检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Youai Wang Yi Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Eduction CRRC Zhuzhou Locomotive Co. Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Traditional 3D visual reconstruction technology based on feature extraction is difficult to estimate the surface depth information of a smooth object with a single texture,while the polarization 3 D reconstruction technology can recover the surface normal information from the image pixel by pixel,which has the characteristics of high precision,low texture dependence and strong material ***,the normals recovered from the polarization information have the problem of multi-value ambiguity,which needs to be corrected before the accurate normal information can be *** the same time,the image collected by the polarization camera contains a lot of noise,which will greatly affect the accuracy of reconstruction *** this paper,the characteristics of polarization information are used to denoise the polarization image,and the reference normal information is used as the prior information for correcting the polarization ***,the degree of polarization and angle of polarization are calculated based on the polarized image,then the two are fused and denoised by the Block Matching threedimensional(BM3D) method,and then the multi-valued ambiguity of polarization normal is corrected according to the reference normal ***,the corrected polarization normal is integrated to obtain a high-precision 3D shape of the object.

关键词： Polarization Denoising 3D Reconstruction Weakly Textured Objects Normal Multi-value Correction

来源：评论

学校读者我要写书评

暂无评论

GCN-Transformer Autoencoder with Knowledge Distillation for Unsupervised Video Anomaly Detection

引用

Journal of advanced Computational Intelligence and intelligent Informatics 2025年第3期29卷 659-667页

作者： Yan, Mingchao Xiong, Yonghua She, Jinhua School of Automation China University of Geosciences No.388 Lumo Road Hongshan District Hubei Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems No.388 Lumo Road Hongshan District Hubei Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education No.388 Lumo Road Hongshan District Hubei Wuhan430074 China School of Engineering Tokyo University of Technology 1404-1 Katakura Hachioji Tokyo192-0982 Japan

Video anomaly detection is crucial in intelligent surveillance, yet the scarcity and diversity of abnormal events pose significant challenges for supervised methods. This paper presents an unsupervised framework that integrates graph attention networks (GATs) and Transformer architectures, combining masked autoencoders (MAEs) with self-distillation training. GATs are utilized to model spatial and inter-frame relationships, while Transformers capture long-range temporal dependencies, overcoming the limitations of traditional MAE and self-distillation approaches. The model employs a two-stage training process: first, a lightweight MAE combined with a GAT-Transformer fusion constructs a knowledge distillation module;second, the student autoencoder is optimized by integrating a graph convolutional autoencoder and a classification head to identify synthetic anomalies. We evaluate the proposed method on three representative datasets—ShanghaiTech Campus, UBnormal, and UCSD Ped2—and achieve promising results. © Fuji technology Press Ltd.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

An Efficient Color and Geometric Feature Fusion Module for 6D Object Pose Estiamtion 12

An Efficient Color and Geometric Feature Fusion Module for 6...

引用

12th International Conference on CYBER technology in Automation, Control, and intelligent systems, CYBER 2022

作者： Li, Jiangeng Liu, Hong Huang, Gao Zuo, Guoyu Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Beijing University of Technology Beijing100124 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

6D pose estimation is widely used in robot tasks such as sorting and grasping. RGB-D-based methods have recently attained brilliant success, but they are still susceptible to heavy occlusion. Our critical insight is that color and geometry information in RGBD images are two complementary data, and the crux of the pose estimation problem under occlusion is fully leveraging them. Towards this end, we propose a new color and geometry feature fusion module that can efficiently leverage two complementary data sources from RGB-D images. Unlike prior fusion methods, we conduct a two-stage fusion strategy to do color-depth fusion and local-global fusion successively. Specifically, we fuse the color features extracted from RGB images into the point cloud in the first stage. In the second stage, we extract local and global features from the fused point cloud using an ASSANet-like network and splice them together to obtain the final fusion features. We conducted experiments on the widely used LineMod and YCB-Video datasets, which shows that our method improves the prediction accuracy while reducing the training time. © 2022 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Research on Urban Air Quality Prediction Method Based on the Fusion of Wide-area Spatiotemporal Distribution Data 26

Research on Urban Air Quality Prediction Method Based on the...

