检索结果-内蒙古大学图书馆

7th International Conference on Information Science and control engineering, ICISCE 2020

作者： Li, Yaqian Lei, Ya Wu, Chao Li, Haibin Yanshan University Key Laboratory of Industrial Computer Control Engineering of Hebei Province Qinhuangdao China

ISBN: (纸本)9781728164069

In this paper, an algorithm is proposed to improve expression recognition by combining reconstructed residuals of local and global information. Firstly, positional relation is introduced into local binary features encoding, and a non-negative matrix decomposition method with sparse correlation constraints is employed to perform reducing of dimension. Then, the features are encoded by bag-of-words model to form local features. Secondly, a discrete wavelet transform is used to emphasis on expression information and extract expression-enhanced global features. Thirdly, collaboration Represents is used to calculate local partial reconstruction residuals and is combined with global reconstruction residuals to construct the final residual to be classified at the decision level. Experiments on Jaffe, TEFID and CK+ data sets prove the effectiveness of the proposed algorithm. © 2020 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Behavioral Recognition of Mice Based on a Deep Network 11

Behavioral Recognition of Mice Based on a Deep Network

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, control, and Intelligent Systems, CYBER 2021

作者： Wang, Xingqi Du, Chen Wang, Ying Hu, Sheng Zhao, Yuliang Key Lab of Industrial Computer Control Engineering of Hebei Province School of Electrical Engineering Yanshan University Qinhuangdao066004 China School of Biomedical Engineering Beijing University of Aeronautics and Astronautics at Beijing Beijing100000 China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China

ISBN: (纸本)9781665425278

In recent years, mouse behavior recognition has been widely used in animal behavior experiments, which is great significance to study ethology, research of animal learning and memory and analysis of drug action. However, how to quickly and accurately determine and recording the behavior of mice is still a challenge. Using manual record of mouse behavior is not only time consuming but also low accuracy;the model obtained by training C3D convolutional neural network is used for prediction and the accuracy of the obtained results cannot meet the requirements. In this paper, according to an 'open field' experiment scheme in animal behavior experiments, an image preprocessing method that integrates multi-Temporal mouse action pictures is proposed. With the theoretical research of deep learning convolutional neural network, the target of mouse behavior classification is finally completed. The preliminary analysis results show that this method has the characteristics of accurate classification, high accuracy and low cost. This method can obtain mouse behavior sequence by continuous batch recognition, which greatly improves the recognition efficiency. © 2021 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Novel Pose Estimation Method of Object in Robotic Manipulation Using Vision-Based Tactile Sensor 5th

A Novel Pose Estimation Method of Object in Robotic Manipula...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhao, Dan Sun, Fuchun Zhou, Quan Wang, Zongtao Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100083 China AnHui Province Key Laboratory of Special Heavy Load Robot Anhui University of Technology Ma Anshan China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066000 China

ISBN: (纸本)9789811623356

The computer vision techniques have been widely used in the robotic manipulation for perception and positioning. However, duo to the inaccuracy of camera calibration and measurement, there is a greatly need for more accurate method to estimate the object pose especially for robotic precise manipulation. In this paper, we propose a novel pose estimation method of object in robotic manipulation using a vision-based tactile sensor. The structure of the tactile sensor and the proposed model are introduced in detail, and verification experiments have been performed. The results show the advantages and better performance of the proposed method. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Robot vision

来源：评论

学校读者我要写书评

暂无评论

CAMInterHand: Cooperative Attention for Multi-View Interactive Hand Pose and Mesh Reconstruction

CAMInterHand: Cooperative Attention for Multi-View Interacti...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Guwen Han Qi Ye Anjun Chen Jiming Chen College of Computer Science and Technology Zhejiang University Hangzhou China College of Control Science and Engineering Zhejiang University Hangzhou China The College of Control Science and Engineeringthe State Key Laboratory of Industrial Control Technology Zhejiang University and the Key Key Lab of CS&AUS of Zhejiang Province

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Interactive hand mesh reconstruction from singleview images poses a significant challenge with the severe occlusion and depth ambiguity inherent in interactive hand gestures. Recent approaches that employ probabilistic models and tokenpruned techniques have shown decent results in multi-view human body reconstruction. Nevertheless, these methods have not fully utilized multi-scale semantic information from multiview images and are not applicable in scenarios involving severe occlusion during dual-hand interactions. Simultaneously, current single-view methods independently reconstruct the left and right hands, which are ineffective in enhancing the interaction between both hands. To address these challenges, we propose CAMInterHand, a cooperative attention-based method for multi-view interactive hand pose and mesh reconstruction. Specifically, CAMInterHand extracts local pyramid features and global vertex features from multi-scale feature maps of multi-view images, enabling the exploration of rich local semantic information and facilitating effective feature alignment. Furthermore, CAMInterHand employs the cooperative attention fusion module to fuse all features from multi-view images, enhancing interactions among vertices of dual hands within global and local contexts. We conduct extensive experiments on the large-scale multi-view dataset InterHand2.6M and CAMInterHand achieves a substantial performance improvement over existing methods for multi-view and single-view interactive hand reconstruction.

关键词： Fuses Semantics Feature extraction Probabilistic logic Data mining Robotics and automation Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Actuator Fault Estimation Based On Adaptive Iterative Learning Algorithm For Nonlinear Periodic Systems

Actuator Fault Estimation Based On Adaptive Iterative Learni...

