检索结果-内蒙古大学图书馆

29th International Conference on systems, Signals and image processing (IWSSIP)

作者： da Silva Junior, Sergio A. Carvalho, Mateus F. T. Calomeno, Celso v. A. Q. Univ Estadual Maringa Dept Informat Maringa Brazil Univ Estadual Maringa Dept Biotecnl Genet & Biol Celular Maringa Parana Brazil

ISBN: (数字)9781665495783

ISBN: (纸本)9781665495783

The use of a computational approach in histological analysis can help in the acquisition and interpretation of results. In this work, we present a computational method to automate the morphometrical protocol proposed by Ewald R. Weibel in 1966. The method proposed here was based on the use of widely known image processing algorithms aiming to identify regions of interest (i.e. image segmentation, thresholding and flood fill). The method also uses mathematical morphology, such as the opening operator to filter the noise left by the thresholding. As a contribution of this work, we also created a software tool, named AutoGrid, to support reasearchers of biology labs apply the method. The proposal was evaluated on a set of images taken from rat prostate. In this scenario, we extracted data to perform histological analysis both using the software tool and following the manual protocol. When the tool was used (i.e. semi-automatic mode), the user was asked to perform a little manual intervention, and the most time consuming and tiring parts of the process runs automatically. Finally, the computational approach presented a faster (i.e. approximate to 45% less time) and less monotonous histological analysis, with statistically equivalent results to those obtained on the manual mode.

关键词： Weibel's Grid Biological tissue segmentation Mathematical Morphology

来源：评论

学校读者我要写书评

暂无评论

Effective in-the-Moment image Compression on FPGA: A Combinatorial Method Including DWT and IWT Techniques

Effective in-the-Moment Image Compression on FPGA: A Combina...

引用

International Conference on Advanced Computing and Communication systems (ICACCS)

作者： U. Dinesh v. Deepak Rajan S. Navaneethan Electronics and Communication Engineering Saveetha Engineering College Chennai India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

This paper presents an innovative way of image compression using Field-Programmable Gate Array (FPGA) implementation of the Integer Wavelet Transform (IWT) and Discrete Wavelet Transform (DWT) algorithms. For situations where resources are limited, the flexibility and adaptability offered by the FPGA architecture are ideal. Our technique strikes a compromise between compression effectiveness and image quality by utilizing DWT for multi-resolution analysis and IWT for spatial redundancy reduction. Real-time processing and resource optimization are ensured by the FPGA implementation. FPGA-optimized algorithms that tackle resource constraints are among the contributions. Evaluations demonstrate enhanced signal-to-noise ratios, compression ratios, and execution times. This study highlights how fast FPGA can compress images, especially for embedded systems and space missions. The study not only improves image compression but also highlights how FPGA can be used to increase the effectiveness of signal processing algorithms.

关键词： image coding Space missions Redundancy Signal processing algorithms Parallel processing Real-time systems Discrete wavelet transforms Field programmable gate arrays Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Classification using Phase Space Reconstruction Integrated Fine-tuned vGG19 Model 15

Bearing Fault Classification using Phase Space Reconstructio...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Swarup, Asim Rath, Soham Rout, Madhusmita Dash, Dipti Ranjan Wagh, Mamata P. C.V. Raman Global University Computer Science And Engineering Bhubaneswar India

ISBN: (纸本)9798350370249

Effective fault detection in rotating machinery is essential for ensuring industrial systems' reliability and operational efficiency. In this work, we proposed a method for fault detection using image matching technique. The continuous images generated from rotating machinery part are considered for experimentation. Traditional signal processing algorithms may fail to extract meaningful information from signals, particularly early in the fault growth process, they might miss the subtle changes that occur during the early phases of fault development. To address this problem an image-matching technique using visual Geometry Group 19 (vGG19) is adopted. The fundamental benefit of this approach is its ability to deal with the complexities of non-stationary chaotic line images, which frequently display temporal changes and noise interference of the expected fault. In the proposed technique, vibration signals are transformed into chaotic line images and vGG-19 architecture is employed to detect the fault from these images. The proposed technique enhances the sensitivity to faults while accommodating the complexities of non-stationary signals and noise by comparing generated images with the pre-stored images of normal and faulty occurrences. The approach showcases its capability to offer advanced warnings of potential malfunctions, enabling maintenance personnel to take proactive measures and prevent costly downtime. The proposed technique exhibits the advantage of improving the reliability and efficiency of industrial systems by enabling timely intervention and preventive maintenance. © 2024 IEEE.

