检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Zhang, Meng Gan, Chao Cao, Weihua School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9798350368604

Currently, the advanced geological prediction for the main tunnel from the parallel tunnel often employs parallel deduction of detection conclusions, which faces issues such as a lack of diverse geological exploration information, a lack of analysis of geological structures and poor accuracy. In this paper, an integrated prediction method for unfavorable geology in main tunnel considering the geological conditions of parallel tunnel is proposed, which consists of three stages. In the first stage, based on the forecast mileage range and tunnel excavation conditions, the process is divided into four specific cases. In the second stage, it deduces the geology of the main tunnel along the orientation of rock strata occurrence or joint to parallel tunnel and selects the results of the rock strata occurrence or joint deduction according to the distance of the deduction. In the last stage, it deduces the geological conditions of parallel tunnel face and the integration of geophysical and drilling information for predictive conclusions based on the four specific cases. The proposed method offers higher prediction accuracy for rock mass integrity and surrounding rock grades compared to parallel deduction method. © 2024 IEEE.

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Steel Strip Defect Detection Method Based on YOLO 43

A Lightweight Steel Strip Defect Detection Method Based on Y...

引用

43rd Chinese control Conference, CCC 2024

作者： Qian, Hao Xu, Chi China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

ISBN: (纸本)9789887581581

As an essential component of modern industry, steel strips play an indispensable role in various fields and serve as a crucial raw material in industrial production. However, due to various factors such as production technology, the surface of steel strips often exhibits unavoidable defects like scratches and crazings. Therefore, implementing online surface quality inspection for steel strips is one effective way to enhance product quality and production efficiency. This paper proposes a detection method for surface defects in steel strips based on YOLO. By optimizing the network structure of YOLOv5s, the performance on the NEU-DET dataset has improved by nearly 4 % compared to the original network's mAP value. Experimental results indicate that the detection performance of this method is significantly superior to the current mainstream lightweight detection networks. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Strip metal

来源：评论

学校读者我要写书评

暂无评论

3D Object Pose Estimation Based on End-to-End Differentiable Perspective Projection 43

3D Object Pose Estimation Based on End-to-End Differentiable...

引用

43rd Chinese control Conference, CCC 2024

作者： Cai, Yuheng Xu, Chi China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9789887581581

Locating 3D objects from a single RGB image via perspective projection is a long-standing problem in computer vision. Inspired by differentiable geometry methods in the field of camera relocation, we apply this neural network combined with differentiable perspective projection to form an end-to-end architecture to the field of object position estimation through object 3D reconstruction methods. The proposed method uses a differentiable LM algorithm for end-to-end pose estimation to achieve higher accuracy, and the gradient is passed back to the neural network to guide its learning. At the same time, we propose a virtual view generation algorithm for augmenting the data to improve the algorithm's sensitivity to the size of the co-vision region. Through experiments, we prove the effectiveness of our method. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enabling Few-Shot Learning with PID control: A Layer Adaptive Optimizer 41

Enabling Few-Shot Learning with PID Control: A Layer Adaptiv...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Le Li, Xinde Zhang, Pengfei Zhang, Zhentong Dunkin, Fir School of Automation Southeast University Nanjing China Nanjing Center for Applied Mathematics Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Southeast University Shenzhen Research Institute Shenzhen China

Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAML-based approaches encounter significant challenges when there is a substantial discrepancy in the distribution of training and testing tasks, resulting in inefficient learning and limited generalization across domains. Inspired by classical proportional-integral-derivative (PID) control theory, this study introduces a Layer-Adaptive PID (LA-PID) Optimizer, a MAML-based optimizer that employs efficient parameter optimization methods to dynamically adjust task-specific PID control gains at each layer of the network, conducting a first-principles analysis of optimal convergence conditions. A series of experiments conducted on four standard benchmark datasets demonstrate the efficacy of the LA-PID optimizer, indicating that LA-PID achieves state-of-the-art performance in few-shot classification and cross-domain tasks, accomplishing these objectives with fewer training steps. Code is available on https://***/yuguopin/LA-PID. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultra-short-term PV Power Forecasting

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultr...

