检索结果-内蒙古大学图书馆

International Conference on image processing and Vision Engineering (IMPROVE)

作者： Hassan, Syed Ibrahim O'Sullivan, Dympna Mckeever, Susan Technol Univ Dublin Dept Comp Sci Dublin Ireland

ISBN: (纸本)9789897585111

One of the most important tasks in road maintenance is the detection of potholes. This process is usually done through manual visual inspection, where certified engineers assess recorded images of pavements acquired using cameras or professional road assessment vehicles. Machine learning techniques are now being applied to this problem, with models trained to automatically identify road conditions. However, approaching this real-world problem with machine learning techniques presents the classic problem of how to produce generalisable models. images and videos may be captured in different illumination conditions, with different camera types, camera angles and resolutions. In this paper we present our approach to building a generalized learning model for pothole detection. We apply four datasets that contain a range of image and environment conditions. Using the Faster RCNN object detection model, we demonstrate the extent to which pothole detection models can generalise across various conditions. Our work is a contribution to bringing automated road maintenance techniques from the research lab into the real-world.

关键词： Object Detection Pavement Inspection deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Addressing challenges in industrial pick and place: A deep learning-based 6 Degrees-of-Freedom pose estimation solution

引用

COMPUTERS IN INDUSTRY 2024年 161卷

作者： Govi, Elena Sapienza, Davide Toscani, Samuele Cotti, Ivan Franchini, Giorgia Bertogna, Marko Univ Modena & Reggio Emilia Dept Phys Math & Comp Sci I-41125 Modena Italy Univ Parma Dept Math Phys & Comp Sci I-43124 Parma Italy Hipert srl I-41122 Modena Italy

Object picking is a fundamental, long-lasting, and yet unsolved problem in industrial applications. To complete it, 6 Degrees-of-Freedom pose estimation can be crucial. This task, easy for humans, is a challenge for machines as it involves multiple intelligent processes (for example object detection, recognition, pose prediction). Pose estimation has recently made huge steps forward, due to the advent of deep learning. However, in real-world applications it is not trivial to compute it: each use-case needs an annotated dataset and a model robust enough to face its specific challenges. In this paper, we present a comprehensive investigation focused on a specific use-case: the picking of four industrial objects by a collaborative robot's arm, addressing challenges related to reflective textures and pose ambiguities of heterogeneous shapes. Thus, Artificial Intelligence is crucial in this process, utilizing Convolutional Neural Networks to discern an object's pose by extracting hierarchical features from a single image. In detail, we propose a new synthetic dataset of industrial objects and a fine-tuning method to close the sim-to-real domain gap. In addition, we improved an existing pipeline for pose estimation and introduced a new version of an existing method, based on Convolutional Neural Networks. Finally, extensive experiments were conducted with a Universal Robot UR5e. Results show our strategy achieves good performances with an average successful picking rate of 75% on these new objects. Considering the lack of available datasets for pose estimation, coupled with the significant time and labor required for annotating new images, we contribute to the scientific community by providing a comprehensive dataset, and the associated generation and estimation pipelines.1 1

关键词： Artificial intelligence in industrial automation learning from synthetic data Computer vision for pose estimation Convolutional Neural Network Machine learning in real-world applications Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Denoising of magnetotelluric data using K-SVD dictionary training

引用

GEOPHYSICAL PROSPECTING 2021年第2期69卷 448-473页

作者： Li, Jin Peng, Yiqun Tang, Jingtian Li, Yong Hunan Normal Univ Coll Informat Sci & Engn Hunan Prov Key Lab Intelligent Comp & Language In Changsha 410081 Peoples R China Cent South Univ Minist Educ Key Lab Metallogen Predict Nonferrous Met & Geol Changsha 410083 Peoples R China Chinese Acad Geol Sci Inst Geophys & Geochem Explorat Key Lab Geophys Electromagnet Probing Technol Minist Nat Resources Langfang 065000 Peoples R China Minist Nat Resources Tech Innovat Ctr Coverage Area Deep Resources Exp Hefei 230001 Peoples R China

