检索结果-内蒙古大学图书馆

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal processing (INCOS)

作者： Oviya Gnanasekar Prapti Dinesh Srividhya K Department of ECE SVCE -Affiliated to Anna University Sriperumbudur Chennai India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Agriculture is one of the most important industries in any economy since it plays a big role in the food supply chain. Agricultural fields, on the other hand, confront a number of issues, including animal encroachment, which can cause severe crop damage and loss. Traditional animal control tactics, such as electrical fences, physical barriers, and scarecrows, can be inefficient, time-consuming and a serious threat to animal lives. The animals either become entangled in the fence's wire mesh or were electrocuted by the electric lines. To overcome these problems we propose a unique method that involves image processing-based animal incursion detection system in agricultural fields using Raspberry Pi and deep learning technique, mainly the YOLOv7. This technology captures live video feeds of agricultural fields using a camera and analyses them using deep learning algorithm to detect any animal invasions. If an intrusion is detected, the system emits specific repellent sounds for specific animal via speakers in order to scare them away and alerts the farmers by sending SMS. This method provides an efficient and practical alternative for crop damage prevention and human-wildlife conflict reduction in agricultural settings.

关键词： deep learning Analytical models Animals Webcams Wires Supply chains Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

image Recognition and processing Algorithm of Power Grid Facilities Map Based on deep learning

Image Recognition and Processing Algorithm of Power Grid Fac...

引用

Software Engineering, Social Network Analysis and Intelligent Computing (SSAIC), Asia-Pacific Conference on

作者： Li Wang Fei Chen Yuxiang Wang Ying Liu Chen Luo Guizhou Power Grid Company Limited Guiyang Guizhou China

ISBN: (数字)9798350393682

ISBN: (纸本)9798350393699

The traditional image processing method of power grid facilities map is based on iconography, which can alleviate the artificial pressure to a certain extent. However, due to the slow speed and low accuracy of the traditional iconography method, it is difficult to be applied in the field of fault inspection. In order to realize intelligent power inspection more quickly and accurately, an image recognition and processing algorithm of power grid facilities map based on deep learning is proposed to solve the problems of occlusion, inaccurate classification and insufficient feature extraction in the actually collected power grid facilities map images. The convolution operation module and residual module in YOLOv5 algorithm are improved, and the learning depth of the algorithm is deepened by increasing the number of convolution layers. At the same time, the SENet attention mechanism is added to the basic convolution module. The research results show that the accuracy of this model for power equipment identification has reached more than $99 \%$. And the recognition accuracy of fault defects can reach $\mathbf{9 2. 7 4 6} \%$. This model improves the detection accuracy and speed of power grid facilities map images, and also provides a novel and feasible scheme for intelligent detection of power grid facilities map images.

关键词： YOLO deep learning Accuracy image recognition Convolution Computational modeling Inspection

来源：评论

学校读者我要写书评

暂无评论

image and Video Captioning Using deep learning and Natural Language processing

Image and Video Captioning Using Deep Learning and Natural L...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Manoj Naidu Athrva Kulkarni Sahil Kadam Siddhesh Joshi Nilesh P. Sable Anuradha Yenkikar Department of CSE – Artificial Intelligence Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

deep learning models have been a huge success in image recognition which hence can be used for the purpose of text generation. In the field of imaging science, captioning images and videos is regarded as an intellectually difficult job. Visual Geometry Group (VGG); is a standard deep Convolutional Neural Network (CNN) architecture with multiple layers, specifically focusing on the integration of CNN for image feature extraction. Exploring this underlying method, the use of another model is essential for caption generation. Here the Recurrent Neural Network (RNN) comes in use for caption generation from the extracted features. Models named Long Short-Term Memory (LSTM) based on RNN and Bidirectional encoder representation transformer (BERT) based on Transformers have been prominent in ensuring accurate results. The Flicker8k dataset is used which provides a variety of information useful for model training. By testing validation data along with evaluation metrics, we analyze the effectiveness of different models to create consistent and descriptive headlines. Extending our inquiry to encompass title generation using transformer models, while also exploring learning techniques for real-time title generation and delivery using the Open-CV library available in Python to get the output from the camera and display it on screen. The result shows that the LSTM is the best model for captioning, with an accuracy of 65.07% at the epochs of 300 and the BERT model has an accuracy of 31% at the epochs of 2. The findings of this study not only contribute to advancing subtitle enhancement methodologies but also broaden the potential applications of deep learning techniques in this domain.

