检索结果-内蒙古大学图书馆

Energy-efficient real-time visual image adversarial generation and processing algorithm for new energy vehicles

JOURNAL OF real-time image processing 2024年第5期21卷 161页

作者： Li, Yinghuan Liu, Jicheng North China Elect Power Univ Sch Econ & Management Beijing 102206 Peoples R China North China Elect Power Univ Beijing Key Lab New Energy & Low Carbon Dev Beijing 102206 Peoples R China

With the rapid development of deep learning in the last decade, generating and processing real-time images have become one of critical methods in intelligent driving systems for new energy vehicles. However, the real-time images captured by sensors are susceptible to variations in various environments, including different weather and lighting conditions. To enhance the real-time image generation performance for new energy vehicles in complex environments, and improve real-time visual image processing capabilities, this study proposes an energy-efficient real-time visual image adversarial generation and processing algorithm, called as ENV-GAN. It hypothesizes a shared latent domain among mixed image domains after analyzing driving situations under various weather and lighting conditions. Mappings are established between different image domains. Besides, a multi-encoder weight-sharing technique is utilized to enhances the generative adversarial network model. Additionally, the algorithm integrates an attention module to enhance the model & acirc;(TM) s image generation. Experimental results and analysis demonstrate that the new algorithm outperforms existing algorithms in tasks such as defogging, rain removal, and lighting enhancement, offering high energy efficiency and low energy consumption.

关键词： New energy vehicles Generative adversarial network image processing Intelligent driving Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Slideflow: deep learning for digital histopathology with real-time whole-slide visualization

引用

BMC BIOINFORMATICS 2024年第1期25卷 134页

作者： Dolezal, James M. Kochanny, Sara Dyer, Emma Ramesh, Siddhi Srisuwananukorn, Andrew Sacco, Matteo Howard, Frederick M. Li, Anran Mohan, Prajval Pearson, Alexander T. Univ Chicago Dept Med Sect Hematol Oncol Med Ctr Chicago IL 60637 USA Ohio State Univ Dept Internal Med Div Hematol Comprehens Canc Ctr Columbus OH USA Univ Chicago Dept Comp Sci Chicago IL USA

deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi.

关键词： Digital pathology Computational pathology Software toolkit Whole-slide imaging Explainable AI Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of real-time deep learning Methods for image-Based Cancer Diagnostics

引用

JOURNAL OF MULTIDISCIPLINARY HEALTHCARE 2024年 17卷 4411-4425页

作者： Sriraman, Harini Badarudeen, Saleena Vats, Saransh Balasubramanian, Prakash Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India

deep learning (DL) drives academics to create models for cancer diagnosis using medical image processing because of its innate ability to recognize difficult-to-detect patterns in complex, noisy, and massive data. The use of deep learning algorithms for realtime cancer diagnosis is explored in depth in this work. real-time medical diagnosis determines the illness or condition that accounts for a patient's symptoms and outward physical manifestations within a predetermined time frame. With a waiting period of anywhere between 5 days and 30 days, there are currently several ways, including screening tests, biopsies, and other prospective methods, that can assist in discovering a problem, particularly cancer. This article conducts a thorough literature review to understand how DL affects the length of this waiting period. In addition, the accuracy and turnaround time of different imaging modalities is evaluated with DL-based cancer diagnosis. Convolutional neural networks are critical for real-time cancer diagnosis, with models achieving up to 99.3% accuracy. The effectiveness and cost of the infrastructure required for real-time image-based medical diagnostics are evaluated. According to the report, generalization problems, data variability, and explainable DL are some of the most significant barriers to using DL in clinical trials. Making DL applicable for cancer diagnosis will be made possible by explainable DL.

关键词： artificial intelligence AI machine learning DL CNN healthcare real-time diagnosis classification image processing elastography feedforward neural network

来源：评论

学校读者我要写书评

暂无评论

Enhanced Driver Drowsiness Detection System using deep learning and image processing Techniques

Enhanced Driver Drowsiness Detection System using Deep Learn...

引用

International Conference on Signal processing, Communication, Power and Embedded System (SCOPES)

作者： Inderjeet Singh Sai Santosh Yerasuri Syed Gilani Pasha Anurag Shrivastava Manu Midha Yash Mahajan Department of Computer Science Chandigarh University Mohali Punjab India Evonik Corporation Northridge USA Department of ETE Bharat Ratna Indira Gandhi College of Eng. Solapur Maharashtra India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Computer Science Chitkara University Punjab India

ISBN: (数字)9798331506452

ISBN: (纸本)9798331506469

Driver drowsiness is among the strong causes of global road accidents. To counter such risk, we introduce a sophisticated detection system based on deep learning and image processing to counteract that type of risk. We visualize designing an end-to-end solution about the precise model to recognize drowsiness from facial images effectively. In the detailed literature review of published works based on drowsiness detection, we identified critical gaps and improvements. Our approach combines the use of CNNs to extract relevant features and classify states of alertness with special techniques applied for image processing to identify facial and eye states. In developing the system, we carefully set up a detailed procedure for data acquisition, model training, and testing. The performance results indicate tremendous strides in detection accuracy; the model yields strong results in controlled experiments and real-world use cases. This work outlines opportunities for enhanced driver-assistance technologies in improving safety on the roads, and we describe future research directions and application scenarios to further extend the development of drowsiness detection systems.

