检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Du, Chaofeng Guo, Jian Guo, Shuxiang Fu, Qiang Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory BinshuiXidao Extension 391 Tianjin300384 China Shenzhen Institute of Advanced Biomedical Robot Co. Ltd. No.12 Ganli Sixth Road Jihua Street Longgang District Shenzhen518100 China School of Life Science Beijing Institute of Technology Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology No.5 Zhongguancun South Street Beijing100081 China

ISBN: (纸本)9798350320831

The amphibious robot needs to accurately estimate the 6D pose of the target in tasks such as target tracking, docking with the recovery module, and target grasping. The current research on target 6D pose estimation is mainly applied to unoccluded targets, but when the target is occluded, the target's pose cannot be accurately identified. Compared with other algorithms, the PVNet algorithm shows better robustness when target is occluded, but the accuracy is still low. To improve the accuracy of the PVNet algorithm, this paper adds the confidence score prediction of the prediction vector at the last layer of the PVNet network, and designs a vector confidence score loss function to train the network. Before generating the hypothetical keypoints, the pixels whose confidence score is lower than the set threshold are screened out, so that the generated hypothetical 2D keypoints are closer to the true 2D keypoints. Finally, the method in this paper is compared with the Tekin, PoseCNN, Oberweger and Pvnet algorithm, and demonstrate the superiority of the proposed method. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Global Perception Attention-based Network for Point Cloud Completion

A Global Perception Attention-based Network for Point Cloud ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Fengyong Wu Enzeng Dong Jigang Tong Sen Yang Wenyu Li Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology 391 Binshui West Road Tianjin China College of Artificial Intelligence Nankai University 94 Weijin Road Tianjin China

The purpose of point cloud completion is designed to high-precision complete the complete shape from local observations. However, the previous approaches have tended to focus on a good perception of local details and lack a better overall representation of the point cloud. To solve this problem, we propose a global attention point cloud reconstruction method based on SnowflakeNet. We designed a global focus module to integrate the global structure information of the original point cloud on the basis of the local shape context features, so as to enhance the perception ability of the network to the local fine structure and the overall shape of the point cloud. At the same time, we improved the point cloud generation part of the network and added SPD that can re-optimize the position of the completion point cloud, so as to achieve more accurate completion results. We conducted a series of experiments on the Completion3D dataset and confirmed that our network outperformed the original algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modal Fusion Sign Language Recognition Based on Swin Transformer Architecture

Modal Fusion Sign Language Recognition Based on Swin Transfo...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Yujie Gao Yadong Li Bin Liu Yifan Tian Minfeng Zhu Jian Luo School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Control Theory &Applications in Complicated System Tianjin University of Technology Tianjin China

Sign language plays an important role in information transmission and emotional communication between the hearing-impaired and the outside world. It is expressed through a rapid and complex combination of gestures, body postures and facial expressions. In this paper, Google's MediaPipe framework is used to extract and process key point information of hands. Depth features are used to supplement the RBG diagram. A framework of skeleton sensing multi-modal recognition suitable for complex scenes is proposed. This can be used to deal with the problem of sign language recognition of multi-modal information in different scenes. However, most of the existing sign language recognition methods are traditional convolutional networks and LSTM. Although they have excellent achievements in image recognition and video recognition, their application in sign language recognition does not conform to the characteristics of sign language. In this paper, a Swin Transformer model is used to process both depth information and RGB information. Finally, statistical data fusion method was used to fuse the depth prediction results with RGB prediction results. Experimental analysis shows that this method performs well in sign language recognition in complex scenes compared with existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Single-Frame Face Anti-Spoofing Algorithm With Circular CDC and Multi-Scale Spatial Attention

A Single-Frame Face Anti-Spoofing Algorithm With Circular CD...

