检索结果-内蒙古大学图书馆

12th International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2022

作者： Ding, Shihong Zhao, Huanyu Han, Zhi Tang, Yandong Shenyang Ligong University CO Shenyang110158 China The First Affiliated Hospital of China Medical University CO Shenyang110002 China Shenyang Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Robotics CO Shenyang110016 China Institutcs for Robotics and Intelligent Manufacturing Chinese Academy of Sciences CO Shenyang110168 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

For a long time, making machines have the ability of pattern recognition is the direction of scientists' continuous research. The study of pattern recognition is the fundamental way to understand the essence of artificial intelligence. At present, computer vision has been used to identify and count cells. In view of the problems existing in the field of cell counting, such as difficulties in identifying cells, dense cells, viscosity, difficult cell counting, inaccurate judgment and so on, this paper realizes the identification and counting through the technology of computer vision, determines the types of cells, and explores the characteristics of dense and sticky cells, At the same time, based on the characteristics of dense and sticky cells, a color based threshold segmentation algorithm is introduced to optimize the performance of cell classification. At the same time, the recognition and classification of different regions of adhesive cells are carried out, and the adhesive cells in different regions are recognized and judged by the technology of computer vision. Through gray-scale transformation, threshold segmentation, morphological processing and LOG algorithm filtering of medical cell image, the cell region is extracted and counted. The cell counting is realized by calculating the connected domain. The experimental results preliminarily verify the effectiveness of this method, but it still needs to be improved. © 2022 IEEE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Precise LiDAR SLAM in Structured Scene Using Finite Plane and Prior Constraint

Precise LiDAR SLAM in Structured Scene Using Finite Plane an...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Xie, Yuhui Zhao, Wentao Wang, Jiahao Wang, Jingchuan Chen, Weidong Institute of Medical Robotics and Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China School of Mechanical Engineering Shanghai Jiao Tong University Ministry of Education Shanghai200240 China

ISBN: (纸本)9781665481090

In this paper, we propose a precise LiDAR SLAM in optimization framework using plane-like object as landmark. Compared to general methods, finite plane feature is used to represent landmark and a new residual model is designed, making constraint from edge of landmark can be used to limit the parallel position between LiDAR and landmark, leading to a more accurate result. Moreover, floor plan is used to provide global pose for reduction of drift, and additionally feature orientation prior is used to prevent map distortion when updating the inaccurate part of floor plan. Experiments are conducted using data collected in real environment. The result qualitatively shows that proposed method can build a corrected map from floor plan without distortion, and quantitatively verifies that proposed method can outperform other baseline methods in accuracy. © 2022 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

A Real-time Local Planner Design for Smart Wheelchairs Based on Koopman Bilinear Model Predictive Control

A Real-time Local Planner Design for Smart Wheelchairs Based...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Guanfeng Yu Han Zhang Zehao Wang Jingchuan Wang Department of Automation Institute of Medical Robotics Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

The paper introduces a Koopman bilinear model predictive control (KBMPC) as a local planner for smart wheelchair systems. This approach leverages the Koopman Operator to streamline the nonlinear terms in MPC, aiming to achieve superior real-time performance. In particular, we employ the Extended Dynamic Mode Decomposition (EDMD) method to approximate the infinite dimensional Koopman operator. To tackle the challenge of designing lifting functions, we systematically utilize the derivatives of known nonlinear structures to methodically derive lifting functions. This systematic approach facilitates the identification of a precise bilinear model. Next, we formulate the corresponding Koopman bilinear MPC problem. Finally, an iterative algorithm is employed to efficiently solve the KBMPC problem. This method linearizes the bilinear model around estimations and iteratively solves the resulting quadratic programming problem to refine estimations. This allows KBMPC to function as a real-time local planner for smart wheelchairs. The prediction of nonlinear terms shows that the identified Koopman bilinear model increases the prediction accuracy. Furthermore, experiments demonstrate the advantages of the designed KBMPC local planner, highlighting its superior real-time performance and predictive capabilities.