引用

2024 China Automation Congress, CAC 2024

作者： Wu, Ji Wang, Kai Ma, Wenwen Zhang, Jingxin Wang, Shibo China Electric Power Research Institute Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (纸本)9798350368604

Accurate ultra-short-term photovoltaic (PV) power forecasting is crucial for the real-time scheduling of grid systems. However, the inherent variability of solar energy makes this task extremely challenging. To enhance PV power forecasting, this paper introduces a novel hybrid model named PVTimesNet, designed to harness the strengths of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) for effective feature extraction. PVTimesNet consists of two parallel branches: the CNN1d branch, which captures correlations between multiple variables and adjacent time steps, and the LSTM branch, which learns the temporal dependencies within the PV power sequences. The features extracted by both branches are then concatenated and passed through a fully connected layer to generate multi-step PV power forecasts. Experimental results demonstrate that for forecast horizons of 1 to 4 hours, the proposed model significantly outperforms individual models and other CNN-LSTM hybrid structures. Additionally, it exhibits superior performance compared to related methods for longer forecast horizons. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

Guided Transformative GAN: Joint Face Image Super-Resolution and Frontalization

Guided Transformative GAN: Joint Face Image Super-Resolution...

引用

International Conference on systems and Informatics (ICSAI)

作者： Minghao Mu Wei Wang Xiaobo Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

Joint face super-resolution and frontalization of non-frontal low-resolution faces is of significant importance for many face analysis applications. However, at the same time, it is a challenging task. In this paper, a novel Guided Transformative Generative Adversarial Network (GT-GAN) is proposed to address the challenge of generating frontal high-resolution face images from non-frontal low-resolution face images. Existing methods usually treat super-resolution and frontalization as two separate tasks, leading to unsatisfactory processing results. GTG AN innovatively achieves both goals within a unified frame-work. Specifically, we propose Profile Attention Guidance (PAG) to generate landmark heatmaps that provide a priori pose information to the generative network and direct its attention to critical facial regions. In addition, an Attention Fusion Transformation Module (AFTM) is proposed to significantly improve the hallucination performance of the network by utilizing the attention mechanism and STNs, combined with sequential feature enhancement strategies. The experimental results show that GT-GAN exhibits superior performance in the joint face super-resolution and frontalization task on the public face dataset Multi-PIE, which provides new ideas and references for this challenging topic.

关键词： Heating systems Attention mechanisms Superresolution Generative adversarial networks Informatics Faces

来源：评论

学校读者我要写书评

暂无评论

A Image steganography Technique based on Denoising Diffusion Probabilistic Models

A Image steganography Technique based on Denoising Diffusion...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Enzhi Xu Yang Cao Le Hu Chenxing Wang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

Image steganography is the process of hiding secret information into an image while still keeping its original appearance intact. It plays a crucial role in secure communication and data storage. While deep learning-based techniques have shown notable progress in the field of image steganography, they still face challenges in extraction accuracy and robust security. This paper introduces an innovative image steganography method utilizing the diffusion model, which is the most powerful technique of image generation. Our method utilizes the sampling process of the diffusion model to hide the secret image in the generated image, and the receiver uses the secret key to extract the secret data accurately. The results of our experiments validate the effectiveness of our approach, outperforming existing methods in security, capacity, and extraction precision, which shows the potential for practical applications.

关键词： Resistance Steganography Visualization Accuracy Noise reduction Receivers Diffusion models

来源：评论

学校读者我要写书评

暂无评论

A Detector-Free Image Matching Method based on Enhanced Feature Fusion 43

A Detector-Free Image Matching Method based on Enhanced Feat...

