检索结果-内蒙古大学图书馆

Illuminating Solar Potential: A real-time deep learning, IoT, and image processing Approach to Ground-Based Cloud Movement Forecasting for Enhanced Solar Energy Management

Illuminating Solar Potential: A Real-Time Deep Learning, IoT...

引用

Women in Computing (InCoWoCo), International Conference for

作者： P.K.M. Perera K.B.S. Karunarathna S. Hewawalpita S.M. Dassanayake Department of Decision Science Faculty of Business University of Moratuwa Sri Lanka

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Cloud movement impacts the performance of photovoltaic (PV) power plants by causing sudden fluctuations in output power, leading to voltage instability in connected electricity networks. This paper introduces a novel and cost-effective deep learning solution for forecasting shortterm cloud movement to regulate PV power output. The methodology involves capturing raw image data through a PyCamera connected to a Raspberry Pi, followed by rigorous pre-processing and cloud detection techniques. Using colourbased segmentation, morphological operations, and contour analysis, the developed pipeline accurately identifies cloud regions in images and predicts their movement for the subsequent time interval. The proposed algorithm is designed to be efficient, lightweight, and suitable for deployment on low-cost processors. This study successfully implements and optimizes a cloud detection system for resource-constrained environments using the Raspberry Pi 4 Model B. The method significantly improves inference speed and model efficiency while addressing the high latency constraints associated with embedded devices with execution periods measured in seconds. The model performance metrics validate the approach, with an accuracy of 89.84%, indicating the practical potential of the model for real-time applications, offering a promising solution towards the integration of effective cloud forecasting into cost-sensitive energy management systems.

关键词： Cloud computing image segmentation Adaptation models Computational modeling Pipelines Predictive models real-time systems Sun Forecasting Morphological operations

来源：评论

学校读者我要写书评

暂无评论

real-time image processing and deep learning 2021

Real-Time Image Processing and Deep Learning 2021

引用

real-time image processing and deep learning 2021

ISBN: (纸本)9781510643093

The proceedings contain 20 papers. The topics discussed include: a review of real-time human action recognition involving vision sensing;embedded real-time people detection and tracking with time-of-flight camera;real-time object detection in 360-degree videos;a real-time software framework for driver monitoring systems: software architecture and use cases;real time circle detection by simplified Hough transform on smartphones;the evaluation of CUDA performance on the Jetson NanoBoard for an image binarization task;chest X-ray classification using transfer learning on multi GPU;and parallel implementation of a hyperspectral feature extraction method based on Gabor filter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

deep learning- and image processing-based methods for automatic estimation of leaf herbivore damage

引用

METHODS IN ECOLOGY AND EVOLUTION 2024年第4期15卷 732-743页

作者： Wang, Zihui Jiang, Yuan Diallo, Abdoulaye Banire Kembel, Steven W. Univ Quebec Montreal Dept Sci Biol Montreal PQ Canada Sun Yat Sen Univ Sch Ecol Guangzhou Peoples R China Univ Quebec Montreal Dept Informat Montreal PQ Canada

Quantifying the intensity of leaf herbivory pressure is crucial for understanding the interaction between plants and herbivores in both applied and basic science. Visual estimates and digital analysis have been commonly used to estimate leaf herbivore damage but are time-consuming which limits the amount of data that can be collected and prevent answering big picture questions that require large-scale sampling of herbivory pressure. Recent developments in deep learning have provided a potential tool for automatic collection of ecological data from various sources. However, most applications have focused on identification and counting, and there is a lack of deep learning tools for quantitative estimation of leaf herbivore damage. Here, we trained generative adversarial networks (GANs) to predict the intact status of damaged leaves and applied image processing technique to estimate the area and percentage of leaf damage. We first described procedures for collecting leaf images, training GAN models, predicting intact leaves and calculating leaf area, with a Python package provided to enable hands-on application of these procedures. Then, we collected a large leaf data set to train a universal deep learning model and developed an online app HerbiEstim to allow direct use of pretrained models to estimate herbivory damage of leaves. We tested these methods using both simulated and real leaf damage data. The procedures provided in our study greatly improved the efficiency of leaf herbivore damage estimation. Our test demonstrated that the reconstruction of damaged leaf image resembled the ground-truth image with a similarity of 98.8%. The estimation of leaf herbivore damage exhibited a high accuracy with an averaged root mean square error of 1.6% and had a general applicability to different plant taxa and leaf shapes. Overall, our work demonstrated the feasibility of applying deep learning techniques to quantify leaf herbivory intensity. The use of GANs allows automatic e

关键词： data collection deep learning generative adversarial network image processing leaf herbivore damage

来源：评论

学校读者我要写书评

暂无评论

Integrating deep learning, satellite image processing, and spatial-temporal analysis for urban flood prediction

引用

JOURNAL OF HYDROLOGY 2024年 639卷

作者： Mohamadiazar, Nasim Ebrahimian, Ali Hosseiny, Hossein Florida Int Univ Dept Civil & Environm Engn 10555 W Flagler St Miami FL 33174 USA Villanova Univ Dept Civil & Environm Engn 800 Lancaster Ave Villanova PA 19085 USA