引用

26th International Conference on Industrial technology, ICIT 2025

作者： Tao, Zixing Cao, Weihua Gan, Chao Wuhan China School of Future Technology School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9798331521950

Air quality data exhibit nonlinearity, sensitivity to environmental factors, and long-term dependencies. Numerous factors influence air quality, making accurate predictions based on a single-dimensional dataset impractical. This study proposes a method for urban air quality prediction that integrates wide-area spatiotemporal data, designed to address the unique characteristics of air quality datasets. First, relevant wide-area spatiotemporal data are selected, and their correlations with air quality are systematically analyzed. Second, a Long Short-Term Memory (LSTM) network-based Transformer model is utilized to capture the long-term dependencies in the air quality sequences. Finally, the model successfully generates hourly multi-step predictions for six air pollutants. The experimental results show that the proposed method outperforms the method that relies on air quality data alone for multi-step air quality prediction. © 2025 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Adjacent and Opposite Current Injection Patterns for 3D Image Reconstruction of the Human Lung Based on a Realistic Model

Evaluation of Adjacent and Opposite Current Injection Patter...

引用

Impedance Spectroscopy (IWIS), International Workshop on

作者： Mejda Bouchhima Oumaima Bader Mariem Hafsa Salwa Sahnoun Najoua Essoukri Ben Amara Olfa Kanoun National School of Electronics and Telecommunications of Sfax University of Sfax Sfax Tunisia Professorship Measurement and Sensor Technology Chemnitz University of Technology Chemnitz Germany Université de Sousse Ecole Nationale d'Ingénieurs de Sousse LATIS - Laboratory of Advanced Technology and Intelligent Systems Sousse Tunisie Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Center of Sfax Sfax Tunisia

ISBN: (数字)9798331507626

ISBN: (纸本)9798331507633

Electrical Impedance Tomography (EIT) is a non-invasive, radiation-free imaging technique that can be used for 2D lung imaging. However, 2D EIT has a simplified geometric assumption, which neglects the 3D dynamic lung changes. This study develops a realistic 3D geometrical model including the lungs and thoracic cavity For EIT analysis. Finite Element (FE) models are generated for forward calculation and image reconstruction using an optimized Gauss-Newton (GN) algorithm. Two common current injection patterns - Adjacent and Opposite - are compared. Results show that using the lung-refined model with prior knowledge of the lungs' elements, GN converges with a Pearson correlation (r) of 0.9707 for the opposite pattern, higher than the adjacent pattern which reaches 0.9703. The second metric is the mean squared errors (MSE) between boundary voltages (BV) from reconstructed images and ground truth. It reaches $5.3965 \cdot 10^{-4},5.3963\cdot 10^{-4}$ , and $1.027{6}\cdot 10^{-12}$ for the Opposite pattern, respectively, for an empty cavity, lung-refined mesh without, and with prior knowledge of the lungs' elements. The results prove the efficiency of the Opposite injection pattern compared to the Adjacent pattern. These findings highlight the importance of injection patterns and the benefits of using a lung-refined mesh with prior knowledge of the lungs' elements for more accurate reconstructions.

关键词： Electrical impedance tomography Solid modeling Spectroscopy Three-dimensional displays Accuracy Correlation Lungs Imaging Finite element analysis Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Indoor Target Detection and Pose Estimation Based on Point Cloud 3

Indoor Target Detection and Pose Estimation Based on Point C...

引用

2021 3rd International Conference on Computer, Communications and Mechatronics Engineering, CCME 2021

作者： Zhang, Di Zhang, Weimin Li, Fangxing Guo, Ziyuan Nie, Fuyu Jin, Jiahao Wang, Yang Shi, Yongliang Huang, Qiang School of Mechatronical Engineering Beijing Institute of Technology Beijing100811 China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education China Beijing Advanced Innovation Center for Intelligent Robots and Systems China

The indoor environment faced by service robots is complex, with plenty of objects and mutual occlusion, traditional algorithms cannot detect the target and estimate its pose accurately. We propose a set of target detection and pose estimation algorithm based on point cloud templates to solve the above problems. Through the segmentation and clustering of scenes, the application of the algorithm in complex scenes is realized. Based on the key points to estimate the pose of the target, we achieve the adaptation to mutual occlusion. Besides, we propose an improved RANSAC algorithm, which maintains the accuracy of the original algorithm while greatly improving the speed. Finally, we test the algorithm through the open source model library, simulated and actual scenarios, compared with the SAC-IA algorithm, our algorithm improves the time by 89%, and in the application of complex scenes, the error of the pose estimation is at the millimeter level. © Published under licence by IOP Publishing Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Classification Based on Lightweight Network and Pruning