引用

第40届中国控制会议

作者： Ya-qi Liu Yi-ming Fang Le Liu Xing-da Li Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University

A actuator fault estimation algorithm based on adaptive iterative learning is proposed for a class of nonlinear periodic systems with actuator fault and ***,the proposed method designs a state observer and a fault estimator based on adaptive iterative *** Lyapunov stability theory and the optimization theory are employed to prove the convergence of the *** the LMI toolbox is utilized to obtain the results of the observer gain matrix and fault estimator parameter *** method combines the iterative learning strategy with the adaptive algorithm,and utilizes not only the state error signals of the last iteration learning,but also the output error signals of this *** makes the estimated fault approximate to the real fault gradually and realizes the accurate estimation of the time-varying fault and the intermittent ***,the validity and accuracy of the proposed method are verified by the simulation of a single-link robotic arm mold.

关键词： Iterative learning scheme Adaptive algorithm Fault estimation Actuator fault Linear matrix inequality

来源：评论

学校读者我要写书评

暂无评论

Sensor Fault Detection in nonlinear system using Adaptive Weighted Fusion Algorithm

Sensor Fault Detection in nonlinear system using Adaptive We...

引用

第40届中国控制会议

作者： Fan Qin Shu-ya Yan Yi-ming Fang Jian-xiong Li Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University

In view of the problem that the state estimation contains fault values when detecting sensor faults containing noise based on the Kalman filter algorithm,a sensor fault detection method based on adaptive weighted fusion is proposed in this *** adaptive weighted fusion algorithm gives different weights to several groups of measurement output data to generate the measurement output without ***,the composite embedded cubature Kalman filter algorithm is used to get the state estimation without faults,which will make the mean or variance of the generated residuals change,so as to realize fault ***,the single-link direct drive manipulator system driven by permanent magnet brush DC motor is simulated and *** results show that,compared with the CECKF algorithm alone,the proposed method can eliminate the faults contained in the Kalman filter state estimation,and detect all the output sensor faults more effectively.

关键词： Sensor fault detection Adaptive weighted fusion State estimation Kalman filter

来源：评论

学校读者我要写书评

暂无评论

A novel multi-modal tactile sensor design using thermochromic material

引用

Science China(Information Sciences) 2019年第11期62卷 189-191页

作者： Fuchun SUN Bin FANG Hongxiang XUE Huaping LIU Haiming HUANG Department of Computer Science and Technology Tsinghua University Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University College of Information Engineering Shenzhen University

Tactile sensors are important for ensuring robotic perception [1], and their performance directly affects a robot’s capability for performing dexterous operations. These sensors mimic the tactile sensing capability of human hands. This is because the skin of human hands is involved in considerably meticulous works and can provide multi-

关键词： A novel multi-modal tactile sensor design using thermochromic material

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Combined with Heuristic Search for Solving Discrete Space Path Planning Problems

Reinforcement Learning Combined with Heuristic Search for So...

引用

第33届中国控制与决策会议

作者： Xiuling Zhang Xuenan Kang Kailun Wei Jinxiang Li Kai Ma Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University

Reinforcement learning(RL) has been successfully applied to solve path planning problems,but learning is generally *** main reason is not making full use of information collected during interaction with the *** paper proposes a novel method to solve the discrete space path planning problem in an environment without prior knowledge with intensive obstacles based on RL and heuristic ***,we apply Dyna-Q algorithm of RL to explore the map and search for the target point and optimize its policy with upper confidence bound(UCB).Then,when the target point is found,we use heuristic search to plan the path from the starting point to the target point and narrow the path to a small ***,we combine Dyna-Q algorithm with the heuristic search recommended path for path *** evaluate our algorithm using maze navigation *** results verify that heuristic search accelerates Dyan-Q convergence.

关键词： Dyna-Q algorithm Heuristic search Path planning Discrete space

来源：评论

学校读者我要写书评

暂无评论

DexRepNet: Learning Dexterous Robotic Grasping Network with Geometric and Spatial Hand-Object Representations

DexRepNet: Learning Dexterous Robotic Grasping Network with ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Qingtao Liu Yu Cui Qi Ye Zhengnan Sun Haoming Li Gaofeng Li Lin Shao Jiming Chen College of Control Science and Engineering Zhejiang University Hangzhou China Key Lab of CS&AUS Zhejiang Province College of Control Science and Engineering and the State Key Laboratory of Industrial Control Technology Zhejiang University Department of Computer Science National University of Singapore Singapore

Robotic dexterous grasping is a challenging problem due to the high degree of freedom (DoF) and complex contacts of multi-fingered robotic hands. Existing deep re-inforcement learning (DRL) based methods leverage human demonstrations to reduce sample complexity due to the high dimensional action space with dexterous grasping. However, less attention has been paid to hand-object interaction representations for high-level generalization. In this paper, we propose a novel geometric and spatial hand-object interaction representation, named DexRep, to capture object surface features and the spatial relations between hands and objects during grasping. DexRep comprises Occupancy Feature for rough shapes within sensing range by moving hands, Surface Feature for changing hand-object surface distances, and LocalGeo Feature for local geometric surface features most related to potential contacts. Based on the new representation, we propose a dexterous deep reinforcement learning method DexRepNet to learn a generalizable grasping policy. Experimental results show that our method outperforms baselines using existing representations for robotic grasping dramatically both in grasp success rate and convergence speed. It achieves a 93% grasping success rate on seen objects and higher than 80% grasping success rates on diverse objects of unseen categories in both simulation and real-world experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Jiaqi Li Hongxu Li Yifan Wu Hailiang Zhou Luigi Manfredi Peng Li Hong Zhang Department of Key Lab of Industrial Computer Control Engineering Hebei Province Yanshan University Qinhuangdao China Department of Computing Science University of Alberta Edmonton AB Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. Department of Institute for Medical Science and Technology (IMSaT) University of Dundee United Kingdom Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots.

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：