检索结果-内蒙古大学图书馆

26th International Conference on Industrial Technology, ICIT 2025

作者： Huang, Nanxin Xu, Chi 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 Wuhan China

ISBN: (纸本)9798331521950

Driven by advancements in industrial production and artificial intelligence, the need for pose estimation of new ob-jects in areas like robotic manipulation and virtual reality is increasing. We introduce a zero-shot object pose estimation approach that identifies the poses of objects excluded from the training dataset, removing the requirement for re-modeling. The method is built around a multi-level features fusion framework de-signed to enhance generalization. First, a trainable feature extraction module filters and selects multi-level features extracted by the backbone network. Unlike traditional convolutional ker-nels, we incorporate a dynamic convolution kernel to enhance the feature extraction capability. Second, in the feature fusion module, we adopt a dynamic weight generation strategy to perform weighted fusion of multi-level features. This method enhances template matching by effectively describing similarities between unseen objects (those absent from the training set) and templates, leveraging robust and adaptive feature representations to narrow the gap with seen objects. Experimental results demonstrate that our approach achieves state-of-the-art performance on two popu-lar benchmark datasets, LineMod and LineMod-Occlusion, proves that our method has better generalization than previous models. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Dual-polarization Dual-mode Silicon 3dB Beam Splitter Based on Shallow Etched Multimode Interference Coupler

Dual-polarization Dual-mode Silicon 3dB Beam Splitter Based ...

引用

Optoelectronics Global Conference (OGC)

作者： Hong Ma Mengyuan Ye Jie Liu Duowei Zeng Yang Chen School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences Wuhan China

In this paper, we propose a dual polarization dual mode 3dB beam splitter. By utilizing the shallow etched multimode interference (MMI) coupler, the proposed device can handle TE 0 , TE 1 , TM 0 and TM 1 modes simul...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Dynamic Labels in Network Pruning

Research on Dynamic Labels in Network Pruning

引用

Industrial Cyber-Physical systems (ICPS)

作者： Lijun Zhang Yaomin Luo Shiqi Xie Xiucheng Wu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Wuhan China

Convolutional neural network compression technology plays an extremely important role in model transplantation and deployment, especially in mobile and embedded hardware platforms with small memory and low computing power, compression technology is even more critical. Convolutional neural network channel pruning technology has developed rapidly in recent years, and a number of excellent pruning algorithms have emerged. The channel pruning technology has gradually developed from the earliest static pruning to dynamic pruning, which adopts different pruning schemes for different inputs. However, the current dynamic pruning scheme needs to introduce multiple modules to predict the mask to prune the feature maps, and some schemes also introduce multiple hyperparameters in the loss function to balance the model accuracy and pruning rate, which leads to The model has difficulty converging during training. We propose a dynamic pruning method, each convolution structure configures a simple prediction module, and generating dynamic labels through the input's norm and similarity to guide the prediction module training, which will not bring new parameters to the loss function. We conducted related experiments on multiple models on the Cifar10 datasets. The experiments on ResNet56 show that our scheme is 1.3% higher than the most advanced scheme in terms of compression rate under the premise of the same accuracy.

关键词： Training Convolution Heuristic algorithms Computational modeling Predictive models Cyber-physical systems Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Oscillation Trajectory Optimization and control Method for Two-Link Underactuated Manipulators 42

Oscillation Trajectory Optimization and Control Method for T...

引用

42nd Chinese control Conference, CCC 2023

作者： Wang, Lejun Wang, Huiming Tang, Xianlun Huang, Zixin Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan430200 China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China

ISBN: (纸本)9789887581543

This paper provides an oscillation trajectory optimization and control method for two-link underactuated manipulators (UMs) in a vertical plane. The proposed method solves the problem that the UMs cannot always enter the balance region in the partitioning method. First, we establish the system dynamic model, and analyze the system couple characteristics. Then, we program an oscillation trajectory for the active link, and use the intelligent method to obtain the trajectory parameters, so ensuring the system can reach the area adjacent to the target position through tracking control. Next, we design the controller to realize the stable control at the target position. Finally, the simulation results show the effectiveness and generality of the control strategy. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Polarization-independent Dual Mode Silicon Spot Size Converter Using Gradual Index Distributed Subwavelength Gratings

Polarization-independent Dual Mode Silicon Spot Size Convert...

引用

Optoelectronics Global Conference (OGC)

作者： Jie Liu Mengyuan Ye Hong Ma Duowei Zeng Yang Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

We propose and demonstrate a polarization-independent dual mode spot size converter (SSC) on silicon integrated platform. By utilizing gradual index distributed subwavelength gratings (GRIN-SWG). The proposed device c...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelength Selective Mode Converter Using Grating Assisted Anti-reflection Contra-asymmetric Directional Couplers

Wavelength Selective Mode Converter Using Grating Assisted A...