Remote Sensing Image Classification Based on Lightweight Net...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Wang, Zexi Xue, Wei Chen, Kehui Ma, Shaopeng School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665465335

In recent years, deep neural network has continuously improved the performance of remote sensing image classification. Though The deep neural network model is powerful, it is difficult to deploy on resource-constrained hardware platforms such as mobile terminal devices and embedded devices due to the large number of network parameters. In this paper, a novel lightweight network (LW-Net) model and a network pruning method are used for remote sensing image classification. This LW-Net model adopts a net block unit to obtain more characteristic graphs with less computational complexity. The proposed network pruning method uses the sparsity regularization on the influence factor in BN layer to automatically identified and pruned unimportant channels to make the model structure simpler. Experimental results demonstrate compared with traditional deep neural networks, the proposed model with the network pruning method can greatly reduce the computational complexity and model parameters with a little accuracy loss. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy

Efficient Hierarchical Exploration with An Active Subgoal Ge...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Xu, Xin Zuo, Guoyu Li, Jiangeng Huang, Gao The Faculty of Information Technology Beijing University of Technology Beijing100124 China The Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Beijing University of Technology Beijing100124 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (纸本)9781665481090

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach in long-horizon and complex tasks. It has been successfully used by decomposing tasks via subgoals. However, the existing goal-conditioned HRL methods often suffer from training inefficiency in the long-horizon tasks with sparse external rewards. For this problem, this paper proposes a novel framework that can train high-level policy efficiently with an effective sub goal generation method. The key component of the framework is an active subgoal generation strategy which consists of (a) an efficient high-level policy learning mechanism and (b) two measures of novelty and coverage for filtering effective subgoals. We also introduce the HER mechanism to the framework to solve the problem of sparse reward in the environment. Building upon the proposed framework, this paper develops an active hierarchical exploration strategy with an efficient subgoal generation method. We test our method on a variety of continuous control tasks. Experimental results demonstrate that the strategy outperforms the state-of-the-art HRL approaches. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of an intelligent Monitoring System for Operating States in a Coal Mine Drilling Process 41

Design of an Intelligent Monitoring System for Operating Sta...

引用

第41届中国控制会议

作者： Xiao Yang Luefeng Chen Sheng Du Chengda Lu Wangnian Li Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Xi'an Research Institute Co.Ltd. China Coal Technology and Engineering Group

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the development trend of intelligent drilling in coal mines,an intelligent monitoring system for operating states in a drilling process is developed to solve the problems of incomplete display of drilling parameters and ineffective *** system realizes the remote monitoring of drilling *** mainly adopts the Fuzzy C-Means clustering algorithm to cluster the drilling *** it combines expert empirical knowledge to classify coal seams into soft,hard and alternating soft and hard coal *** boundary values are calculated according to the boundary ***,three drilling operating states,rated,conservative and over-excited,are judged to provide guidance for the drilling process control.

关键词： Drilling process intelligent monitoring Fuzzy C-Means clustering Operating states

来源：评论

学校读者我要写书评

暂无评论

Design of An intelligent Control System for Underground Directional Drilling Trajectory in Coal Mines 41

Design of An Intelligent Control System for Underground Dire...

引用

第41届中国控制会议

作者： Wangnian Li Min Wu Ke Yao Quanxin Li Chengda Lu Sheng Du School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Xi'an Research Institute Co.Ltd. China Coal Technology and Engineering Group

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Directional drilling trajectory control technology is one of the key technologies to realize automation and intelligence of underground tunnel drilling in coal *** construction of directional drilling in underground coal mines mainly relies on manual observation of measurement-while-drilling parameters to control the drilling trajectory,which is highly dependent on manual *** paper designs an intelligent control system of underground directional drilling trajectory for coal *** the idea of hierarchical design and modular design,this system collects and displays geometric parameters,geological parameters,and engineering parameters of the directional drilling ***,an intelligent decision-making platform for directional drilling trajectory prediction and control is developed,laying a foundation for the research of directional drilling trajectory prediction and intelligent control for coal mines.

关键词： Trajectory prediction trajectory control geometric parameters geological parameters engineering parameters

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：