关键词： deep learning Recurrent neural networks Accuracy Computational modeling Bidirectional control Transformers Feature extraction Encoding Data models Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A mechatronics data collection, image processing, and deep learning platform for clinical posture analysis: a technical note

引用

PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE 2021年第3期44卷 901-910页

作者： Salahzadeh, Zahra Rezaei-Hachesu, Peyman Gheibi, Yousef Aghamali, Ali Pakzad, Hamed Foladlou, Saeideh Samad-Soltani, Taha Tabriz Univ Med Sci Fac Rehabil Physiotherapy Dept 29 Bahman St Tabriz Iran Tabriz Univ Med Sci Sch Management & Med Informat Dept Hlth Informat Technol Tabriz Iran Univ Tabriz Fac Comp Engn Dept Artificial Intelligence Tabriz Iran Sanam Sahand Hlth Promot Ind Dept Res & Dev Tabriz Iran Islamic Azad Univ Tabriz Dept Biomed Engn Tabriz Iran

Static and dynamic posture analysis was a critical clinical examination in physiotherapy and rehabilitation. It was a time-consuming task for clinicians, so a semi-automatic method can facilitate this process as well as provide well-documented medical records and strong infrastructure for deep learning scenarios. The current research presents a mechatronics platform for static and real-time dynamic posture analysis, which consisted of hybrid computational modules. Our study was a developmental and applied research according to a system development life cycle. The designed modules are as follows: (1) a mechanical structure includes patient place, 360-degree engine, mirror, laser, distance meter, and cams;(2) a software module includes data collection, electronic medical record, semi-automatic image analysis, annotation, and reporting, and (3) a network to exchange raw data with deep learning server. Patients were informed about the research by their healthcare provider and all data were transformed into a Fourier format, in which the patients remained autonomous without a bit of information. The results show acceptable reliability and validity of the instruments. Also, a telerehabilitation application was designed to cover the patients after diagnosis. We suggest a longer time for data acquisition. It will lead to a more accurate and fully automated dynamic posture analysis. The result of this study suggest that the designed mechatronics device used in conjunction with smartphone application is a valid tool that can be used to obtain reliable measurements.

关键词： Posture image processing Telerehabilitation Decision support system

来源：评论

学校读者我要写书评

暂无评论

Automatic Chart Decoding System Based on deep learning and image processing

Automatic Chart Decoding System Based on Deep Learning and I...

引用

Artificial Intelligence and Intelligent Manufacturing (AIIM), International Symposium on

作者： Chaofan Liang Fenghao Xue Zhangwei Li College of Software Engineering Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798331541729

ISBN: (纸本)9798331541736

Statistical Charts contain a wealth of information. As an important way to visualize data presentation, statistical charts allow viewers to obtain a complete and intuitive understanding of the content shown in a very short time. At present, the research on automatic extraction and understanding of a large amount of text information has been relatively mature. However, even the latest big artificial intelligence models cannot accurately extract statistical graphs, which are personalized and contain a large amount of information. We propose an automatic bar chart data extraction process by combining deep learning and image processing technology, and construct an intelligent bar chart decoding system. The system is divided into three parts: the classification of statistical chart types, the text detection in the image, the classification of text roles and the image extraction. The original data used to create the chart in the pan-bar graph image is extracted for downstream applications. We evaluate and compare our system on public datasets. The results show that our system has better accuracy.

