检索结果-内蒙古大学图书馆

26th International Conference on Technologies and applications of artificial Intelligence, TAAI 2021

作者： Chang, Chih-Lung Tseng, Hsin-Ming Chu, Hsueh-Ting Asia University Department of Computer Science and Information Engineering Taichung Taiwan Asia University Ph.D. Program in Artificial Intelligence Taichung Taiwan

ISBN: (纸本)9781665408257

Before the advent of deep learning, traditional image recognition used algorithms to find features and then classify images using classical machine learning algorithms. But it is difficult to define features for variable types of images. Instead, Representation learning is a way to allow a system to discover the representations of feature for image processing. Deep-learning algorithms attempt to learn multiple levels of representation and play the key role of modern Representation learning. When deep learning neural networks recognize images, the shallow layers usually extract lower-level features, then start with intermediate-level features, and finally the full images. This study uses CNN (Convolutional neural Network) to classify fireworks images, and the trained modules are used to evaluate the accuracy and suitability. © 2021 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

SpikingVPR: Spiking neural Network-Based Feature Aggregation for Visual Place Recognition

SpikingVPR: Spiking Neural Network-Based Feature Aggregation...

引用

Sensing, Measurement & Data Analytics in the era of artificial Intelligence (ICSMD), International Conference on

作者： Gulin Wang Ziliang Ren Qieshi Zhang Jun Cheng CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Computer Science and Technology Dongguan University of Technology Dongguan China

ISBN: (数字)9798331529192

ISBN: (纸本)9798331529208

Visual Place Recognition (VPR) is a crucial task in robotics and autonomous driving, where it identifies the geographic location of a query image by matching it with a reference database. VPR faces significant challenges, including appearance variations due to lighting, occlusion, weather, and seasonal changes, alongside the need for real-time processing under low computational cost and latency. To address these challenges, we introduce Spiking neural networks (SNN) into the VPR task, specifically focusing on the feature aggregation component. SNN, with their event-driven nature, offer advantages in computational efficiency and energy consumption, making them well-suited for energy-constrained environments such as drones. Our approach transforms the feature aggregation stage of VPR into a spiking, event-driven mechanism, which maintains high recall performance while integrating seamlessly with traditional ANN-based methods. Experimental results demonstrate that our SNN-based method effectively maintains high recall performance, validating its potential in autonomous driving and other related applications.

关键词： Energy consumption Spiking neural networks Transforms Real-time systems Computational efficiency Visual databases Autonomous vehicles Robots Visual place recognition Meteorology

来源：评论

学校读者我要写书评

暂无评论

Large-scale road extraction from high-resolution remote sensing images based on a weakly-supervised structural and orientational consistency constraint network

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2022年 193卷 234-251页

作者： Zhou, Mingting Sui, Haigang Chen, Shanxiong Liu, Junyi Shi, Weiyue Chen, Xu Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430079 Peoples R China Hong Kong Polytech Univ Dept Land Surveying & Geoinformat Hong Kong Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan 430079 Peoples R China

Fully supervised road segmentation neural networks from remote sensing images rely on a large number of densely labeled road samples, limiting their potential in large-scale applications. In this paper, a weakly -supervised road segmentation network based on structural and orientational consistency (SOC-RoadNet) is proposed to learn road surface from open-source road maps, thus supporting high-quality large-scale road extraction. The open-source road maps can be made with scribble-labels to train the weakly-supervised SOC-RoadNet. However, these scribble-labels that represent the approximate location of road centerlines with only one-pixel width cannot provide supervision for road boundaries, leading to low road surface segmentation ac-curacy using scribble-supervised methods. Existing weakly-supervised road extraction networks deploy complex scribble-label propagation procedures to generate pseudo labels to train models and exploit image edge maps to refine road boundaries. Nevertheless, road edges in images are blurry due to occlusions and spectral-confusing backgrounds, limiting reliability when processing complex scenes. The proposed SOC-RoadNet is designed as a one-stage end-to-end architecture that directly learns road surface features from scribble-labels without extra label propagation procedures. Instead of using unreliable edge maps to regularize road boundaries, a structural consistency loss function is introduced to evaluate the structural similarity between road surface segmentation results and the input images for improved road boundary accuracy. Considering that roads are elongated targets with local directional consistency, orientation learning is integrated to SOC-RoadNet to improve road integrity. A road refining module was designed to aggregate the road surface features and road orientation features to further refine the road extraction results. The reference road orientation maps are generated from the scribble labels;thus, the results of orienta

