检索结果-内蒙古大学图书馆

7th International conference on Electronics Technology, ICET 2024

作者： Ling, Long Lu, Zhijun Shi, Manli Wang, Jie Li, Yuqing Hu, Minghe Beijing Institute of Space Mechanics & Electricity China Academy of Space Technology Beijing China

ISBN: (纸本)9798350363951

In order to meet the real-time detection and processing requirements of on-board targets in the field of remote sensing image processing, this paper carries out relevant research from the perspective of software optimization and proposes an onboard adaptive image windowing processing method based on differential evolution algorithm to solve the problem of shortage of on-board hardware computing resources. Based on the adaptive differential evolution algorithm, combined with the engineering application scenario, the algorithm innovatively designs an individual objective function to evaluate the 'advantages and disadvantages' of the algorithm evolution results. By coordinating all the target positions to be tracked in the image plane, the algorithm optimizes the number of windows, and considers the application boundary of the algorithm, which can effectively reduce the amount of data to be processed and greatly improve the timeliness of real-time detection on the board without losing the calculation accuracy. © 2024 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Lightweight Machine Sound Anomaly Detector Based on Parallel Discrete Wavelet Transform

引用

IEEE SENSORS JOURNAL 2025年第10期25卷 18529-18542页

作者： Choi, Eunhye Park, Hyunggon Agcy Def Dev Daejeon 34186 South Korea Ewha Womans Univ Dept Elect & Elect Engn Seoul 03760 South Korea

The development of Industrial Internet of Things (IIoT) technology and network infrastructures has enabled the acquisition of substantial data, enabling data-driven condition monitoring and analysis. Detecting anomalies in machinery equipment is crucial in IIoT environments for safety enhancement, productivity, and reliability. To provide effective anomaly detection at IIoT edge nodes without delay, it is necessary to efficiently collect and process vast amounts of data from various sensors. While this demands a significant amount of computing resources, edge nodes only have limited data storage and processing capabilities. Therefore, our focus is on developing a lightweight anomaly detection algorithm for acoustic signal processing, considering the computational resources of the IIoT edge node. In this article, we propose the parallel discrete wavelet transform (PDWT) as an efficient method for compressing and processing acoustic signals received at edge nodes. This approach significantly alleviates memory consumption and reduces the computational time at the edge. In addition, by harnessing preprocessed features through PDWT, we can develop lightweight anomaly detection models suitable for deployment at the edge, making them highly practical for real-world implementation. The experimental results using real-world data collected from industrial machines confirm the effectiveness of the proposed solution.

关键词： Anomaly detection Feature extraction image edge detection Acoustics Industrial Internet of Things Computational modeling Training Autoencoders Transforms Discrete wavelet transforms Acoustic signal anomaly detection autoencoder discrete wavelet transform (DWT) edge computing Industrial Internet of Things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

COARSE-FINE SPECTRAL-AWARE DEFORMABLE CONVOLUTION FOR HYPERSPECTRAL image RECONSTRUCTION 31

COARSE-FINE SPECTRAL-AWARE DEFORMABLE CONVOLUTION FOR HYPERS...

引用

2024 International conference on image processing

作者： Yang, Jincheng Wang, Lishun Cao, Miao Wang, Huan Zhao, Yinping Yuan, Xin Northwestern Polytech Univ Xian Peoples R China Westlake Univ Hangzhou Peoples R China

ISBN: (纸本)9798350349405;9798350349399

We study the inverse problem of Coded Aperture Snapshot Spectral Imaging (CASSI), which captures a spatial-spectral data cube using snapshot 2D measurements and uses algorithms to reconstruct 3D hyperspectral images (HSI). However, current methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies and non-local similarities. The recently popular Transformer-based methods are poorly deployed on downstream tasks due to the high computational cost caused by self-attention. In this paper, we propose Coarse-Fine Spectral-Aware Deformable Convolution Network (CFSDCN), applying deformable convolutional networks (DCN) to this task for the first time. Considering the sparsity of HSI, we design a deformable convolution module that exploits its deformability to capture long-range dependencies and non-local similarities. In addition, we propose a new spectral information interaction module that considers both coarse-grained and fine-grained spectral similarities. Extensive experiments demonstrate that our CFSDCN significantly outperforms previous state-of-theart (SOTA) methods on both simulated and real HSI datasets.

关键词： Compressive sensing coded aperture snapshot spectral imaging (CASSI) hyperspectral image reconstruction deformable convolution spectral similarities

来源：评论

学校读者我要写书评

暂无评论

Essential Depth Map processing Algorithms for real-time Applications: An Overview 26

Essential Depth Map Processing Algorithms for Real-time Appl...

