检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industrial Process

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industria...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Shaojie Yang Peng Li Shuai Li Xiaofeng Zhou Shanghong Jiang Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Information Center of Ansteel Mining Limited Company Anshan China

ISBN: (纸本)9781665401166

Aiming at the characteristics of multi-scale, time series and nonlinear of the complex industrial process data, in order to extract process information more efficiently for improving the diagnosibility, a novel fault diagnosis method based on multi-scale long short term memory- fully convolutional networks (LSTM-FCNs) for industrial process is proposed. Firstly, variational mode decomposition (VMD) is used to obtain the multi-scale components of the process data. Then a parallel LSTM and FCNs optimized by batch normalization and random inactivation is built to extract features for each component. Finally, based on the fusion of multi-scale features, a fully connected layer is used for diagnosis. The LSTM-FCNs method is evaluated by the Tennessee Eastman (TE) benchmark industrial process, and compared with other methods, its effectiveness and superiority are verified.

关键词： Fault diagnosis Fault detection Time series analysis Benchmark testing Feature extraction Safety Data mining

来源：评论

学校读者我要写书评

暂无评论

Optomechanical dissipative solitons (vol 600, pg 75, 2021)

引用

NATURE 2022年第7896期602卷 E24-E24页

作者： Zhang, Jing Peng, Bo Kim, Seunghwi Monifi, Faraz Jiang, Xuefeng Li, Yihang Yu, Peng Liu, Lianqing Liu, Yu-xi Alu, Andrea Yang, Lan Department of Electrical and Systems Engineering Washington University St. Louis MO USA Department of Automation Tsinghua University Beijing P. R. China Photonics Initiative Advanced Science Research Center City University of New York New York NY USA Physics Program Graduate Center City University of New York New York NY USA State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang P. R. China Institute of Microelectronics Tsinghua University Beijing P. R. China

来源：评论

学校读者我要写书评

暂无评论

HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration

arXiv

引用

arXiv 2021年

作者： Yan, Shuaizheng Chen, Xingyu Wu, Zhengxing Tan, Min Yu, Junzhi The Laboratory of Cognitive and Decision Intelligence for Complex System Institute of Automation Chinese Academy of Sciences Beijing100190 China The Department of Mechanical Engineering Fuzhou University Fuzhou350000 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Xiaobing.AI Beijing100080 China The State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing100871 China

Robust vision restoration of underwater images remains a challenge. Owing to the lack of well-matched underwater and in-air images, unsupervised methods based on the cyclic generative adversarial framework have been widely investigated in recent years. However, when using an end-to-end unsupervised approach with only unpaired image data, mode collapse could occur, and the color correction of the restored images is usually poor. In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater and in-air images. For effective color correction and quality enhancement, an underwater image degeneration model must be explicitly constructed based on the optically unambiguous physics law. Thus, we employ the Jaffe-McGlamery degeneration theory to design a generator and use neural networks to model the process of underwater visual degeneration. Furthermore, we impose physical constraints on the scene depth and degeneration factors for backscattering estimation to avoid the vanishing gradient problem during the training of the hybrid physical-neural model. Experimental results show that the proposed method can be used to perform high-quality restoration of unconstrained underwater images without supervision. On multiple benchmarks, the proposed method outperforms several state-of-the-art supervised and unsupervised approaches. We demonstrate that our method yields encouraging results in real-world applications. © 2021, CC BY-NC-ND.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

One to many: Adaptive instrument segmentation via meta learning and dynamic online adaptation in robotic surgical video

arXiv

引用

arXiv 2021年

作者： Zhao, Zixu Jin, Yueming Lu, Bo Ng, Chi-Fai Dou, Qi Liu, Yun-Hui Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The T Stone Robotics Institute The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The Department of Surgery The Chinese University of Hong Kong Hong Kong

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and expensive to collect and annotate sufficient data from every new domain. To greatly increase the label efficiency, we explore a new problem, i.e., adaptive instrument segmentation, which is to effectively adapt one source model to new robotic surgical videos from multiple target domains, only given the annotated instruments in the first frame. We propose MDAL, a meta-learning based dynamic online adaptive learning scheme with a two-stage framework to fast adapt the model parameters on the first frame and partial subsequent frames while predicting the results. MDAL learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. The added gradient gate excludes the noisy supervision from pseudo masks for dynamic online adaptation on target videos. We demonstrate empirically that MDAL outperforms other state-of-the-art methods on two datasets (including a real-world RAS dataset). The promising performance on ex-vivo scenes also benefits the downstream tasks such as robot-assisted suturing and camera control. Copyright © 2021, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