关键词： deep learning Accuracy Heavily-tailed distribution Text recognition Text detection Decoding Manufacturing Data mining Artificial intelligence Bars

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition (HAR) using image processing on deep learning 13

Human Action Recognition (HAR) using Image Processing on Dee...

引用

13th IEEE International Conference on Control System, Computing and Engineering, ICCSCE 2023

作者： Ismail, Ahmad Puad Azahar, Muhammad Afiq Bin Tahir, Nooritawati Md Daud, Kamarulazhar Kasim, Nazirah Mohamat Universiti Teknologi Mara Cawangan Pulau Pinang Electrical Engineering Studies Malaysia Universiti Teknologi Mara Electrical Engineering Studies Shah Alam Malaysia

ISBN: (纸本)9798350323184

The advancement of artificial intelligence (AI) has bought many advances to human society as a whole. By using daily activities and integrating the technology from the fruits of AI, we can manage to gain further access to knowledge we can only begin to imagine. In identifying human action recognition (HAR);processing photos and videos to discern whether a human is present, then mapping the subject classified, which lastly determines the action being carried out is the objective. To achieve this, various steps are taken and careful approach is required, with the extensive amount of research, numerous troubleshooting and experimentation is required. The AI architecture has to learn from dataset collected for it to discern the identification of action properly. HAR is achieved by using Python code using real-time webcam feed. Human pose detection library known as MediaPipe Pose Detection detects human anatomy from input through joints key-points. MediaPipe algorithm that extract features in x-y-z axis with visibility (four variables) and the extracted data is trained using CNN-LSTM based on the trained and tested algorithm classifier model. The output obtained produced an RGB-skeleton and an action label on the detected subject as standing, waving, walking and sitting, has yielded good results. © 2023 IEEE.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

A real-time traffic sign detection in intelligent transportation system using YOLOv8-based deep learning approach

引用

SIGNAL image AND VIDEO processing 2024年第8-9期18卷 6103-6113页

作者： Tang, Mingdeng Chongqing Vocat Inst Safety & Tech Dept Network & Informat Secur Chongqing 404120 Peoples R China

Intelligent transportation systems rely heavily on accurate traffic sign detection (TSD) to enhance road safety and traffic management. Various methods have been explored in the literature for this purpose, with deep learning methods consistently demonstrating superior accuracy. However, existing research highlights the persistent challenge of achieving high accuracy rates while maintaining non-destructive and real-time requirements. In this study, we propose a deep learning model based on the YOLOv8 architecture to address this challenge. The model is trained and evaluated using a custom dataset, and extensive experiments and performance analysis demonstrate its ability to achieve precise results, thus offering a promising solution to the current research challenge in deep learning-based TSD.

关键词： Traffic sign detection deep learning YOLOv8 model real-time Intelligent transportation

来源：评论

学校读者我要写书评

暂无评论

Efficient NPU-GPU scheduling for real-time deep learning inference on mobile devices

引用

JOURNAL OF real-time image processing 2025年第2期22卷 1-13页

作者： Yu, Chengwu Wang, Meng Chen, Shan Wang, Wanqi Fang, Weiwei Chen, Yanming Xiong, Neal N. Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing 100044 Peoples R China Hubei Engn Res Ctr Intelligent Detect & Identifica Wuhan 430205 Hubei Peoples R China Anhui Univ Sch Comp Sci & Technol Hefei 230601 Anhui Peoples R China Sul Ross State Univ Dept Comp Sci & Math Alpine TX 79830 USA

