检索结果-内蒙古大学图书馆

Dense dilated network with probability regularized walk for vessel detection

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Mou, Lei Chen, Li Cheng, Jun Gu, Zaiwang Zhao, Yitian Liu, Jiang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430081 China Cixi Institute of Biomedical Engineering Chinese Academy of Sciences Zhejiang315201 China UBTech Research UBTech Robotics Corp Ltd Guangdong518055 China Department of Computer Science and Engineering Southern University of Science and Technology Guangdong518055 China Cixi Institute of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Zhejiang315201 China

The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multi-scale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method outperforms the state-of-the-art methods in accuracy, sensitivity, specificity and also area under receiver operating characteristic curve. Copyright © 2019, The Authors. All rights reserved.

关键词： Diagnosis

The limits and potentials of deep learning for robotics

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Sünderhauf, Niko Brock, Oliver Scheirer, Walter Hadsell, Raia Fox, Dieter Leitner, Jürgen Upcroft, Ben Abbeel, Pieter Burgard, Wolfram Milford, Michael Corke, Peter Brisbane Australia Robotics and Biology Laboratory Technische Universität Berlin Germany Department of Computer Science and Engineering University of Notre Dame IN United States DeepMind London United Kingdom Paul G. Allen School of Computer Science & Engineering University of Washington WA United States Oxbotica Ltd. Oxford United Kingdom UC Berkeley Department of Electrical Engineering and Computer Sciences CA United States Department of Computer Science University of Freiburg Germany

The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluation metrics, highlight the importance and unique challenges for deep robotic learning in simulation, and explore the spectrum between purely data-driven and model-driven approaches. We hope this paper provides a motivating overview of important research directions to overcome the current limitations, and help fulfill the promising potentials of deep learning in robotics. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

Design, Development and Control of a Three Flexible-Fingers Gripper Based On Hand Gesture

学校读者我要写书评

暂无评论

Design, Development and Control of a Three Flexible-Fingers ...

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Rasoul Sadeghian Pooyan Sedigh Parastoo Azizinezhad Shahrooz Shahin Mehdi Tale Masouleh Human and Robot Interaction Laboratory Tehran Iran Department of Biomedical Engineering Science and Research Branch Islamic Azad University Tehran Iran Faculty of Electrical and Computer Science Robotic Engineering Tehran North Branch Islamic Azad University Tehran Iran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781728101286;9781728101279

In this paper, the process of design, and construction of a flexible gripper with three fingers is presented. The fingers of the proposed gripper are fabricated using a 3D printing device. The gripper is controlled remotely by an autonomous glove which is designed to help people with disability. In order to ameliorate the movement accuracy of the gripper a Fuzzy-PID controller is implemented on the system. The result of experimental tests demonstrate a decrease of the gripper movement error to less than 2 degrees in average. An ultrasonic sensor is set on the gripper's body to improve the grasping process by detecting the distance of the object to the gripper. The fabricated fingers are flexible and provides the ability of grasping the objects with irregular shapes. The experimental test approves the significant performance of the gripper in term of grasping complex shape objects.

关键词： Grippers Grasping Flexible printed circuits Robot sensing systems Shape Kalman filters

Minimum uncertainty latent variable models for robot recognition of sequential human activities

学校读者我要写书评

暂无评论

Minimum uncertainty latent variable models for robot recogni...

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Han, Fei Reardon, Christopher Parker, Lynne E. Zhang, Hao Human-Centered Robotics Lab Department of Computer Science Colorado School of Mines GoldenCO80401 United States US Army Research Laboratory AdelphiMD20783 United States Distributed Intelligence Laboratory Department of Electrical Engineering and Computer Science University of Tennessee TN37996 United States

ISBN: (纸本)9781509046331

Recognition of sequential human activities, such as 'sitting down' and 'standing up', is a common but challenging problem in human-robot interaction, which requires modeling their underlying temporal patterns. Although previous sequence modeling methods, such as Hidden Conditional Random Fields (HCRFs), demonstrated satisfactory recognition accuracy, they do not explicitly model the uncertainty in underlying temporal patterns, which can provide valuable information to characterize sequential activities. To address this problem, we introduce a novel Minimum Uncertainty HCRF (MU, or μHCRF). Different from traditional HCRF-based techniques that only utilize the negative log-likelihood of the categories' conditional probability as the loss function, the proposed μ-HCRF also introduces a regularization term to model the underlying temporal pattern of the latent variables. As another theoretical contribution, we provide a derivation to show that the formulated problem has a closed-form solution, and prove that inference of the proposed μHCRF is tractable. Extensive empirical study is performed to evaluate our approach, using four public benchmark datasets. Experimental results have shown that our μHCRFs outperform previous techniques and achieve state-of-the-art performance on human activity recognition, especially on sequential activities. © 2017 IEEE.