Urban flooding is escalating worldwide due to the increasing impervious surfaces from urban developments and frequency of extreme rainfall events by climate change. Traditional flood extent prediction and mapping methods based on physical-based hydrological principles often face limitations due to model complexity and computational burden. In response to these challenges, there has been a notable shift toward satellite image processing and Artificial Intelligence (AI) based approaches, such as deep learning (DL) models, including architectures like Convolutional Neural Networks (CNN). The objective of this research is to predict near real-time (NRT) flood extents within urban areas. This research integrated CNN (U-Net) with Sentinel-1 satellite imagery, Digital Elevation Model (DEM), hydrologic soil group (HSG), imperviousness, and rainfall data to create a flood extent prediction model. To detect flooded areas, a binary raster map was created using calibrated backscatter values derived from the VV (vertical transmit and vertical receive) polarization mode of Sentinel-1 imagery, which was highlighted as having a significant impact on backscatter behavior and prediction results. Application of the model was demonstrated in urban areas of Miami-Dade County, Florida. The results demonstrated the capability of the model to provide rapid and accurate flood extent predictions at a spatial resolution of 10 m, with an overall accuracy of 97.05 %, F-1 Score of 92.49 %, and AUC of 93 % in the study area. The U-Net model's flood predictions were compared with historical floodplain data and then using GIS overlay analysis, resulting in a Ground Truth Index of 84.05 % that shows the accuracy of the model in identifying flooded areas. The research incorporated crucial flood-influencing data (including rainfall) to the flood extent prediction models and expanded the focus models beyond major rainfall events only to encompass a wider range of flood events. The presented NRT flood e

关键词： Near real -time Flood Mapping Convolutional Neural Networks (CNN) U -Net Machine learning Florida Sentinel-1

来源：评论

学校读者我要写书评

暂无评论

Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy grading

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024年 249卷 108160-108160页

作者： Romero-Oraa, Roberto Herrero-Tudela, Maria Lopez, Maria I. Hornero, Roberto Garcia, Maria Univ Valladolid Biomed Engn Grp Valladolid 47011 Spain Ctr Invest Biomed Red Bioingn Biomat & Nanomed CIB Zaragoza Spain

Background and objective: Early detection and grading of Diabetic Retinopathy (DR) is essential to determine an adequate treatment and prevent severe vision loss. However, the manual analysis of fundus images is time consuming and DR screening programs are challenged by the availability of human graders. Current automatic approaches for DR grading attempt the joint detection of all signs at the same time. However, the classification can be optimized if red lesions and bright lesions are independently processed since the task gets divided and simplified. Furthermore, clinicians would greatly benefit from explainable artificial intelligence (XAI) to support the automatic model predictions, especially when the type of lesion is specified. As a novelty, we propose an endto-end deep learning framework for automatic DR grading (5 severity degrees) based on separating the attention of the dark structures from the bright structures of the retina. As the main contribution, this approach allowed us to generate independent interpretable attention maps for red lesions, such as microaneurysms and hemorrhages, and bright lesions, such as hard exudates, while using image-level labels only. Methods: Our approach is based on a novel attention mechanism which focuses separately on the dark and the bright structures of the retina by performing a previous image decomposition. This mechanism can be seen as a XAI approach which generates independent attention maps for red lesions and bright lesions. The framework includes an image quality assessment stage and deep learning-related techniques, such as data augmentation, transfer learning and fine-tuning. We used the architecture Xception as a feature extractor and the focal loss function to deal with data imbalance. Results: The Kaggle DR detection dataset was used for method development and validation. The proposed approach achieved 83.7 % accuracy and a Quadratic Weighted Kappa of 0.78 to classify DR among 5 severity degrees, which outp

关键词： Diabetic retinopathy grading Fundus images deep learning Attention mechanism Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on design of image processing and recognition based on deep learning

Research on design of image processing and recognition based...

引用

2024 International Conference on Physics, Photonics, and Optical Engineering, ICPPOE 2024

作者： Li, Yanan Wang, Hua Li, Yongbo Guangdong University of Science and Technology Guangdong Dongguan523668 China

ISBN: (数字)9781510689121

ISBN: (纸本)9781510689114

To achieve target detection and defect recognition in power inspection images, an image processing and recognition algorithm based on deep learning is proposed. This algorithm mainly adopts an improved Faster-RCNN model, combined with HSI color feature extraction, for real-time image processing and identification of various conventional faults. Firstly, the collected power inspection images are normalized, converting the RGB colors of the images to HSI colors. By traversing each pixel in HSI space, it is determined whether there is a fault in the pixel based on the color characteristics of the image. Secondly, a DenseNet network is constructed and connected to the RoIAlign layer and prediction layer. Finally, the identification of target defects is achieved through Faster-RCNN. Simulation results show that the algorithm can accurately identify fault defects with a precision of up to 94.60%, indicating a broad application prospect in power equipment defect recognition. © 2025 SPIE.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

image processing and Visualization Technology Application of an Improved deep learning Algorithm 2