引用

IEEE International Conference on Mechatronics and Automation

作者： Shan He Enzeng Dong Jigang Tong Sen Yang Xuehui Liang Wenyu Li Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology 391 Binshui West Road Tianjin China College of Artificial Intelligence Nankai University 94 Weijin Road Tianjin China

Face anti-spoofing is to prevent face images with attack properties from entering face recognition and causing confusion or spoofing of the face recognition function. Since most face presentation attacks do not possess true deep information, some recent works use this information as supervisory signal. In this paper, we continue such a pattern by proposing a circular CDC (Central Difference Convolution) with larger sensory field and contextual semantic awareness, and use it in a backbone network for improving the network model’s ability to characterize texture features and multi-scale information. Combined with the spatial attention method concat multiple scale feature maps are used to fuse the feature map information from multiple scales. We conduct a series of experiments on OULU-NPU and demonstrate that our network accuracy is better than the original algorithm, especially in terms of generalizability across devices and different environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Feature Fusion Based Pedestrian Detection Method 17

A Multi-Feature Fusion Based Pedestrian Detection Method

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Dong, Enzeng Jing, Cunlei Zhang, Zufeng Tianjin University of Technology Tianjin Key Laboratory for Control Theory Applications in Complicated Systems Tianjin China

ISBN: (纸本)9781728164151

This paper proposes an improved pedestrian detection algorithm, the Haar-like feature and Adaboost cascade classifier Histogram of Oriented Gradient (HOG) feature are utilizing to construct hybrid features library, then the weak classifiers in Adaboost are trained by using the combined hybrid features. And the strong classifiers are built based on the weak classifiers. In the proposed algorithm, For improving the detection speed, the HOG feature is rapidly calculated by integral histogram instead of gradient histogram features, and the experimental results showed that the method proposed improved the detection performance and detection accuracy of pedestrians. © 2020 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Discrete sliding mode repetitive control based on parabola approach law 17

Discrete sliding mode repetitive control based on parabola a...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Jia, Chao Gao, Xuewei Wei, Jiaqi He, Haocheng Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjiin300384 China

ISBN: (纸本)9781728164151

According to the characteristics of parabola function, a new discrete-time sliding mode repetitive control method based on parabola approach law is proposed for the periodic trajectory tracking of uncertain discrete-time systems in modern industrial production. The discrete sliding mode controller based on parabola approach law can effectively suppress chattering, and the discrete sliding mode repetitive controller based on ideal switching dynamics can solve the problem of periodic disturbance. The convergence characteristics of parabola approach law are analyzed, including absolute convergence layer, monotone convergence layer and steady-state error band, which are used to describe the dynamic performance of system error under different parameters. The simulation results verify the effectiveness of the proposed control method. © 2020 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Mobile Robot Based on Improved Artificial Potential Field Method

Path Planning of Mobile Robot Based on Improved Artificial P...

引用

Chinese control and Decision Conference, CCDC

作者： Jianyun Ni Helei Du Tie Wang Hao Li Chenyang Xue Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin China School of Electronic Engineering and Automation Tianjin University of Technology Tianjin China Tianjin Climate Center Tianjin China Tianjin University of Technology Tianjin China

An improved artificial potential field method is proposed to address the problems of target unreachability and falling into local minima in the path planning process of the traditional artificial potential field method. Firstly, the distance factor between the robot and the target point is introduced to solve the target unreachability problem; secondly, the robot is guided out of the local minima point by setting the virtual target point through the double-circle strategy; finally, in order to satisfy the continuity of robot velocity and acceleration, the resulting path is smoothed by using three uniform B-sample curves. The experimental results show that the improved algorithm can effectively solve the problems of target unreachability and falling into local minima in the traditional algorithm, and the smoothness of the path after the spline treatment is better compared with the original path.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point Density-aware Channel-wise Transformer for LiDAR 3D Object Detection

Point Density-aware Channel-wise Transformer for LiDAR 3D Ob...