Magnetotelluric is one of the mainstream exploration geophysical methods, which plays a vital role in studying deep geological structures and finding deep hidden blind ore bodies. The seriousness of human electromagnetic noise causes a large number of abnormal waveforms in the time series of measured magnetotelluric data, and the data can no longer objectively reflect the underground electrical distribution. In this work, we propose a magnetotelluric time series data processing method based on K singular value decomposition dictionary training. First, a training matrix and a to-be-processed matrix are built with the pending magnetotelluric signals. Then, let the K singular value decomposition dictionary training process the training matrix to obtain an over-complete dictionary reflecting the characteristics of the pending signal. Lastly, orthogonal matching pursuit is combined with an over-complete dictionary updated in real time to sparsely represent the to-be-processed matrix and remove human electromagnetic interference in the signal. Experimental results show that the method can update the over-complete dictionary in real-time according to the pending magnetotelluric signals, realize the self-learning signal-noise separation of magnetotelluric signals, and effectively retain low-frequency information. Compared with method of directions dictionary learning, remote reference method, and orthogonal matching pursuit method, the reconstructed data of the proposed method can more accurately reflect the underground electrical structure information.

关键词： Data processing Filtering Magnetotelluric

来源：评论

学校读者我要写书评

暂无评论

A Review on Machine learning Algorithms for real-time Traffic Management 3rd

A Review on Machine Learning Algorithms for Real-Time Traffi...

引用

3rd International Conference on Advancements in Smart Computing and Information Security, ASCIS 2024

作者： Cholera, Bhavesh Jayantilal Bajeja, Sunil Lalchand Faculty of Computer Application Marwadi University Gujarat Rajkot India

ISBN: (纸本)9783031862984

The use of machine learning algorithms in traffic control has garnered a lot of interest recently. In order to better understand the design and development of prediction algorithms for machine learning-based real-time traffic management, In this paper, we summarize the deep learning and machine learning methods for data processing, like image processing, SVM, KNN, CNN, HOG, big data, ANN, regression, Yolov3 algorithms, LSTM, GRU, etc. We are attempting to identify these methods’ limitations and potential future applications. This study helps to choose the best prediction algorithms. Here, we tried to use congestion theory in a real-time traffic application. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

UCloudNet: A Residual U-Net with deep Supervision for Cloud image Segmentation

UCloudNet: A Residual U-Net with Deep Supervision for Cloud ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Yijie Li Hewei Wang Shaofan Wang Yee Hui Lee Muhammad Salman Pathan Soumyabrata Dev School of Computer Science University College Dublin Dublin Ireland Faculty of Information Technology Beijing University of Technology Beijing China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Innovation Value Institute Maynooth University Ireland The ADAPT SFI Research Centre Dublin Ireland

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Recent advancements in meteorology involve the use of ground-based sky cameras for cloud observation. Analyzing images from these cameras helps in calculating cloud coverage and understanding atmospheric phenomena. Traditionally, cloud image segmentation relied on conventional computer vision techniques. However, with the advent of deep learning, convolutional neural networks (CNNs) are increasingly applied for this purpose. Despite their effectiveness, CNNs often require many epochs to converge, posing challenges for real-time processing in sky camera systems. In this paper, we introduce a residual U-Net with deep supervision for cloud segmentation which provides better accuracy than previous approaches, and with less training consumption. By utilizing residual connection in encoders of UCloudNet, the feature extraction ability is further improved. In the spirit of reproducible research, the model code, dataset, and results of the experiments in this paper are available at: https://***/Att100/UCloudNet.