关键词： Large-scale road extraction Weakly supervised learning Scribble supervision Structural consistency learning Orientation learning Feature aggregation

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 18th International Conference on Soft Computing Models in Industrial and Environmental applications, SOCO 2023

Proceedings of the 18th International Conference on Soft Com...

引用

18th International Conference on Soft Computing Models in Industrial and Environmental applications, SOCO 2023

ISBN: (纸本)9783031425288

The proceedings contain 61 papers. The special focus in this conference is on Soft Computing Models in Industrial and Environmental applications. The topics include: Missing Values Imputation for Visualizing the Air Quality Evolution During the COVID-19 Pandemic in Madrid;Comparative Study of Wastewater Treatment Plant Feature Selection for COD Prediction;effectiveness of Quantum Computing in image processing for Burr Detection;hyperspectral Technology for Oil Spills Detection by Using artificial neural Network Classifier;Model-Based Design of the IMO-NMPC Strategy: Real-Time Implementation;first Approach of an Intelligent Automatic System for Aircraft Flap/Slat Positioning;multi-scale neural Model for Tool-Narayanaswamy-Moynihan Model Parameter Extraction;comparative Study of Open Source Database Management Systems to Enable Predictive Maintenance of Autonomous Guided Vehicles;deep Learning and Metaheuristic for Multivariate Time-Series Forecasting;forecasting Greenhouse Temperature Using Machine Learning Models: Optimizing Crop Production in Andalucia;extended Rank-Based Ant Colony Optimization Algorithm for Traveling Salesman Problem;Managing Pandemics Through Agent-Based Simulation: A Case Study Based on COVID-19;leveraging Smart Meter Data for Adaptive Consumer Profiling;Categorization of CoAP DoS Attack Based on One-Class Boundary Methods;text Classification for Automatic Distribution of Review Notes in Movie Production;fault Detection in Biological Methanation Process Using Machine Learning: A Comparative Study of Different Algorithms;machine Learning Approaches for Predicting Tree Growth Trends Based on Basal Area Increment;integrated Forecast and Optimization for Retailer Allocation in a Two-Echelon Inventory System;application of Fuzzy Logic to the Risk Assessment of Production Machines Failures;Neuron Characterization in Complex Cultures Using a Combined YOLO and U-Net Segmentation Approach;neuroevolutionary Transfer Learning for Time Series Forecasting;f

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mathematics-Inspired Learning: A Green Learning Model with Interpretable Properties *

Mathematics-Inspired Learning: A Green Learning Model with I...

引用

IEEE Conference on Multimedia Information processing and Retrieval (MIPR)

作者： Ling Guan Lei Gao Kai Liu Zheng Guo Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto Canada

ISBN: (数字)9798350351422

ISBN: (纸本)9798350351439

The advances of machine learning (ML), and artificial intelligence (AI) in general, have attracted unprecedented attention in different applications (such as image classification, video computing, natural language processing, etc.). Nevertheless, due to the black-box nature and concern for sustainability of ML models, especially deep neural networks (DNNs), green and interpretable learning have been extensively studied in recent years, despite suspicions on effectiveness, subjectivity of interpretability and complexity. To address some of the concerns, this paper first explores a mathematics-inspired (M-I) learning model, which is green in nature with numerous interpretable properties. It will then present several application examples in object recognition and action recognition to demonstrate that the M-I methodology promises a plausible and sustainable path for natural evolution of machine learning.