引用

IEEE International Conference on Mechatronics and Automation

作者： Fanhang Yang Enzeng Dong Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology 391 Binshui West Road Xiqing District Tianjin China Department of Electrical Engineering Tshwane University of Technology Pretoria South Africa

We present a two-stage 3D object detection framework from point clouds, named Point Density-aware Channel-wise Transformer (PD-CT3D), which investigate the property of point density. This architecture uses 3D sparse CNN to effectively generate high-quality proposals at the first stage, then integrates the inherent property of point density and 3D CNN-based voxel features by density-aware proposal grid pooling. Specifically, each generated proposal from the first stage is divided into grids to aggregate corresponding voxel-wise features and raw point-based features for encoding the representative features from the whole scene. Subsequently, a channel-wise encoder-decoder transformer is adopted to extract the encoded density-aware features and decode them into a global representation for final refinement. Experiments on the widely used KITTI dataset show that the PD-CT3D achieves competitive performance among state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rapid calibration method for 3d laser scanner

引用

Recent Patents on Engineering 2020年第2期14卷 234-241页

作者： Liu, Bin Qiao, Qian Han, Fangfang Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin City300384 China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin City300384 China

Background: The 3D laser scanner is a non-contact active-sensing system, which has a number of applications. Many patents have been filed on the technologies for calibrating 3D laser scanner. A precise calibration method is important for measuring the accuracy of the 3D laser scanner. The system model contains three categories of parameters to be calibrated which include the camera intrinsic parameters, distortion coefficients and the light plane parameters. Typically, the calibration process is completed in two steps. Based on Zhangs method, the calibration of the camera intrinsic parameters and distortion coefficients can be performed. Then, 3D feature points on the light plane should precisely be formed and extracted. Finally, the points are used to calculate the light plane parameters. Methods: In this paper, a rapid calibration method is presented. Without any high precision auxiliary device, only one coplanar reference target is used. By using a group of captured images of the coplanar reference target placed in the field of view arbitrarily, calibration can be performed in one step. Based on the constraint from the planes formed by the target in different directions and the camera imaging model, a large amount of 3D points on the light plane can easily be obtained. The light plane equation in the camera coordinates system can be gathered by executing plane fitting to the 3D points. Results: During the experimental process, the developed 3D laser scanner was calibrated by the proposed method. Then, the measuring accuracy of the system was verified with known distance in vertical direction of 1mm with sequential shifting motion generated by precision translation stage. The average value of the measured distances was found to be 1.010mm. The standard deviation was 0.008mm. Conclusion: Experimental results prove that the proposed calibration method is simple and reliable. © 2020, Bentham Science Publishers. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Design of control System for Lower Limb Rehabilitation Robot on the Healthy Side sEMG Signal 20

Design of Control System for Lower Limb Rehabilitation Robot...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Yu, Shiqin Guo, Jian Guo, Shuxiang Fu, Qiang Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory Binshui Xidao Extension 391 Tianjin300384 China Shenzhen Institute of Advanced Biomedical Robot Co. Ltd. No.12 Ganli Sixth Road Jihua Street Longgang District Shenzhen518100 China Beijing Institute of Technology Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science No.5 Zhongguancun South Street Beijing100081 China

ISBN: (纸本)9798350320831

With the number of stroke patients increasing year by year, rehabilitation exoskeleton robot has been paid more and more attention. For the rehabilitation exoskeleton robot, human-computer interaction ability is an important index, which affects the effect of rehabilitation therapy to a great extent. Surface Electromyography (sEMG) signals are the combined effect of sEMG signals and electrical activities on nerve stem on the skin surface, which can reflect neuromuscular activities in advance and can be used to predict movement intention by sEMG signals. Therefore, this article proposes to use sEMG signals to monitor the motion information of the healthy leg in real-time, extract the characteristics of the electromyography signals, use the sEMG of the healthy leg as the control signal, reflect the motion patterns reflected by the sEMG collected from the healthy side, and then use the motion intention recognition method of Long Short Term Memory(LSTM) neural network to identify the motion intention of the prosthetic limb by identifying the motion patterns of the swing phase of the healthy side. The results indicate that the predicted maximum Root Mean Squared Error(RMSE) is 5.3729, which proves the feasibility of using LSTM model for motion intention recognition and contributes to the real-time and accuracy of lower limb exoskeleton rehabilitation. © 2023 IEEE.

关键词： Long short-term memory

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：