关键词： Human robot interaction

Pose estimation of periacetabular osteotomy fragments with intraoperative x-ray navigation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Grupp, Robert B. Hegeman, Rachel A. Murphy, Ryan J. Alexander, Clayton P. Otake, Yoshito McArthur, Benjamin A. Armand, Mehran Taylor, Russell H. Department of Computer Science Johns Hopkins University BaltimoreMD United States Research and Exploratory Development Department Johns Hopkins University Applied Physics Laboratory LaurelMD United States Research and Exploratory Development Department Johns Hopkins University Applied Physics Laboratory Auris Surgical Robotics LaurelMD United States Department of Orthopaedic Surgery Johns Hopkins Medicine BaltimoreMD United States Nara Japan Washington Orthopedics and Sports Medicine Chevy ChaseMD United States Dell Medical School University of Texas AustinTX United States Texas Orthopedics AustinTX United States Research and Exploratory Development Department Johns Hopkins University Applied Physics Laboratory LaurelMD United States Department of Mechanical Engineering Johns Hopkins University BaltimoreMD United States

Objective: State of the art navigation systems for pelvic osteotomies use optical systems with external fiducials. We propose the use of X-Ray navigation for pose estimation of periacetabular fragments without fiducials. Methods: A 2D/3D registration pipeline was developed to recover fragment pose. This pipeline was tested through an extensive simulation study and 6 cadaveric surgeries. Using osteotomy boundaries in the fluoroscopic images, the preoperative plan is refined to more accurately match the intraoperative shape. Results: In simulation, average fragment pose errors were 1.3°/1.7 mm when the planned fragment matched the intraoperative fragment, 2.2°/2.1 mm when the plan was not updated to match the true shape, and 1.9°/2.0 mm when the fragment shape was intraoperatively estimated. In cadaver experiments, the average pose errors were 2.2°/2.2 mm, 3.8°/2.5 mm, and 3.5°/2.2 mm when registering with the actual fragment shape, a preoperative plan, and an intraoperatively refined plan, respectively. Average errors of the lateral center edge angle were less than 2° for all fragment shapes in simulation and cadaver experiments. Conclusion: The proposed pipeline is capable of accurately reporting femoral head coverage within a range clinically identified for long-term joint survivability. Significance: Human interpretation of fragment Copyright © 2019, The Authors. All rights reserved.

关键词： Pipelines

Mobile robot localisation and navigation using LEGO NXT and ultrasonic sensor

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Yanan Fan, Rui Yu, Bin Junaid Bocus, M. Liu, Ming Ni, Hepeng Fan, Jiahe Mao, Shixin Bristol Robotics Laboratory University of Bristol Bristol United Kingdom Robotics and Multi-Perception Laboratory Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Electrical and Electronic Engineering University of Bristol BristolBS8 1UB United Kingdom School of Mechanical Engineering Shandong University Jinan250061 China School of Communication Engineering Jilin University Changchun130000 China Shenzhen Sanhang Industrial Technology Research Institute Shenzhen518000 China

Mobile robots are becoming increasingly important both for individuals and industries. Mobile robotic technology is not only utilised by experts in this field but is also very popular among amateurs. However, implementing a mobile robot to perform tasks autonomously can be expensive because of the need for various types of sensors and the high price of robot platforms. Hence, in this paper we present a mobile robot localisation and navigation system which uses a LEGO ultrasonic sensor in an indoor map based on the LEGO MINDSTORM NXT. This provides an affordable and ready-to-use option for most robot fans. In this paper, an effective method is proposed to extract useful information from the distorted readings collected by the ultrasonic sensor. Then, the particle filter is used to localise the robot. After robot's position is estimated, a sampling-based path planning method is proposed for the robot navigation. This method reduces the robot accumulative motion error by minimising robot turning times and covering distances. The robot localisation and navigation algorithms are implemented in MATLAB. Simulation results show an average accuracy between 1 and 3 cm for three different indoor map locations. Furthermore, experiments performed in a real setup show the effectiveness of the proposed methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Mobile robots

The dynamic interactions between chemotherapy drugs and plasmid DNA investigated by atomic force microscopy

学校读者我要写书评

暂无评论

Science China Materials 2017年第3期60卷 269-278页

作者：李密刘连庆肖秀斌席宁王越超 State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Department of Lymphoma Affiliated Hospital of Military Medical Academy of Sciences Department of Electrical and Computer Engineering Michigan State University

The advent of atomic force microscopy （AFM） provides a powerful tool for imaging individual DNA molecules. Chemotherapy drugs are often related to DNAs. Though many specific drug-DNA interactions have been observed by AFM, knowledge about the dynamic interactions between chemotherapy drugs and plasmid DNAs is still scarce. In this work, AFM was applied to investigate the nanoscale interactions between plasmid DNAs and two commercial chemotherapy drugs （methotrexate and cisplatin）. Plasmid DNAs were immobilized on mica which was coated by silanes in advance. AFM imaging distinctly revealed the dynamic changes of single plasmid DNAs after the stimulation of methotrexate and cisplatin. Geometric features of plasmid DNAs were extracted from AFM images and the statistical results showed that the geometric features of plasmid DNAs changed significantly after the stimulation of drugs. This research provides a novel idea to study the actions of chemotherapy drugs against plasmid DNAs at the single-molecule level.