Image Processing and Visualization Technology Application of...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Deng, Yunsheng Huang, Yinghui Chen, Zhangbao Chen, Yan Bengbu University Bengbu Anhui Huainan City China

ISBN: (纸本)9798350372892

In today's world, technology is changing our way of life and work at an alarming rate. This paper studies the performance of an improved deep learning algorithm in image processing tasks, introduces the implementation principle of algorithm design, and puts forward an improved deep learning algorithm. In the experimental method part, a group of experiments are designed to evaluate the image quality performance of the improved deep learning algorithm, which is based on three key performance indicators: Peak Signal-to-Noise Ratio (PSNR), Interactive Response time (IRT) and Structural Similarity Index Measure (SSIM). The research conclusion shows that the peak signal-to-noise ratio (PSNR) of the improved image quality-preserving deep learning algorithm is as high as 58 dB. The maximum IRT measurement of the improved algorithm is only 95 ms, which provides users with faster response speed and enables users to experience a smoother interactive experience in real-time image processing applications. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Volume Control Using image processing and deep learning Techniques: A Review

Automatic Volume Control Using Image Processing and Deep Lea...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Theraja, Kinshuk Gupta, Sakshi Gupta, deepak Kumar Amity Institute of Information and Technology Amity University Noida India

ISBN: (纸本)9798350375237

This paper presents an innovative approach to automatic volume control using image processing and deep learning techniques. The ability to automatically adjust volume levels based on environmental factors and user preferences has significant implications for various audio applications, including teleconferencing systems, smart devices, and public address systems. By combining image processing algorithms with deep learning models, this paper aims to develop a robust and adaptive volume control system capable of accurately adjusting audio levels in real-time. The paper discusses the theoretical foundations, technical implementation, experimental results, and potential applications of the proposed automatic volume control system. © 2024 IEEE.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Combining deep learning with chemometrics when it is really needed: A case of real time object detection and spectral model application for spectral image processing

引用

ANALYTICA CHIMICA ACTA 2022年 1202卷 339668-339668页

作者： Xu, Junli Mishra, Puneet Univ Coll Dublin UCD Sch Biosyst & Food Engn Dublin 4 Ireland Wageningen Food & Biobased Res Bornse Weilanden 9POB 17 NL-6700 AA Wageningen Netherlands

deep learning (DL) being popularly used in computer vision applications is still in its early stage in chemometric domain for spectral image processing. Often the challenge is that there are too few samples from analytical laboratory experiments to preform DL. In this study, we present a novel combination of DL and chemometrics to process spectral images even with as few as < 100 spectral images. We divided the image processing part such as object detection and recognition as the DL task and prediction of chemical property as the chemometric task based on latent space modelling. For image processing tasks of object detection and recognition, transfer learning was performed on the pretrained YOLOv4 object detection network weights to adapt the model to work well on spectral images captured in laboratory settings. Once the object is identified with DL, a background query is performed for the pre-built chemometric models to select the model for predicting the properties for specific object. The obtained results showed good potential of using DL and chemometric approaches in conjunction to reap the best of both scientific domains. This approach is of high interest to whoever involved in spectral imaging and dealing with object detection and physicochemical properties prediction of the samples with chemometric approaches.(c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Transfer learning Fruit spectroscopy image processing Object detection

来源：评论

学校读者我要写书评

暂无评论

TrashIntelAI- Garbage Collection Automation using deep learning and image processing

TrashIntelAI- Garbage Collection Automation using Deep Learn...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Jadhav, Ranjana Mhaske, Aditya Nawale, Aditya Oswal, Mokshit Mulhar, Sumit Vishwakarma Institute of Technology Dept. of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798350308167

Garbage collection in urban areas has become a major challenge due to the increase in trash production. New technologies, including the application of deep learning and image processing methods, have been created to solve this problem. In this study, we present an automated garbage collection system that recognizes and categorizes rubbish in real-time using computer vision and machine learning methods. A deep learning model classifies the garbage into several categories, and the system also contains an image processing pipeline that pre-processes incoming photos and extracts relevant data. We executed experiments on a real-world dataset to assess the performance of the suggested solution. The outcomes demonstrate that the suggested approach classifies garbage with a high degree of accuracy. The system can recognize and categorize various waste categories, including recyclables, organic garbage, and non-recyclables, which can then be collected individually for proper disposal. This is made possible by the application of deep learning and image processing algorithms. The suggested approach can potentially increase trash disposal efficiency, reduce waste sent to landfills, and promote a cleaner and healthier environment in metropolitan settings. The burden of garbage collection staff can be reduced, and the danger of harm can be reduced, with real-time monitoring and automated waste collection. © 2023 IEEE.

关键词： deep learning image processing mobile application object detection smart city waste management

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：