关键词： deep learning Training Analytical models Visualization Accuracy Feature extraction Data models Safety Vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

MobileMEF: fast and efficient method for real-time mobile multi-exposure fusion

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-15页

作者： Kirsten, Lucas Nedel Fu, Zhicheng Madhusudhana, Nikhil Ambha Motorola Mobil Comercio Prod Eletron Ltda Jaguariuna SP Brazil Lenovo Res Chicago IL USA

Recent advances in camera design and imaging technology have enabled the capture of high-quality images using smartphones. However, due to the limited dynamic range of digital cameras, the quality of photographs captured in environments with highly imbalanced lighting often results in poor-quality images. To address this issue, most devices capture multi-exposure frames and then use some multi-exposure fusion method to merge those frames into a final fused image. Nevertheless, most traditional and current deep learning approaches are unsuitable for real-time applications on mobile devices due to their heavy computational and memory requirements. We propose MobileMEF, a new method for multi-exposure fusion based on an encoder-decoder deep learning architecture with efficient building blocks tailored for mobile devices. This efficient design makes MobileMEF capable of processing 4K resolution images in less than 2 s on mid-range smartphones. MobileMEF outperforms state-of-the-art techniques regarding full-reference quality measures and computational efficiency (runtime and memory usage), making it ideal for real-time applications on hardware-constrained devices. Our code is available at: https://***/LucasKirsten/MobileMEF.

关键词： image fusion Multi-exposure image real-time methods Smartphone photography

来源：评论

学校读者我要写书评

暂无评论

Physics-guided deep learning-based real-time image reconstruction of Fourier-domain optical coherence tomography

引用

BIOMEDICAL OPTICS EXPRESS 2024年第11期15卷 6619-6637页

作者： Wang, Mengyuan Mao, Jianing Su, Hang Ling, Yuye Zhou, Chuanqing Su, Yikai Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China Shanghai Univ Med & Hlth Sci Coll Med Instrument Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn State Key Lab Adv Opt Commun Syst & Networks Shanghai Peoples R China

In this paper, we introduce a physics-guided deep learning approach for high-quality, real-time Fourier-domain optical coherence tomography (FD-OCT) image reconstruction. Unlike traditional supervised deep learning methods, the proposed method employs unsupervised learning. It leverages the underlying OCT imaging physics to guide the neural networks, which could thus generate high-quality images and provide a physically sound solution to the original problem. Evaluations on synthetic and experimental datasets demonstrate the superior performance of our proposed physics-guided deep learning approach. The method achieves the highest image quality metrics compared to the inverse discrete Fourier transform (IDFT), the optimization-based methods, and several state-of-the-art methods based on deep learning. Our method enables real-time frame rates of 232 fps for synthetic images and 87 fps for experimental images, which represents significant improvements over existing techniques. Our physics-guided deep learning-based approach could offer a promising solution for FD-OCT image reconstruction, which potentially paves the way for leveraging the power of deep learning in real-world OCT imaging applications. (c) 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Biomedical imaging deep learning High speed imaging image metrics Imaging systems Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

An ensemble deep learning model for fast classification of Twitter spam

引用

INFORMATION & MANAGEMENT 2024年第8期61卷

作者： Dhar, Suparna Bose, Indranil NSHM Knowledge Campus 12460Basanta Lal Saha RdT Kolkata 700053 West Bengal India NEOMA Business Sch 59 rue Pierre Taittinger F-51100 Reims France

Twitter spam needs to be detected and arrested quickly. The paper examines methods for classification of spam in terms of determination of important features, comparative performance of classification models, and improvement in time performance for classification. It presents a conceptualization of several novel rich, deep, and na & iuml;ve features. The extraction processes for rich and deep features increase the time complexity of spam classification. To address this, the proposed model selectively segregates and combines features to enable near real-time processing. This supersedes the time performance of standard machine learning and deep learning models, with no compromise on the quality of classification.