As the need for on-device artificial intelligence (AI) has increased in recent years, mobile devices tend to be equipped with multiple heterogeneous processors, including CPU, GPU, and Neural processing Unit (NPU). While NPUs can offer low-cost and real-time AI processing capabilities for deep Neural Network (DNN) inference, its limited resources often lead to a trade-off between performance and accuracy, potentially resulting in a non-trivial accuracy drop. To address this problem, we propose a new NPU-GPU Scheduling (NGS) framework for DNN-based video analytics. The main challenge lies in determining when and how to execute inference on the NPU/GPU to satisfy the performance objectives. To make more precise scheduling decisions, we first propose a new image complexity assessment model to replace the existing normalized edge density metric. Then, we formulate the scheduling problem with the objective of maximizing inference accuracy under the given latency constraint, and introduce an adaptive solution based on dynamic programming to determine which frames should be processed on the GPU and when to exit from inference for each of them. Extensive experiments conducted on a real mobile device show that our NGS framework substantially outperforms other solutions, and achieves a close-to-oracle performance.

关键词： Edge computing DNN inference Heterogeneous processors Task scheduling Dynamic Programming

来源：评论

学校读者我要写书评

暂无评论

Speed-Up DDPM for real-time Underwater image Enhancement

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第5期34卷 3576-3588页

作者： Lu, Siqi Guan, Fengxu Zhang, Hanyu Lai, Haitao Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Heilongjiang Peoples R China

Underwater images often suffer from serious color bias and blurred features because of the effect of the water bodies on the light. To enhance underwater images, we present SU-DDPM, a method of real-time underwater image enhancement (UIE) based on a denoising diffusion probabilistic model (DDPM). SU-DDPM outperforms other baseline and generative adversarial network models in underwater image enhancement, thus establishing a new state-of-the-art baseline. SU-DDPM processes images more rapidly than the diffusion model, which makes it competitive with other deep learning-based methods. We demonstrate that if conditional DDPM is used directly for the UIE task, the processing speed is slow, and the enhanced images are of poor quality and show color bias. The quality of the enhanced image is improved by combining the degraded image with the reference image in the diffusion stage to create a fusion-DDPM model. The specificity of the UIE task allows us to accelerate the inference process by changing the initial sampling distribution and reducing the number of iterations in the denoising stage of the model. We evaluate SU-DDPM on the UIE task using challenging real underwater image datasets and a synthetic image dataset and compare it to state-of-the-art models. SU-DDPM ensures increased enhancement quality, and enhancement processing speed is comparable to the speed of real-time enhancement models.

关键词： Underwater image enhancement denoising diffusion probabilistic model (DDPM) underwater image restoration deep learning

来源：评论

学校读者我要写书评

暂无评论

Nanotechnology in Biomedical image processing Using Ensemble deep learning Approach 2

Nanotechnology in Biomedical Image Processing Using Ensemble...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Ancysophia Thomas, M. Esakkiammal, S. Jayanthi, N. Kamalarajan, P. Yamini, G. Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Tamil Nadu India Department of Chemistry St. Mother Theresa Engineering College Vagaikulam Tamil Nadu Thoothukudi India Institute of Management Nirma University Tragad Ahmedabad Gota India Department of Physics R. M. K. College of Engineering and Technology Tamil Nadu India Department of Chemistry R.M.D. Engineering College India Department of English Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology India

ISBN: (纸本)9798331541217

Correct identification of the most recent case of pneumonia fever determines successful therapy and management of the condition. Computable tomography (CT) scans can rapidly and precisely classify and evaluate cases of pneumonia fever. Almost every hospital has chest CT scanning available, which lets one rapidly classify pneumonia fever sufferers. Considering the great availability of chest CT imaging, this seems reasonable. The chest CT-based pneumonia fever categorization requires a lot of time with fast spreading infections. Medical staff workers should be able to gain from automated CT scan analysis considering their busy schedules. In the framework of this work, we build a feature extraction and classification system leveraging CT scan inputs. Part of the framework's training and testing courses is teaching the classifier-in charge of creating a model that exactly classifies entering CT images. This module among others makes up the framework. The classifier in this work is convolutional neural network (CNN) variants. The performance of the present model is evaluated by the simulation;the results show that the suggested method achieves better accuracy than any other classifications. © 2024 IEEE.

关键词： Convolutional neural networks

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：