关键词： atomic force microscopy plasmid DNA drug methotrexate cisplatin

Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wagner, Martin Müller-Stich, Beat-Peter Kisilenko, Anna Tran, Duc Heger, Patrick Mündermann, Lars Lubotsky, David M. Müller, Benjamin Davitashvili, Tornike Capek, Manuela Reinke, Annika Yu, Tong Vardazaryan, Armine Innocent Nwoye, Chinedu Padoy, Nicolas Liu, Xinyang Lee, Eung-Joo Disch, Constantin Meine, Hans Xia, Tong Jia, Fucang Kondo, Satoshi Reiter, Wolfgang Jin, Yueming Long, Yonghao Jiang, Meirui Dou, Qi Heng, Pheng Ann Twick, Isabell Kirtac, Kadir Hosgor, Enes Bolmgren, Jon Lindström Stenzel, Michael von Siemens, Björn Kenngott, Hannes G. Nickel, Felix von Frankenberg, Moritz Mathis-Ullrich, Franziska Maier-Hein, Lena Speidel, Stefanie Bodenstedt, Sebastian Department for General Visceral and Transplantation Surgery Heidelberg University Hospital Im Neuenheimer Feld 420 Heidelberg69120 Germany Heidelberg Im Neuenheimer Feld 460 Heidelberg69120 Germany Data Assisted Solutions Corporate Research & Technology KARL STORZ SE & Co. KG Dr. Karl-Storz-Str. 34 Tuttlingen78332 Germany Im Neuenheimer Feld 223 Heidelberg69120 Germany Im Neuenheimer Feld 223 Heidelberg69120 Germany Faculty of Mathematics and Computer Science Heidelberg University Im Neuenheimer Feld 205 Heidelberg69120 Germany ICube University of Strasbourg CNRS France 300 bd Sébastien Brant - CS 10413 Illkirch CedexF-67412 France IHU Strasbourg France 1 Place de l'hôpital Strasbourg67000 France Sheikh Zayed Institute for Pediatric Surgical Innovation Children's National Hospital 111 Michigan Ave NW WashingtonDC20010 United States University of Maryland College Park 2405 A V Williams Building College ParkMD20742 United States Fraunhofer Institute for Digital Medicine MEVIS Max-von-Laue-Str. 2 Bremen28359 Germany University of Bremen FB3 Medical Image Computing Group ℅ Fraunhofer MEVIS Am Fallturm 1 Bremen28359 Germany Lab for Medical Imaging and Digital Surgery Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Konika Minolta Inc. JP TOWER 2-7-2 Marunouchi Chiyoda-ku Tokyo100-7015 Japan Wintegral GmbH Ehrenbreitsteiner Str. 36 München80993 Germany Department of Computer Science and Engineering Ho Sin-Hang Engineering Building The Chinese University of Hong Kong Sha Tin NT Hong Kong Caresyntax GmbH Komturstr. 18A Berlin12099 Germany Department of Surgery Salem Hospital of the Evangelische Stadtmission Heidelberg Zeppelinstrasse 11-33 Heidelberg69121 Germany Health Robotics and Automation Laboratory Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Geb. 40.28 KIT Campus Süd Engler-Bunte-Ring 8 Karlsruhe76131 Germany Medical Faculty Heidelberg Uni

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center video dataset. In this work we investigated the generalizability of phase recognition algorithms in a multi-center setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 hours was created. Labels included framewise annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 international Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 research teams trained and submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n=9 teams), for instrument presence detection between 38.5% and 63.8% (n=8 teams), but for action recognition only between 21.8% and 23.3% (n=5 teams). The average absolute error for skill assessment was 0.78 (n=1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but are not solved yet, as shown by our comparison of machine learning algorithms. This novel HeiChole benchmark can be used for comparable evaluation and validation of future work. In future studies, it is of utmost impo

关键词： Learning algorithms

Relaxed conditions for uniform complete observability and controllability of LTV systems with bounded realizations

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 3598-3605页

作者： Batista P. Petit N. Silvestre C. Oliveira P. Institute for Systems and Robotics Laboratory for Robotics and Engineering Systems Instituto Superior Técnico Universidade de Lisboa Portugal MINES ParisTech PSL Research University CAS – Centre automatique et systémes 60 bd St Michel Paris 75272 France Department of Electrical and Computer Engineering Faculty of Science and Technology of the University of Macau Macau Department of Mechanical Engineering Instituto Superior Técnico Universidade de Lisboa Portugal

Uniform complete observability and controllability are key concepts for the design of state observers and controllers for linear time-varying systems. While the definitions of these properties are simple, it is more often that not very difficult to show they hold for a particular system. This paper presents alternative simpler sufficient conditions. Examples are shown that illustrate the improvement over previous results, the fact that the new conditions are not necessary, and a practical application. © 2017

关键词： linear time-varying systems uniform complete controllability uniform complete observability