关键词： Training deep learning image segmentation Clouds Geoscience and remote sensing Cameras Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Application of Particle image Velocimetry Method Based on Full Convolution Neural Network in Turbulence Field

Application of Particle Image Velocimetry Method Based on Fu...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Zhicheng Xie Shuqiang Guo School of Computing Northeast Electric Power University Jilin China

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

Exploring fluid flow phenomena has always been a hot topic in fluid mechanics research. Particle image Velocimetry (PIV) is a non-contact technique applied in fluid mechanics laboratories for measuring the velocity field of fluids. The core of PIV lies in extracting displacement vector information from particle image pairs to ultimately generate a two-dimensional velocity field. Traditional methods typically estimate the two-dimensional velocity field using cross-correlation algorithms and optical flow techniques. In recent years, with the rapid development of artificial intelligence technologies and their high compatibility with PIV in image processing, there is significant potential and research value in designing deep learning techniques for accurately estimating fluid velocity vector fields in particle image velocimetry. Compared to traditional methods, the PIV technique proposed in this paper, based on fully convolutional neural networks, not only maintains the accuracy of velocity field estimation but also significantly enhances resolution and computational efficiency. Experiments demonstrate that the proposed method exhibits higher accuracy and stronger generalization capabilities.

关键词： deep learning Visualization Accuracy Sea measurements Vectors real-time systems Computational efficiency Convolutional neural networks Velocity measurement Meteorology

来源：评论

学校读者我要写书评

暂无评论

License Plate Detection and Recognition System for All Types of Bangladeshi Vehicles Using Multi-step deep learning Model

License Plate Detection and Recognition System for All Types...

引用

International Conference on Digital image Computing - Techniques and Applications (DICTA)

作者： Shomee, Homaira Huda Sams, Ataher Brac Univ Dept Comp Sci & Engn Dhaka Bangladesh Bangladesh Univ Engn & Technol Dept Elect & Elect Engn Dhaka Bangladesh

ISBN: (纸本)9781665417099

A robust license plate (LP) detection and recognition system can extract the license plate information from a still image or video of a moving or stationary vehicle. Bangla license plate recognition is a complicated subject of study due to no publicly available dataset and its specific characteristics with over 100 unique classes, including words, letters, and digits. This paper proposes a robust multi-step deep learning system based on You Only Look Once (YOLO) architecture that can extract license plate information from a real-world image. The resulting system localizes license plates using YOLOv4 object detector model, automatically crops the license plates using bounding box coordinates, enhances the extracted license plate image quality using Enhanced Super Resolution Generative Adversarial Networks (ESRGAN), and then recognizes the classes using YOLOv4 without segmenting the characters. Synthetic images have been used to make proposed method capable of recognizing the classes in unfavorable and complicated conditions. A complete two-part dataset named 'Bangla LPDB-A' is created in this study. This dataset includes Bangladeshi vehicle images with manually annotated license plates and cropped license plates with manually annotated words, letters, and digits. The proposed system is tested on this dataset that has achieved mean average precision (mAP) of 98.35% and 98.09% for final detection and recognition model, which has an average prediction time of 23 ms and 35 ms.

关键词： Bangla license plate deep learning Generative adversarial networks image processing Object detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction of Underwater Acoustic Signal Target Using Machine learning Technique

引用

TRAITEMENT DU SIGNAL 2024年第3期41卷 1303-1314页

作者： Ashok, P. Latha, B. Anna Univ Sri Sai Ram Inst Technol Dept Comp Sci & Engn Chennai 600044 India Sri Sairam Engn Coll Dept Comp Sci & Engn Chennai 600044 India

Finding underwater sound sources is quite difficult because of how complex and interconnected the undersea world is. When trying to use ship-radiated noise for Underwater Acoustic Target Recognition (UATR), the complicated presence of aquatic creatures makes the process even more tough. An innovative DNN called the Audio Perspective Regionbased Convolutional Neural Network (APRCNN) is presented in this study. In order to train APRCNN, we used Depth Wise Separable (DWS) Convolutional deep Neural Network architecture using initial underwater acoustic wave data. After that, APRCNN is used to categories and forecast underwater sound waves. Novel aspects of the suggested APRCNN model include optimization, adaptive learning, processing in parallel with residual connections, and underwater environment adaptation. With the help of integration layers that were influenced by the perceptual processing of the SPDNN system. Machine translation approaches also improve the model's performance through the use of time-dilated convolution. In this research, we offer a technique for underwater target detection with a full-featured DNN architecture. To achieve optimal classification accuracy with minimal compute load in different underwater degradation conditions, the suggested architecture maximizes the reallocation of prior feature maps. In addition, the suggested method eliminates the requirement for time-frequency spectrum analyzer pictures by allowing the network to be fed real data from audio signals instead. With a remarkable 98.4 percent accuracy level at 0 -dB Signal to Noise Ratio (SNR), our classification methodology outperforms both state -of -the -art DNN systems and classic ML approaches, as demonstrated by thorough examination of a real -world dataset of passive sonar waves. When compared to other DNN systems for processing underwater acoustic signals, PRCNN stands out due to its adaptive learning mechanisms, focus on perspective regions, integration of domain knowledge,