关键词： deep learning ensemble models image analytics Spam classification Text analytics Twitter

来源：评论

学校读者我要写书评

暂无评论

Cotton Leaf Disease Based on image processing Using deep learning

Cotton Leaf Disease Based on Image Processing Using Deep Lea...

引用

Innovations and Challenges in Emerging Technologies (ICICET), International Conference on

作者： D. Menaga B T Shri Roshan S R Shri Vikaas Department Of Computer Science and Engineering St. Joseph’s Institute of Technology Chennai India

ISBN: (数字)9798350319019

ISBN: (纸本)9798350319026

One of the most important occupations in India is agriculture. Out of all the crops, cotton is the best and is crucial to the agricultural economy of the country. In India, 40-50 million people work in the cotton trade and processing, while six million farmers directly depend on the crop. The cotton leaf disease has grown in importance over the last few decades, resulting in losses to crops, farming operations, and financial resources. To achieve this aim, we first need to acquire different images of cotton plants. We can use image processing techniques to analyze dead leaf images and extract features like color, texture, and other characteristics with the deep CNN model’s assistance. In addition to being less expensive and more straightforward, automatic disease detection supports machine vision, which offers image-based automated process control and inspection. To properly train the algorithm, we will be using a dataset of approximately 1752(approximately 440 images in each class) images classified into different categories according to the diseases. This model will be developed using tools present in Anaconda such as Jupyter Notebook, Spyder etc. The results of this project will demonstrate whether using it in real-time applications is feasible and whether traditional or manual disease and pest identification could benefit from the use of IT- based solutions.

关键词： Support vector machines Technological innovation Neural networks Crops Process control Feature extraction Vectors

来源：评论

学校读者我要写书评

暂无评论

deep learning-Driven Smart Signal Systems for Advanced image and Video processing in Urban Infrastructure

Deep Learning-Driven Smart Signal Systems for Advanced Image...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： K. S. Bharaty Praveen SR Konduri Department of EEE School of Engineering Mohan Babu University Tirupati Andhra Pradesh Department of Data Science School of Computing Mohan Babu University Tirupati Andhra Pradesh

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

The increasing integration of intelligent systems in metropolitan environments emphasizes the important role effective image and video processing performs in applications including the traffic management, the monitoring of safety, and the urban planning. When handling dynamic scenarios, that is, changes in traffic conditions, occlusions, and the need for real-time analysis, conventional signal processing methods sometimes fail. Strong and adaptable solutions able to manage both these complexity as well as others are thus much needed. This work intends to introduce a deep learning-based smart signal system designed to process real-time video feeds for uses connected to urban traffic and safety. The proposed system uses recurrent neural networks (RNNs) for temporal sequence comprehension; conversely, convolutional neural networks (CNNs) are used for spatial data analysis. Two approaches used in order to improve the performance of the model are data augmentation and transfer learning, which increase the accuracy of decision-making using multi-modal data sources, video streams, sensor inputs, environmental parameters. This helps one to get beyond the challenge of small datasets. System performance is discovered using benchmark datasets and video from actual traffic events. Better than the methods now in use, the results show object detection has 95% accuracy and anomaly detection has 92% accuracy. Promising for use in smart cities, the proposed framework exhibits scalability and flexibility over a wide range of events. Its characteristics, traffic optimization, safety monitoring, and data-driven urban planning, which comprise traffic control, safety monitoring, and data-driven urban planning, have the ability to drastically change urban transportation infrastructure management.

关键词： Accuracy Recurrent neural networks Smart cities Urban planning Object detection Streaming media Traffic control real-time systems Safety Monitoring

来源：评论

学校读者我要写书评

暂无评论

Development of real-time Unmanned Aerial Vehicle Urban Object Detection System with Federated learning

引用

JOURNAL OF AEROSPACE INFORMATION SYSTEMS 2024年第7期21卷 547-553页

作者： Lu, You-Ru Sun, Dengfeng Purdue Univ Sch Aeronaut & Astronaut W Lafayette IN 47906 USA

In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring and urban traffic management. The system includes an object detection algorithm, deep learning model training, and deployment on a real UAV. For the object detection algorithm, the Mobilenet-SSD model is applied owing to its lightweight and efficiency, which make it suitable for real-time applications on an onboard microprocessor. For model training, federated learning (FL) is used to protect privacy and increase efficiency with parallel computing. Last, the FL-trained object detection model is deployed on a real UAV for real-time performance testing. The experimental results show that the object detection algorithm can reach a speed of 18 frames per second with good detection performance, which shows the real-time computation ability of a resource-limited edge device and also validates the effectiveness of the developed system.

关键词： deep Convolutional Neural Network Computing Environments Reinforcement learning Embedded Systems Avionics Computers Track Algorithm image processing Computer Vision Electric Power Conversion

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：