关键词： Computational modeling Closed box Machine learning Information processing Mathematical models Natural language processing Complexity theory Object recognition Sustainable development image classification

来源：评论

学校读者我要写书评

暂无评论

28th International Conference on image processing, Computer Vision, and Pattern Recognition, IPCV 2024, and 23rd International Conference on Information and Knowledge Engineering, IKE 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024

28th International Conference on Image Processing, Computer ...

引用

28th International Conference on image processing, Computer Vision, and Pattern Recognition, IPCV 2024, and 23rd International Conference on Information and Knowledge Engineering, IKE 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024

ISBN: (纸本)9783031859328

The proceedings contain 28 papers. The special focus in this conference is on image processing, Computer Vision, and Pattern Recognition. The topics include: image-Based Seal Recognition: Approaches and Challenges in Current Automated Systems;Deep Learning Techniques for Lunar Impact Crater Identification Based on CCD and DEM Data;silicon Wafer Map Defect Classification Using artificial Intelligence Models;low Light image Enhancement Using Autoencoder-Based Deep neural networks;towards Elephants Intelligent Monitoring in Zakouma National Park, Chad;a Review of Multi-modal and Multi-view applications in Hand-Drawn Sketch images;residential Real Estate image Classification for Property Valuation;Novel Method to Investigate Decay in Rotting Bananas Using RGB Color images;lalitha: A Hand Gesture-Based Computer Control System;dishari: A Novel Gesture-Based Educational Application for Specially Challenged People;mobility Anomaly Detection with Intelligent Video Surveillance;Weakly-Supervised Video Anomaly Detection Using Modified Anomaly Score Module and Modified BERT;Contour Detection of Seeds Based on Traditional and Convolutional neural Network (CNN) Based Algorithms;Early Detection of Lameness in Dairy Cattle Using Activity Data, image Analysis, AI and ML - An Approach for Improved Animal Welfare and Economic Impact;implications for Designing Hawks Detection with Data Augmentation and Network Optimizations;a Review of Detecting and Quantification of Cracks Using Convolutional neural networks and image processing Techniques;using Linkage Context for Automated Correction in Unsupervised Entity Resolution;the Rising Threat Against Modern Technology in Cybersecurity;an Online Bookstore Design and Implementation;cybersecurity: Sight and Foresight;the Application of Blockchain Technology in the Transmission of Semiconductor Process Recipes;the Use of Social Media and the Internet for the Facilitation of Human Trafficking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Satellite Crop Zone Canvas Analysis

Deep Learning Based Satellite Crop Zone Canvas Analysis

引用

International Conference on Power, Energy, Control and Transmission Systems (ICPECTS)

作者： S. Jeyanthi R. Kavya T. Saravanan S. Subburam M. Balamurugan S. Ananthi Department of Computer Applications New Prince Shri Bhavani College of Engineering and Technology Chennai India Department of ECE New Prince Shri Bhavani College of Engineering and Technology Chennai India Department of IT New Prince Shri Bhavani College of Engineering and Technology Chennai India Master of Computer Applications New Prince Shri Bhavani College of Engineering and Technology Chennai India Department of EEE New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508852

Satellite Crop Zone Canvas Analysis refers to the utilization of deep learning techniques, a subset of artificial intelligence, for analyzing satellite imagery to study crop zones or agricultural regions. Satellite Crop Zone Canvas Analysis is method to classify the satellite images. Domain knowledge has been required for feature extraction and various sets of parameters has been obtained from satellites images for pre-processing. image processing techniques like histogram equalization and Median Filter used for enhance the image contrast. In Convolutional neural Network (CNN), most famous network ResNet50 help for train the model and also helpful for predict the images. CZCA method helps to analysing satellite imaginary. CZCA applications like yield prediction, land use mapping, and crop health monitoring rely on accurate delineation of agricultural zones.

关键词： Deep learning Training Histograms Satellites Accuracy Crops Satellite images Convolutional neural networks Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Asset Detection in Railroad Environments using Deep Learning-based Scanline Analysis 16

Asset Detection in Railroad Environments using Deep Learning...