关键词： features extractor underwater acoustic Region-based Convolutional Neural Network image processing ship-radiated noise target recognition

来源：评论

学校读者我要写书评

暂无评论

Rendering the image of glare effect based on paired and unpaired dual generative adversarial network

引用

DISPLAYS 2023年 76卷

作者： Ao, Jinlong Zhang, Xiaoteng Lin, Yandan Fudan Univ Inst Elect Light Sources Sch Informat Sci & Technol Shanghai 200438 Peoples R China Hasco Vis Technol Shanghai Co 767 Yecheng Rd Shanghai 201821 Peoples R China

It is a great challenge to rendering glare on image as the current rendering algorithms did not consider well the refraction of human eyes, thus the effect of rendering, in some critical application such as vehicle headlamps, is not real and may affect the safety evaluation. The traditional glare rendering algorithm relies on a large number of hand-designed wave optics processing operators, not only cannot complete the rendering work online in real time, but also cannot cope with the complex and changeable imaging conditions in reality. The mainstream generative adversarial network based algorithms in the field of image style translation are introduced to generate glare effect, which could be rendering online in a real time, however they still fail to render some effects such as detail distortion. In this work, we present a novel glare simulation generation method which is the first algorithm to apply a generative model based style transfer method to glare rendering. In a nutshell, a new method named Glare Generation Network is proposed to aggregate the benefits of content diversity and style consistency, which combines both paired and unpaired branch in a dual generative adversarial network. Our approach increase the structural similarity index measure by at least 0.039 on the custom darkroom vehicle headlamp dataset. We further show our method significantly improve the inference speed.

关键词： Glare generation Generative adversarial network deep learning

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Parallel Distributed Streaming Framework for near real-time Science Sensors and High-Resolution Medical images 21

An Intelligent Parallel Distributed Streaming Framework for ...

引用

50th International Conference on Parallel processing (ICPP)

作者： Shivadekar, Samit Mangalagiri, Jayalakshmi Phuong Nguyen Chapman, David Halem, Milton Gite, Rahul Univ Maryland Baltimore Cty Baltimore MD 21228 USA OpenKneck Inc Halethorpe MD USA

ISBN: (纸本)9781450384414

Our goals are to address challenges such as latency, scalability, throughput and heterogeneous data sources of streaming analytics and deep learning pipelines in science sensors and medical imaging applications. We present a prototype Intelligent Parallel Distributed Streaming Framework (IPDSF) that is capable of distributed streaming processing as well as performing distributed deep training in batch mode. IPDSF is designed to run streaming Artificial Intelligent (AI) analytic tasks using data parallelism including partitions of multiple streams of short time sensing data and high-resolution 3D medical images, and fine grain tasks distribution. We will show the implementation of IPDSF for two real world applications, (i) an Air Quality Index based on near real time streaming of aerosol Lidar backscatter and (ii) data generation of Covid-19 Computing Tomography (CT) scans using deep learning. We evaluate the latency, throughput, scalability, and quantitative evaluation of training and prediction compared against a baseline single instance. As the results, IPDSF scales to process thousands of streaming science sensors in parallel for Air Quality Index application. IPDSF uses novel 3D conditional Generative Adversarial Network (cGAN) training using parallel distributed Graphic processing Units (GPU) nodes to generate realistic 3D high resolution Computed Tomography scans of Covid-19 patient lungs. We will show that IPDSF can reduce cGAN training time linearly with the number of GPUs.

关键词： Distributed streaming Data Parallelism deep learning Lidar backscatter Computed Tomography cGAN

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：