关键词： chaotic line images CNN Fault detection rotating machinery template image-matching vGG-19

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Based Smart Intrusion Detection and Alerting System 10

Deep Neural Network Based Smart Intrusion Detection and Aler...

引用

10th International Conference on Communication and Signal processing, ICCSP 2024

作者： Karthikeyan, N. Mahapatro, Soumya Ranjan Akash, R. Rakesh Teja, P.v. Vellore Institute of Technology School of Computer Science and Engineering Chennai Campus Tamil Nadu India Vellore Institute of Technology School of Electronics and Comm. Engineering Chennai Campus Tamil Nadu India

ISBN: (纸本)9798350353068

With the increasing prevalence of surveillance systems, the need for an automated system that detects the presence of intruders from the surveillance camera and send an alert message to the user immediately has become very crucial. The research paper aims to provide a deep learning (DL) model-based solution to accurately detect the presence of human figures in the frame. The approach includes using YOLOv8 (You Only Look Once - version 8) object detection model to detect human figures, paired with the implementation of the Non-Maximum Suppression technique to remove duplicate bounding boxes around humans. Additionally, Gaussian Noise Reduction technique has been used to remove Gaussian blur from the image for obtaining a clearer image of human figure present in the frame. The research paper demonstrates a procedure to quickly send alert message to the user when a human figure is detected in the camera using the Telegram application. The paper also demonstrates the implementation of frame skipping method based on periodic intervals for optimizing the computational efficiency. In addition to this, the paper also demonstrates a comparative study between the frequently used human detection algorithms namely YOLOv8, YOLOv4, SSD and HOG and provides statistical proof on how YOLOv8 outperforms the other standard models. © 2024 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of American Sign Language Using Wavelet Transform and CNN

Performance Analysis of American Sign Language Using Wavelet...

引用

International Conference on Intelligent systems and Sustainable Computing, ICISSC 2022

作者： Thalange, A.v. Shrigandhi, M.N. Konapure, R.R. Ankaskar, v.N. Walchand Institute of Technology Solapur India

ISBN: (纸本)9789819947164

Sign languages play an important role to bridge the communication gap with hearing-impaired people. A lot of research is carried out to provide efficient, portable, and economical, tools, techniques, and products to make communication smooth, fast, and correct for both static and dynamic sign language recognition. For vision-based sign language recognition, various machine learning algorithms are used. Convolutional Neural Network (CNN) is one such method popularly used. However, the accuracy and speed of recognition are still a matter of concern, especially in dynamic sign language recognition. This paper presents the analysis of the performance of two methods Wavelet Transform and CNN for static American Sign Language (ASL) recognition in terms of (i) the average time of recognition, i.e., processing time for a single sign image, and (ii) accuracy, i.e., recognition rate. This work is carried out on signer-dependent static ASL images. It is observed that using CNN, the accuracy of recognition is 97.30%, and for Wavelet Transform it is 96.20%, indicating a very small difference. However, the average time required for recognition or the processing time for a single image using CNN is 41.2 s of CPU time, and using Wavelet Transform, it is 13.5 s of CPU time, which is almost 67% less than that required using CNN. Thus, compared to CNN, Wavelet Transform can be preferred in applications where timing is a major constraint. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

HarvestAI: IoT based Crop Protection and Wild Animal Monitoring

HarvestAI: IoT based Crop Protection and Wild Animal Monitor...