Multibody simulation for tracking error reduction in solar tracking robots

引用

AIP Conference Proceedings 2023年第1期2872卷

作者： Aldo Hernández-Díaz Diego A. Flores-Hernández Alberto Luviano-Juárez Sergio Isai Palomino-Resendiz Itzamá López-Yáñez National Polytechnic Institute - UPIITA Applied Dynamic Systems Laboratoy Mexico City 07340 Mexico National Polytechnic Institute - UPIITA Advanced Robotics Laboratory Mexico City 07340 Mexico National Polytechnic Institute - ESIME-ZAC Department of Control and Automation Mexico City 07738 Mexico National Polytechnic Institute - CIDETEC Mexico City 07738 Mexico

Currently, the use of renewable energy sources such as solar energy, collected by photovoltaic technology, has gained ground in the energy sector. Its use has been popularised due to the fact that it is considered a clean energy, that is a type of energy is produced without burning fossil fuels which are a cause of global warming, among other environmental damages. In order to optimize the energy harvesting through photovoltaic technology, it is necessary to maintain a perpendicular incidence of the sun rays with the photovoltaic module, leading to the use of solar tracking systems that demand the application of trajectory tracking control strategies that minimize the tracking errors while ensuring the lowest energy consumption of the robotic system. In this work, a comprehensive multibody simulation was carried out to obtain a concrete appreciation of the behavior of the tracking system prior to an experimental implementation. This type of simulations allows us to simulate complete systems formed by solid links and rigid joints that were previously designed, and with a calculated analytical model (Kinematic and Dynamic). Furthermore, the obtained simulator allows us to apply a variety of control strategies that are represented by means of 3D simulations which are very similar to the actual experimental results, so that it would be possible to estimate the ªtracking error results° without the necessity of a physical implementation. From the kinematic and dynamic models of a solar tracker of two degrees of freedom, released in an azimuthal-elevation configuration, a PID controller and a passivity-based controller were implemented in Matlab-Simscape®, obtaining simulations of a solar trajectory tracking minimizing the error between the reference and the solar tracker.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A grasping CNN with image segmentation for mobile manipulating robot

A grasping CNN with image segmentation for mobile manipulati...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Yu, Yingying Cao, Zhiqiang Liang, Shuang Liu, Zhicheng Yu, Junzhi Chen, Xuechao Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Intelligent Robotics Institute BIT Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (纸本)9781728163215

This paper presents a grasping convolutional neural network with image segmentation for mobile manipulating robot. The proposed method is cascaded by a feature pyramid network FPN and a grasping network DrGNet. The FPN network combined with point cloud clustering is used to obtain the mask of the target object. Then, the grayscale map and the depth map corresponding to the target object are combined and sent to the DrGNet network for providing multi-scale images. On this basis, depthwise separable convolution is used for encoding. The results of encoders are refined according to the light-weight RefineNet as well as sSE, which can achieve a better grasp detection. The proposed method is verified by the experiments on mobile manipulating robot. © 2019 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Stairs reconstruction with 3D point cloud for gait generation of lower limb exoskeleton robot

Stairs reconstruction with 3D point cloud for gait generatio...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Feng, Yachun Xia, Linqing He, Yong Wang, Can Yan, Zefeng Wu, Xinyu Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

With the aging of the population, a considerable number of elderly persons suffer from walking disability. Lower limb exoskeleton robots have been proved to be effective in rehabilitation training and walking assistance. Though significant advancement has been made in the last decade, lacking the ability of adapting to complex terrain is one of the main challenges that restrict the wide application of exoskeleton robots. Thus we focus on the environmental perception and corresponding gait pattern generation of lower limb assistant exoskeleton. In this paper, we introduce a method to generate gait of exoskeleton walking on a stair, which applies the L-0 minimization-based acquisition and reconstruction of stairs information through 3D Point Cloud. The results of experiments show that our method can precisely measure the physical dimension information of stairs. © 2019 IEEE.

关键词： Stairs

来源：评论

学校读者我要写书评

暂无评论

GC-IGTG: A rehabilitation gait trajectory generation algorithm for lower extremity exoskeleton

GC-IGTG: A rehabilitation gait trajectory generation algorit...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： He, Yong Wu, Xinyu Ma, Yue Cao, Wujing Li, Nan Li, Jinke Feng, Wei Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for the patients with lower limb disability. Lower extremity exoskeleton has been proven to be efficient to provide highly repeatable and accurate rehabilitation exercise, but most existing exoskeletons' gait trajectories won't vary with the users. This paper proposes an algorithm, named as gait cell based individualized gait trajectory generation (GC-IGTG), for the purpose of offering a natural and personalized gait trajectory reference for the lower extremity exoskeleton based on the body parameters of the patients. The GC-IGTG is based on extreme learning machine and AutoEncoder, which makes it achieve fast training speed and suitable for small sample training conditions. The gait cell concept is proposed to improve the efficiency and safety of the algorithm. The experimental results indicate that the generated trajectories with GC-IGTG are almost identical to the original ones. © 2019 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：