引用

26th Irish Machine Vision and image processing conference, IMVIP 2024

作者： Budak, Ugurcan Ilola, Lauri Kondrad, Lukasz Alface, Patrice Rondao Fasogbon, Peter Schwarz, Sebastian Nokia Technologies Finland

ISBN: (纸本)9781837242672

RGB-D cameras provide both depth (D) and colour (RGB) data as the output simultaneously in real-time. The depth data provided by the camera typically contains imperfections, such as holes and noise. Improving the quality of depth data is a widely researched topic of practical importance for multimedia, computer vision, and robotics. Typically, RGB-D cameras provide color data with higher resolution and quality compared to depth data. In this paper, we propose to enhance the depth map, which can be a pre-processing step of real-time volumetric streaming. First, we survey and categorize the depth improvement methods into two, and then test them to improve the quality of the depth data in real-time. We present the empirical results, which are informative for selecting a suitable depth map refinement method. Our experiments show that there is a trade-off between improvement level and real-time capability of the methods. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Pothole Detection and Road Damage Assessment System Utilizing image processing Techniques 2

Pothole Detection and Road Damage Assessment System Utilizin...

引用

2nd International conference on Inventive Computing and Informatics (ICICI)

作者： Swathika, R. Radha, N. Parthiban, D. Sriram, J. Sri Sivasubramaniya Nadar Coll Engn IT Dept Chennai Tamil Nadu India

ISBN: (纸本)9798350373301;9798350373295

Road infrastructure degradation remains a significant challenge, prompting the utilization of cutting-edge image processing techniques to enhance infrastructure management and road safety. While traditional pothole patching methods are time-consuming, this research study focuses on three key aspects of road maintenance: assessing the prevalence of potholes, evaluating their impact on road conditions, and alerting drivers to nearby potholes to mitigate risks. To differentiate from approaches that merely detect and count potholes, the proposed methodology incorporates segmentation techniques to precisely quantify areas impacted by potholes. This involves utilizing the capabilities of a YOLOv8 model trained on custom real-time image datasets. The YOLOv8 model stands out for its user-friendly interface, simplicity, and effectiveness, as highlighted in this research. Moreover, this study introduces a novel route selection method based on the severity of road damage and pothole presence. The main aim of this study is to substantially enhance road safety, refine maintenance practices, and reinforce the resilience of urban environments through these innovative solutions.

关键词： Pothole detection image processing Instance Segmentation damage assessment Distance Estimation

来源：评论

学校读者我要写书评

暂无评论

real-time motion classification with efficient event stream data processing

Real-time motion classification with efficient event stream ...

引用

2023 IEEE International conference on Consumer Electronics-Asia, ICCE-Asia 2023

作者： Jeon, Seokhun Park, Sihyeong Kim, Kyungmo Kim, Byung-Soo Jang, Youngjong Korea Electronics Technology Institute SoC Platform Center Korea Republic of

ISBN: (纸本)9798350344318

In this paper, we introduce an effective technique for real-time motion classification using event cameras to process input data streams. Our method allows for real-time operation. To enhance memory efficiency, our approach reduces buffers in the event-to-frame conversion process, while simultaneously distributing frame conversion tasks to reduce processing time bottlenecks. © 2023 IEEE.

关键词： real time systems

来源：评论

学校读者我要写书评

暂无评论

Quality Improvement of image Datasets using Hashing Techniques

Quality Improvement of Image Datasets using Hashing Techniqu...

引用

2023 IEEE International conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Joshi, Aditi Shet, Aman V Thambi, Adarsh S Sunitha, R. BNM Institute of Technology Department of AI & ML Bangalore India

ISBN: (纸本)9781665462631

image processing has become extremely important, with the consequences of real-time image processing failures being severe;thus, research and study in real-time image processing methods are extremely important. Some images contain incorrect information, requiring the use of techniques to improve the image and make it more understandable. Others require some pre-processing for the machine to understand and make important decisions about the image on its own, without any manual intervention. Part of pre-processing includes doing a clean-up of the dataset by removal of the bias that could appear. This paper presents the framework for detecting duplicates and near duplicates aiming towards making the dataset more efficient. This will in turn help in training the ML model to be better. This is achieved by implementing the Difference Hash (dHash), Average Hash (aHash), and Perceptual Hash (pHash). Hash functions are ideal to detect (near-)identical photos because of the robustness against minor changes, while also minimizing the number of false positive collisions. The proposed model is well-suited for various real-time image processing applications. © 2023 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

SignTrack: Advancements in real-time Sign Language processing for Inclusive Computing with optimized AI 13

SignTrack: Advancements in Real-Time Sign Language Processin...