引用

43rd Chinese control Conference, CCC 2024

作者： Chen, Ziyang Xu, Chi China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Eduction Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

ISBN: (纸本)9789887581581

Image feature matching is an important research field in computer vision that can be widely applied to advanced vision tasks, such as 3D reconstruction and visual tracking. Considering the low matching accuracy and poor robustness of traditional detector-based matching methods on weakly textured images, we propose a detector-free image matching method based on enhanced feature fusion. Given that weak texture images consist of a large number of similar or irregular pixels, we introduce a new model that enhances feature fusion to recover the underlying texture information of the image. First, we propose a bidirectional fusion model to extract multi-scale feature maps and add an initialization module to correlate the feature maps and enhance the representation ability of the backbone. Then, we perform feature transformation using the quadtree attention model and finally establish dense pixel-by-pixel matching at both coarse and fine scales. The quadtree attention model employs a hierarchical computational attention method, accurately capturing image details and remote dependencies while ensuring linear complexity. Experimental results demonstrate that the proposed method achieves higher matching accuracy and better generalization on large datasets such as MegaDepth and ScanNet, making it suitable for subsequent work. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Parallel Sensing in Metaverses: Virtual-Real Interactive Smart systems for “6S” Sensing

引用

IEEE/CAA Journal of Automatica Sinica 2022年第12期9卷 2047-2054页

作者： Yu Shen Yuhang Liu Yonglin Tian Xiaoxiang Na School of Artificial Intelligence University of Chinese Academy of ScienceBeijing 100190China IEEE The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Department of Engineering University of CambridgeTrumpington StreetCB21PZUnited Kingdom

In the construction of Metaverses,sensors that are referred to as the“bridge of information transmission”,play a key *** functionality and efficiency of today’s sensors,which operate in a manner similar to physical sensing,are frequently constrained by their hardware and *** this research,we proposed the Parallel Sensing framework,which includes background,concept,basic methods and typical application of parallel *** our formulation,sensors are redefined as the integration of real physical sensors and virtual software-defined sensors based on parallel intelligence,in order to boost the performance of the *** sensor will have a parallel counterpart in the virtual world within the framework of parallel *** sensors serve as the brain of sensors and maintain the same properties as physical *** sensing allows physical sensors to operate in discrete time periods to conserve energy,while cloud-based descriptive,predictive,and prescriptive sensors operate continuously to offer compensation data and serve as *** better illustrate parallel sensing concept,we show some example applications of parallel sensing such as parallel vision,parallel point cloud and parallel light fields,both of which are designed by construct virtual sensors to extend small real data to virtual big data and then boost the performance of perception *** results demonstrate the effective of parallel sensing *** interaction between the real and virtual worlds enables sensors to operate actively,allowing them to intelligently adapt to various scenarios and ultimately attain the goal of“Cognitive,Parallel,Crypto,Federated,Social and Ecologic”6S sensing.

关键词： Parallel Sensing Parallel Intelligence CPSS Metaverses Virtual and Real Interaction “6S”Sensing.

来源：评论

学校读者我要写书评

暂无评论

Animatable Human Neural Radiance Field from Sparse Images Captured by a Single Camera 43

Animatable Human Neural Radiance Field from Sparse Images Ca...

引用

43rd Chinese control Conference, CCC 2024

作者： Yang, Qingru Xu, Chi China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9789887581581

Recently, the use of neural radiance fields (NeRF) for three-dimensional reconstruction of humans has achieved high-quality view rendering. However, existing methods often rely on multiple or single videos as input, requiring dense images, and the rendering quality tends to be poor with sparse image inputs. To address this issue, this paper proposes a novel method that solely utilizes sparse images captured by a single camera to create an animatable human neural radiance field, enabling the rendering of high-fidelity human images under arbitrary novel viewpoints and poses. Specifically, our method utilizes body poses and multi-view feature to build a deformable neural radiance field, and employs frequency-segmented positional encoding to mitigate overfitting during training process. Extensive quantitative and qualitative experiments demonstrate that our proposed method outperforms prior works. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image reconstruction

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：