关键词： Pedestrians Accuracy Systematics Wheelchairs Estimation Predictive models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

K-BMPC: Derivative-based Koopman Bilinear Model Predictive Control For Tractor-trailer Trajectory Tracking With Unknown Parameters

K-BMPC: Derivative-based Koopman Bilinear Model Predictive C...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Zehao Wang Han Zhang Jingchuan Wang Department of Automation Institute of Medical Robotics Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Nonlinear dynamics bring difficulties to controller design for control-affine systems such as tractor-trailer vehicles, especially when the parameters in the dynamics are unknown. To address this constraint, we propose a derivative-based lifting function construction method, show that the corresponding infinite dimensional Koopman bilinear model over the lifting function is equivalent to the original control-affine system. Further, we analyze the propagation and bounds of state prediction errors caused by the truncation in derivative order. The identified finite dimensional Koopman bilinear model would serve as predictive model in the next step. Koopman Bilinear Model Predictive control (K-BMPC) is proposed to solve the trajectory tracking problem. We linearize the bilinear model around the estimation of the lifted state and control input. Then the bilinear Model Predictive Control problem is approximated by a quadratic programming problem. Further, the estimation is updated at each iteration until the convergence is reached. Moreover, we implement our algorithm on a tractor-trailer system, taking into account the longitudinal and side slip effects. The open-loop simulation shows the proposed Koopman bilinear model captures the dynamics with unknown parameters and has good prediction performance. Closed-loop tracking results show the proposed K-BMPC exhibits elevated tracking precision with the commendable computational efficiency. The experimental results demonstrate the feasibility of K-BMPC.

关键词： Trajectory tracking Computational modeling Estimation Predictive models Control systems Data models Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Design, Modeling, and Control of a Coaxially Aligned Steerable (COAST) Guidewire Robot” [Jul 20 4947-4954]

引用

IEEE robotics and automation Letters 2023年第11期8卷 7823-7824页

作者： Seokhwan Jeong Yash Chitalia Jaydev P. Desai Medical Robotics and Automation (RoboMed) Laboratory Georgia Institute of Technology Atlanta GA USA Department of Mechanical Engineering Sogang University Seoul South Korea Healthcare Robotics and Telesurgery (HeaRT) Laboratory Department of Mechanical Engineering University of Louisville Louisville KY USA RoboMed Laboratory Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA USA

Presents corrections to the article “Design, Modeling, and Control of a Coaxially Aligned Steerable (COAST) Guidewire Robot”.

关键词： medical robotics Catheters Position control Blood vessels Wires

来源：评论

学校读者我要写书评

暂无评论

NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising

arXiv

引用

arXiv 2024年

作者： Deng, Tianchen Wang, Yanbo Xie, Hongle Wang, Hesheng Wang, Jingchuan Wang, Danwei Chen, Weidong Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

In recent years, there have been significant advancements in 3D reconstruction and dense RGB-D SLAM systems. One notable development is the application of Neural Radiance Fields (NeRF) in these systems, which utilizes implicit neural representation to encode 3D scenes. This extension of NeRF to SLAM has shown promising results. However, the depth images obtained from consumer-grade RGB-D sensors are often sparse and noisy, which poses significant challenges for 3D reconstruction and affects the accuracy of the representation of the scene geometry. Moreover, the original hierarchical feature grid with occupancy value is inaccurate for scene geometry representation. Furthermore, the existing methods select random pixels for camera tracking, which leads to inaccurate localization and is not robust in real-world indoor environments. To this end, we present NeSLAM, an advanced framework that achieves accurate and dense depth estimation, robust camera tracking, and realistic synthesis of novel views. First, a depth completion and denoising network is designed to provide dense geometry prior and guide the neural implicit representation optimization. Second, the occupancy scene representation is replaced with Signed Distance Field (SDF) hierarchical scene representation for high-quality reconstruction and view synthesis. Furthermore, we also propose a NeRF-based self-supervised feature tracking algorithm for robust real-time tracking. Experiments on various indoor datasets demonstrate the effectiveness and accuracy of the system in reconstruction, tracking quality, and novel view synthesis. © 2024, CC BY-NC-SA.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Accurate Segmentation of Lumbar Spine Magnetic Resonance Imaging by Deep Neural Network with Size-Adaptive Loss 23

Accurate Segmentation of Lumbar Spine Magnetic Resonance Ima...

引用

15th International Conference on Machine Learning and Computing, ICMLC 2023

作者： Zhang, Yingdi Shi, Zelin Wang, Huan Yan, Chongnan Wang, Lanbo Mu, Yueming Liu, Yunpeng Wu, Shuhang Liu, Tianci Pang, Mingqi Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Spine Surgery Department ShengJing Hospital of China Medical University Shenyang China