引用

13th International conference on Modern Circuits and Systems Technologies (MOCAST)

作者： Piperakis, Stavros Papatsimouli, Maria Argyriou, Vasilis Sarigiannidis, Panagiotis Fragulis, George F. Univ Western Macedonia Dept Elect & Comp Engn ZEP Campus Kozani 50100 Greece Kingston Univ Dept Networks & Digital Media Kingston England

ISBN: (纸本)9798350385434;9798350385427

Visual-based translator systems, which utilize image and video data for real-time translation, represent a captivating research area. While previous research has explored text-based translation, limitations exist in capturing the nuances of human communication. Visual-based approaches address this gap by leveraging deep learning and image processing to extract information like objects, faces, and environmental context. This research project investigates the application of deep learning in sign language translation using Automated AI. By analyzing visual data, the system recognizes signs and translates them into spoken languages or generates text descriptions. This technology holds significant promise for various fields - education, entertainment, tourism, and healthcare - and can contribute to the advancement of information technology and artificial intelligence systems.

关键词： Automated AI IoT Sign Language Sign language transcription

来源：评论

学校读者我要写书评

暂无评论

TransCGAN-based Parameter Extraction Framework for SAR image Simulation 2

TransCGAN-based Parameter Extraction Framework for SAR Image...

引用

2nd IEEE International conference on Signal, Information and Data processing, ICSIDP 2024

作者： Deng, Sidan He, Jingfei Mao, Yongfei Zhao, Liangbo Chen, Liang Shi, Hao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Chongqing Innovation Center Chongqing China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Chongqing Innovation Center Beijing China

ISBN: (纸本)9798331515669

Synthetic Aperture Radar (SAR) images have a wide range of applications due to their all-weather and all-day working conditions. However, SAR images with different scenarios and imaging conditions are insufficient or even rare, which is required in specific SAR image tasks. Fortunately, SAR image simulation technology can provide ample simulated images under these conditions at a low cost, addressing the scarcity of specific real SAR data. Accurate parameters are crucial for obtaining high-quality simulated images. However, it is time-consuming and labour-intensive to adjust parameters manually, and it often fails to achieve accurate simulation parameters. To tackle this problem, this paper proposes a TransCGAN-based SAR image simulation method that combines deep learning with traditional methods. By training TransCGAN, a conditional generative adversarial network (CGAN) integrated with Transformer architecture, a mapping between SAR images and simulation parameters is established. This enables the extraction of simulation parameters directly from the real SAR image, guided by the corresponding real SAR image. Ultimately, the parameters are subsequently converted into simulated SAR images via simulation software. Experimental results demonstrate that our TransCGAN-based method can effectively extract accurate simulation parameters from real SAR images, resulting in simulated images holding high similarity to real images. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Smart Monitoring and Guidance System for Parking Spaces 5

Smart Monitoring and Guidance System for Parking Spaces

引用

5th IEEE International conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Manvanth, G.S. Pavan Kumar, A. Priyanka, Valipe Devi Goduguluri, Varshitha Ravish, Roopa Pes University Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350383522

A parking system refers to the infrastructure and technology used to manage and facilitate the parking of vehicles in a specific area. These systems are designed to streamline the process of finding parking spaces, enhance efficiency, and improve overall traffic management. The proposed system is designed to address the challenges faced by open space parking spaces in major metropolitan cities. The prevailing issue of locating parking spaces in busy urban settings is tackled using Machine Learning (ML) model. Smart Monitoring and Guidance system is a ML based technology which allows the users to find vacant parking slots in a given area. The system uses ML model over Internet of Things (IoT) based solutions as scaling and maintenance is easier using ML models. The system provides real time information to the users about the total number of parking slots available at a parking space using image processing. The users can select a parking space of their choice. Upon selecting a suitable parking space, users are provided with real-time navigation assistance to the parking space of their choice. ML model improves the overall efficiency, reliability, and robustness of the system. The system obtains parking information of multiple parking spaces by processing their video footages concurrently. The system provides users with real-time navigation to the parking space thus providing the users and hassle free experience. © 2024 IEEE.

关键词： Directions assistance image processing Machine Learning Parking issues Parking Monitoring Parking slot availability real-time navigation real-time processing Smart city solutions Support Vector Classifier time-saving Traffic reduction

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：