引用

16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and applications (VISIGRAPP) / 16th International Conference on Computer Vision Theory and applications (VISAPP)

作者： Wolf, Johannes Richter, Rico Doellner, Juergen Univ Potsdam Fac Digital Engn Hasso Plattner Inst Potsdam Germany

ISBN: (纸本)9789897584886

This work presents an approach for the automated detection of railroad assets in 3D point clouds from mobile mapping LiDAR scans using established convolutional neural networks for image analysis. It describes how images of individual scan lines can be generated from 3D point clouds. In these scan lines, objects such as tracks, signal posts, and axle counters can be detected using artificial neural networks for image analysis, previously trained on ground-truth data. The recognition results can then be transferred back to the 3D point cloud as a semantic classification result, or they are used to generate geometry or map data for further processing in GIS applications. Using this approach, trained objects can be found with high automation. Challenges such as varying point density, different data characteristics of scanning devices, and the massive amount of data can be overcome with this approach.

关键词： LiDAR 3D Point Clouds Digital image Analysis Semantic Classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Industrial Automation Flexibility Through neural Network-Empowered Machine Vision applications 1

引用

1st International Conference on artificial Intelligence and its applications, ICAIA 2023

作者： George, Navin M. Rosero, Evelyn Mayakannan, S. Shameem, A. Divya, S. Arul, N. Electronics and Communication Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore641114 India Riobamba060155 Ecuador Department of Mechanical Engineering Vidya Vikas College of Engineering and Technology Namakkal Tamilnadu Tiruchengode India AMET Business School AMET University Tamilnadu Chennai India Erode Tamil Nadu Perundurai638057 India Department of Mechatronics Engineering Sona College of Technology Tamilnadu Salem India

ISBN: (数字)9783031843976

ISBN: (纸本)9783031843969

Vision-based systems provide non-contact sensory input for processing and feedback, expanding the capabilities of industrial automation applications. Prediction using ANNs aids such conformities in navigating nonlinear computational landscapes. They map the plethora of potential outcomes or zones of uncertainty introduced by the system’s constituents onto a set of feasible options for action. A measure of intelligence is transferred to robotic systems through the use of trained networks. Two uses of machine vision are presented here. The 3 DOF robotic assembly enables precision cutting of fragile materials with the help of visual guiding and pixel elimination. The 6-degrees-of-freedom robot uses a combination of visual feedback from an onboard camera and supervision from an external camera to achieve its goals. Pick-and-place operations are executed with a switching control method. Both systems improved in terms of computing time and convergence once ANN was used to make the strategies intelligent. The retrieved scene image features are put to use by the networks in a variety of ways. The simulation and experimental results that back up the suggested approaches demonstrates the value of artificial neural network in machine vision applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study between artificial neural networks and Optical neural networks

A Comparative Study between Artificial Neural Networks and O...

引用

Current Research in Engineering and Science applications (ICCRESA), International Conference on

作者： Zainab Faris Ibrahim A. Murdas Department of Electrical Engineering University of Babylon Babel Iraq

artificial intelligence has gained widespread interest from people from all walks of life since the big data era arrived, so artificial neural networks (ANNs) are one of the most important areas of artificial intelligence that have a close relationship and an effective role in diverse artificial intelligence applications, data is loaded between memory and processor during the calculation, which reduces the calculation rate and increases the power consumption. Training artificial neural network parameters take a long time and consume a lot of energy. Therefore, it is necessary to use new neural networks that differ from artificial neural networks, called optical neural networks. Optical neural networks can overcome the above shortcomings. Compared with artificial neural networks, they have obvious advantages such as high speed, high bandwidth, high balanced processing, low latency, and low power consumption. The optical neural network can significantly improve the performance of required tasks by taking advantage of the high-speed characteristics. The study compares artificial neural networks and optical neural networks to train networks by nonlinear activation functions to perform image classification tasks. The neural networks are trained and tested with the help of the KMNIST dataset. The backward propagation occurs using the backpropagation algorithm.

关键词：

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：