ISBN: (纸本)9781450398411

Accurate segmentation of lumbar spine is crucial for the assessment of spine disease diagnosis. The accuracy and robustness of segmentation is challenged by morphological complexity of lumbar spine anatomy structure, low contrast and background noise. Moreover, unbalanced anatomical structure impede the segmentation of small-size anatomy. To overcome these problems, an automatic segmentation method of lumber spine MRI is needed. In this paper, we propose to segment lumbar spine using a convolutional neural network (CNN) model. Based on the canonical u-shaped model, a multi-scale feature fusion module (MSFF) is proposed as bottleneck to better capture lumbar spine anatomy information of different sizes. To address the problem of anatomy size imbalance, we reshape the standard cross entropy loss as Size-Adaptive loss such that it adaptively weights the loss assigned to anatomy with different sizes. In order to fully verify the accuracy and effectiveness of the proposed method, we construct the first lumbar spine anatomy segmentation dataset which consists of 747 lumbar axial images from 83 patients. The dice similarity coefficient (DSC) is used to evaluate the segmentation methods. Compared with other methods, the proposed method achieves the best results with the highest average DSC of 0.8911. Ablation study shows that the proposed MSFF module and SizeAdaptive loss can promote segmentation accuracy a lot compared with the baseline model. The results indicate that our proposed method can overcome the influence of morphological variety in some degree and is competitive with other current medical image segmentation algorithms. This novel methodology will be expected to use in clinic for image diagnosis in the future. © 2023 ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes

arXiv

引用

arXiv 2024年

作者： Deng, Tianchen Wang, Nailin Wang, Chongdi Yuan, Shenghai Wang, Jingchuan Wang, Danwei Chen, Weidong The Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China The School of Electrical and Electronic Engineering Nanyang Technological University Singapore

Dense scene reconstruction for photo-realistic view synthesis has various applications, such as VR/AR, autonomous vehicles. However, most existing methods have difficulties in large-scale scenes due to three core challenges: (a) inaccurate depth input. Accurate depth input is impossible to get in real-world large-scale scenes. (b) inaccurate pose estimation. Existing methods are not robust enough with the growth of cumulative errors in large scenes and long sequence. (c) insufficient scene representation capability. A single global radiance field lacks the capacity to effectively scale to large-scale scenes. To this end, we propose an incremental joint learning framework, which can achieve accurate depth, pose estimation, and large-scale scene reconstruction. A vision transformer-based network is adopted as the backbone to enhance performance in scale information estimation. For pose estimation, a feature-metric bundle adjustment (FBA) method is designed for accurate and robust camera tracking in large-scale scenes. In terms of implicit scene representation, we propose an incremental scene representation method to construct the entire large-scale scene as multiple local radiance fields to enhance the scalability of 3D scene representation. Extended experiments have been conducted to demonstrate the effectiveness and accuracy of our method in depth estimation, pose estimation, and large-scale scene reconstruction. The code will be open-sourced upon paper acceptance. © 2024, CC BY-NC-SA.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Nanoscale imaging and mechanical analysis of viral infection on cells by atomic force microscopy

引用

生物化学与生物物理学报（英文版） 2020年第11期52卷 1289-1292页

作者： Bin Liu Dan Dang Yang Yang Peng Yu Mi Li State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China lnstitutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China School of Medical Devices Shenyang Pharmaceutical UniversityShenyang 110016China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China lnstitutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China lnstitutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China lnstitutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China

Investigating the mechanical cues involved in virus-cell interactions opens novel possibilities for understanding the underlying mech-anisms guiding viral infection,which will have great impacts on virology and human *** threat from viruses to human health is increasingly severe,and new deadly viruses are constantly dis-covered in the world,including severe acute respiratory syndrome-related coronavirus,severe acute respiratory syndrome coronavirus 2,Middle East respiratory syndrome-related coronavirus(MERS-CoV),Zika virus(ZIKV),Ebola virus,avian influenza virus,and so on[1-3],which pose unprecedented burden to human society.

关键词： microscopy atomic force virus diseases diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality Enabled Telepresence Framework for Intuitive Robotic Teleoperation

Augmented Reality Enabled Telepresence Framework for Intuiti...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zheng Xu Zecai Lin Huanghua Liu Qingsong Ren Anzhu Gao Institute of Medical Robotics and Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai P. R. China

In terms of telepresence for robotic teleoperation, the existing remote surgery provides the patient’s side real-time videos to remote operators. Its effectiveness is limited due to the lack of depth information, occlusion, and restricted viewing angles. To address it, this paper develops a robotic telepresence framework integrating augmented reality (AR) and 3D reconstruction technology, providing a 3D virtual patient’s side environment for remote operators. The real scene of the patient’s side is reconstructed by a monocular camera with a manipulator before the operation, and the manipulator is teleoperated by the operator at the remote’s side. The manipulator’s pose is fused into the classic SVO+REMODE algorithm to improve the reconstructed accuracy. On the remote’s side, an AR head-mounted display (HMD) is deployed to provide telepresence for operators under a similar environment, and the reconstructed scene of the patient’s side is registered to the remote room, from which the operator can see the whole scene of the patient body and surrounding objects. An ArUco cube is used to evaluate the superimposed error between virtual and real displays, and the effectiveness is validated in an experimental platform for remote surgery.

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：