引用

2024 International Conference on Knowledge Engineering and Communication systems, ICKECS 2024

作者： Akash, R. Harish, S. Shinas, H. Sakthivel, S. vignesh, v. Karpagam College of Engineering Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359688

This research project introduces a novel approach to animal detection and repellence in agricultural settings, employing image processing techniques through deep learning algorithms. The system aims to mitigate the damage caused by wildife intrusion into farming areas. Upon detection of motion, the system triggers a message to a centralized control unit, which then utilizes the GSM network to alert farmers via NodeMCU devices. Furthermore, the system incorporates an innovative animal repellence mechanism to deter intruding animals effectively. Additionally, to address the issue of crop damage during rainy periods, a module is implemented to measure water levels using a level sensor. Excess water is efficiently removed from the land using a pump motor, thus safeguarding the crops from potential harm. The repellence system, integrated into the framework, employs advanced methods to deter animals from the farmland, contributing further to crop protection and farm sustainability. This integrated system offers an innovative solution for enhancing agricultural productivity and protecting crops, emphasizing the synergy between advanced technology and practical farming needs. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Monocular Depth Estimation of Noncooperative Spacecraft Based on Deep Learning

引用

JOURNAL OF AEROSPACE INFORMATION systems 2023年第6期20卷 334-342页

作者： Zhao, Erxun Zhang, Yang Gao, Jingmin Beijing Informat Sci & Technol Univ Sch Automat Beijing 100192 Peoples R China

Estimating position and stereographic geometry information of noncooperative spacecraft through three-dimensional (3-D) reconstruction techniques is of great significance. Depth information acquisition is an important component of 3-D reconstruction. Monocular cameras are cheaper and more widely used than depth sensors. The relative positions of noncooperative spacecraft and our spacecraft can be calculated from depth maps of monocular depth estimation and the camera parameters, providing data support for subsequent tracking and capture missions. This paper proposes a monocular depth estimation network combining the convolutional neural network (CNN) and a vision transformer (vIT) to improve the prediction accuracy of few-shot samples. We extract detail features and global features from the CNN and vIT encoders, respectively, and then fuse deep features and shallow features by a skip-connected upsampling decoder. Compared with the representative depth estimation algorithms in recent years on the NYU-Depth v2 dataset, the proposed network structure combines the advantages of the CNN and vIT as well as estimates the global depth of the scene more accurately while maintaining details. To solve the lack of spacecraft data collection, a new dataset is made from 3-D simulation models. Experiments on the self-made dataset demonstrate the feasibility of this method in aerospace engineering.

关键词： Spacecrafts Artificial Neural Network Sensors Aerospace Engineering Satellites Space Science and Technology Data Acquisition image processing Computer vision Aerial Cameras

来源：评论

学校读者我要写书评

暂无评论

IoT Based Forest Fire Detection Using Deep Learning Techniques- A Survey 5

IoT Based Forest Fire Detection Using Deep Learning Techniqu...

引用

5th International Conference on Intelligent Communication Technologies and virtual Mobile Networks, ICICv 2024

作者： Murugesan, M. Arun Kumar, K. Karthikeyan, v.v. Sivaranjani, S. Nirvin Chandar, R. Kishore, P. M.Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Thalavapalayam Karur639113 India M.Kumarasamy College of Engineering Department of Computer Science Engineering Thalavapalayam Tamilnadu Karur639113 India M.Kumarasamy College of Engineering Department of Electronics and Communication and Engineering Tamilnadu Thalavapalayam Karur639113 India M.Kumarasamy College of Engineering Department of Electronics and Communication Engineering Tamilnadu Thalavapalayam Karur639113 India