引用

Optoelectronics Global Conference (OGC)

作者： Duowei Zeng Mengyuan Ye Yang Chen Hong Ma Jie Liu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

We propose and demonstrate a wavelength selective mode converter on silicon integrated platform. By utilizing grating assisted anti-reflection contra-asymmetric directional couplers (CADCs), wavelength selective TE 0 -TE 1 mode conversion could be achieved. Simulation results show that the operation wavelength is 1544.8 nm and 3 dB bandwidth is 8.3 nm. Insertion loss of the proposed device is simulated to be 0.29dB and the crosstalk is less than -50dB. The proposed device can be used in mode division multiplexing (MDM) wavelength division multiplexing (WDM) communication network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Expression Recognition Network Based on Spot-Adaptive Knowledge Distillation

Efficient Facial Expression Recognition Network Based on Spo...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Xin Wen Zhen-Tao Liu Dan Chen School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

Facial expression recognition plays a key role in promoting the development of comprehensive intelligence and building friendly human-computer interaction. Due to the interference of feature noise in expression data, the lightweight facial expression recognition model with fewer parameters is difficult to learn more expression features through simple training, which limits the improvement of its recognition performance. An efficient facial expression recognition network based on Spot-adaptive Knowledge Distillation is proposed in this paper. Inspired by VoVNetV2, the network designed in this paper is lightweightly improved using Depthwise Separable Convolution and the parameter-free SimAM attention mechanism, reducing the number of parameters to 0.21 M. To further improve the recognition accuracy of the model, Spot-adaptive Knowledge Distillation is employed to improve the characterization ability of the model. The recognition accuracies of the student network designed in this paper on the KDEF and RAF-DB datasets are 93.05% and 81.17% respectively after spot-adaptive distillation.

关键词： Knowledge engineering Training Human computer interaction Accuracy Face recognition Computational modeling Noise Neural networks Interference Data models

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Features Fusion for Zero-Shot Object Pose Estimation

Multi-Level Features Fusion for Zero-Shot Object Pose Estima...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Nanxin Huang 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 Education Wuhan China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

关键词： Training Solid modeling Convolution Service robots Pose estimation Zero shot learning Virtual reality Benchmark testing Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

SDSFusion: A Semantic-Aware Infrared and Visible Image Fusion Network for Degraded Scenes

引用

IEEE Transactions on Image Processing 2025年 34卷 3139-3153页

作者： Chen, Jun Yang, Liling Yu, Wei Gong, Wenping Cai, Zhanchuan Ma, Jiayi China University of Geosciences School of Automation Wuhan 430074 China Automation for Complex Systems Hubei Key Laboratory of Advanced Control and Intelligent Wuhan 430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan 430074 China China University of Geosciences Faculty of Engineering Wuhan 430074 China Macau University of Science and Technology School of Computer Science and Engineering Macau Macao Wuhan University Electronic Information School Wuhan 430072 China

A single-modal infrared or visible image offers limited representation in scenes with lighting degradation or extreme weather. We propose a multi-modal fusion framework, named SDSFusion, for all-day and all-weather infrared and visible image fusion. SDSFusion exploits the commonality in image processing to achieve enhancement, fusion, and semantic task interaction in a unified framework guided by semantic awareness and multi-scale features and losses. To address the disparity between infrared and visible images in degraded scenes, we differentiate modal features in a unified fusion model. Unlike existing joint fusion methods, we propose an adversarial generative network that refines the reconstruction of low-light images by embedding fused features. It provides feature-level brightness supplementation and image reconstruction to refine brightness and contrast. Extensive experiments in degraded scenes confirm that our approach is superior to state-of-the-art approaches in visual quality and performance, demonstrating the effectiveness of interaction improvement. © 1992-2012 IEEE.

关键词： adversarial generative network image fusion Multi-modal fusion semantic awareness

来源：评论

学校读者我要写书评

暂无评论

Inverse Compensation Feedforward control Strategy for a Vertical Pneumatic Artificial Muscle system 8

Inverse Compensation Feedforward Control Strategy for a Vert...

引用

8th International Conference on control Science and systems Engineering, ICCSSE 2022

作者： Xiao, Huai Meng, Qingxin Lai, Xuzhi Yan, Ze Zhao, Shiying Wu, Min 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 Hubei Wuhan430074 China

ISBN: (纸本)9781665484138

This paper proposes an inverse compensation feed-forward control strategy for a vertical pneumatic artificial muscle (PAM) system. Firstly, we conduct a preliminary experiment on the vertical PAM system, and on this basis, we analyze the motion characteristics of the system. Moreover, we clarify the control objective of this paper. Then, we establish a model that can describe the hysteresis characteristics of the system, and we further construct an inverse compensation feedforward controller by inversing this established model. Finally, we carry out some tracking control experiments based on the vertical PAM experimental platform to verify the effectiveness and superiority of the proposed control strategy, © 2022 IEEE.

关键词： Hysteresis

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：