is on Intelligent Information Hiding and Multimedia signal Processing. The topics include: An Expressway Congestion Detection Algorithm based on ETC Data Mining;A New PPE Algorithm based on Parallel Communication Strategy;design and Optimization of Electric Vehicle Seat;design and Fault Research of Relay Protection for Shore Power;applying image Processing technology to Estimate Vehicle Speed;K-PPE: A Variant Phasmatodea Population Evolution Algorithm for Global Optimization;five Phases Algorithm for Global Optimization;an image Encryption Method based on Logistic Mapping and Phasmatodea Population Evolution Algorithm;video Surveillance System of Substation based on AdaBoost Pedestrian Anti-misjudgment Algorithm;transformer Fault Identification Method based on Improved Roberts Algorithm;Expressway Traffic Speed Prediction Method based on CNN_Bi-LSTM Model via ETC Data;How Consumers’ Lending Knowledge and Self-efficacy Drive Their Intention: A Model of TAM Within Information Asymmetric Condition;occluded and Tiny Face Detection with Deep and Shallow Features Fusion and Compensation;simulation and Analysis of Steering Mechanical Characteristics Between Tire and Soil;Study on the Method of Adversarial Example Attack based on MI-FGSM;virtual Design of Chinese Theater Arts in Augmented Reality Media System;design Analysis and Optimization of the Anti-collision Structure of the Four-Wheel Electric Scooter;binary Fish Migration Optimization for Feature Selection Using Time-Varying Transfer Function;ResRnnNet: Learning to Reconstruct the 3D Room Layout from a Single RGB Panorama;design and Optimization of Spring in Damping System of New Energy Electric Vehicle;small Object Detection based on Multi-source Data Learning Fusion Network;preface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

17th International Conference on Intelligent Information Hid...

引用

ISBN: (纸本)9789811910562

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Denoising of Multiple Compressed image based on Structure-Texture Decomposition 8

Research on Denoising of Multiple Compressed Image Based on ...

引用

8th IEEE international conference on Cloud Computing and Intelligence systems, CCIS 2022

作者： Zhou, Faguo Liu, Qiqi Wang, Xin China University of Mining and Technology-Beijing School of Mechanical Electronic and Information Engineering Beijing100083 China

ISBN: (纸本)9781665477352

At present, most of the researches on denoising of compressed images are one-time compression. But in practice, the image will be compressed more than once. Therefore, a denoising method combining deep learning and traditional methods was proposed for multiple compressed images. First, the data set was compressed twice through singular value decomposition (SVD) to obtain noisy images after multiple compressions. Secondly, the noisy image was decomposed to obtain the noisy structure image and texture image. Then denoised them separately, the noisy structure image was used the feed-forward denoising convolutional neural network (DnCNN), and the noisy texture image was used the selected mean method. Finally, the denoised structure image and texture image were combined to obtain the denoised multiple compressed image. The Peak signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) of this method are approximately improved by 0.91.5dB and 0.020.06, respectively. Moreover, the texture image is extracted and targeted for denoising, retaining more detailed information and achieving a clearer visual effect. © 2022 IEEE.

关键词： Textures

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：