ISBN: (纸本)9798350385649

Real hazards to infrastructure, environmental systems, and human life come from forest fires. According to a survey, forest fire will damage the forest to a half by 2030. Forest fire can be prevented by taking actions by having fire detection devices. Most of the institutions and research development centers are attracted towards the fire detection systems. There are many sensors for detecting the fire but it also has many demerits like expensive, requires large space for installation and other problems. Due to the emergence of a digital camera, detection of fire has become easier. The use of sensors has many limitations but it is resolved by using image processing techniques. Because certain things share characteristics with fire, making accurate forest fire detection algorithms difficult, false alert rates may be significant. In this study, we may examine several ways for detecting forest fires and provide a brand-new, four-stage video-based method for detecting forest fires using image processing. To find moving areas, a background-subtraction technique is used first. Secondly, RGB color space is used to identify possible fire zones. Third, because candidate zone might have moving fire-like things, extraction of characteristics is employed to differentiate between the actual fire as well as fire-like items. The category of the fire can be determined by using the convolutional neural network method. Further incorporate devices for fire detection alerts into this system. © 2024 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

International Conference on Internet of Everything and Quantum Information processing, IEQIP 2023

International Conference on Internet of Everything and Quant...

引用

International Conference on Internet of Everything and Quantum Information processing, IEQIP 2023

ISBN: (纸本)9783031619281

The proceedings contain 31 papers. The special focus in this conference is on Internet of Everything and Quantum Information processing. The topics include: Revolutionizing Agriculture: A Mobile App for Rapid Plant Disease Prediction and Sustainable Food Security;EMG Based Human Machine Integration for IoT Based Instruments;medrack: Bridging Trust and Technology for Safer Drug Supply Chain Using Ethereum and IoT;a Review on Tuberculosis Pattern Detection Based on various Machine Learning Techniques;sensor Based Hand Gesture Identification for Human Machine Interface;an Improved Detection System Using Genetic Algorithm and Decision Tree;a Detailed Analysis of Colorectal Polyp Segmentation with U-Network;a Review on Internet of Things (IoT): Parkinson’s Disease Monitoring Device;Machine Learning-Based Prediction of Temperature Rise in Squirrel Cage Induction Motor (SCIM);quantum Many-Body Problems: Quantum Machine Learning Applications;Experimental Study on the Impact of Airborne Dust Deposition on Pv Modules Using Internet of Things;bidirectional Converter with Time Utilization-Based Tariff Investigation and IoT Monitoring of Charging Parameters Based on G2v and v2G Operations;predictive Analysis of Telecom Customer Churn Using Machine Learning Techniques;baker’s Map Based Chaotic image Encryption in Military Surveillance systems;Cyber Security Investigation of GPS-Spoofing Attack in Military UAv Networks;ioT Based Enhanced Safety Monitoring System for Underground Coal Mines Using LoRa Technology;ioT Based Hydroponic System for Sustainable Organic Farming;predicting Stride Length from Acceleration Signals Using Lightweight Machine Learning algorithms;unveiling Hate: Multimodal Perspectives and Knowledge Graphs;vision-Based Toddler Activity Recognition: Challenges and Applications;automated W-Sitting Posture Detection in Toddlers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote Plant Disease Diagnosis

Remote Plant Disease Diagnosis

引用

2023 Intelligent Computing and Control for Engineering and Business systems, ICCEBS 2023

作者： Sree, R. Sharmikha Niranjan Kumar, S.K. Meera, S. Karthikeyan, S.v. Nithish Kumar, S. Jaya Kumar, S. Sri Sairam Engineering College Computer Science and Engineering Chennai India

ISBN: (纸本)9798350394580

One of the key factors that determines the loss of agricultural production and in its yield is the discernment and recognition of plant diseases. Plant disease research is the investigation of any visible points of defects in any portion of the plant that differentiates it from others. Identifying the disease requires a great deal of effort and competence, as well as extensive knowledge of plants and disease detection investigations. The methods of image accession, extraction, segmentation, and pre-processing of the image's layers, are used to detect diseases, commonly, and still here. This paper presents the technical architecture of our solution, highlighting the integration of Python, FastAPI, and *** to detect plant diseases and demonstrates its effectiveness through comprehensive testing and evaluation. The results indicate high accuracy in disease detection and underscore the system's potential to revolutionize potato crop health monitoring. © 2023 IEEE.

关键词： Accuracy Agriculture CNN algorithms disease detection Endpoints FastAPI Python React.js

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：