检索结果-内蒙古大学图书馆

SIFT texture description for understanding breast ultrasound images

12th International Workshop on Breast Imaging, IWDM 2014

作者： Massich, Joan Meriaudeau, Fabrice Sentís, Melcior Ganau, Sergi Pérez, Elsa Puig, Domenec Martí, Robert Oliver, Arnau Martí, Joan Computer Vision and Robotics Group University of Girona Spain Laboratoire Le2i-UMR CNRS University of Burgundy Le Creusot France Department of Breast and Gynecological Radiology UDIAT-Diagnostic Center Parc Taulí Corporation Sabadell Spain Department of Radiology Hospital Josep Trueta of Girona Spain Department of Computer Engineering and Mathematics University Rovira I Virgili Tarragona Spain

ISBN: (纸本)9783319078861

Texture is a powerful cue for describing structures that show a high degree of similarity in their image intensity patterns. This paper describes the use of Self-Invariant Feature Transform (SIFT), both as low-level and high-level descriptors, applied to differentiate the tissues present in breast US images. For the low-level texture descriptors case, SIFT descriptors are extracted from a regular grid. The high-level texture descriptor is build as a Bag-of-Features (BoF) of SIFT descriptors. Experimental results are provided showing the validity of the proposed approach for describing the tissues in breast US images. © 2014 Springer International Publishing.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Online discovery of AUV control policies to overcome thruster failures

Online discovery of AUV control policies to overcome thruste...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Seyed Reza Ahmadzadeh Matteo Leonetti Arnau Carrera Marc Carreras Petar Kormushev Darwin G. Caldwell Department of Advanced Robotics Istituto Italiano di Tecnologia Genova Italy Department of Computer Science The University of Texas at Austin Austin TX Computer Vision and Robotics Group (VICOROB) University of Girona Girona Spain

We investigate methods to improve fault-tolerance of Autonomous Underwater Vehicles (AUVs) to increase their reliability and persistent autonomy. We propose a learning-based approach that is able to discover new control policies to overcome thruster failures as they happen. The proposed approach is a model-based direct policy search that learns on an on-board simulated model of the AUV. The model is adapted to a new condition when a fault is detected and isolated. Since the approach generates an optimal trajectory, the learned fault-tolerant policy is able to navigate the AUV towards a specified target with minimum cost. Finally, the learned policy is executed on the real robot in a closed-loop using the state feedback of the AUV. Unlike most existing methods which rely on the redundancy of thrusters, our approach is also applicable when the AUV becomes under-actuated in the presence of a fault. To validate the feasibility and efficiency of the presented approach, we evaluate it with three learning algorithms and three policy representations with increasing complexity. The proposed method is tested on a real AUV, Girona500.

关键词： Optimization Trajectory Vectors Vehicles Robots Fault tolerance Fault tolerant systems

来源：评论

学校读者我要写书评

暂无评论

Latent Space Policy Search for robotics

Latent Space Policy Search for Robotics

引用

IEEE/RSJ International Conference on intelligent Robots and Systems

作者： Kevin Sebastian Luck Gerhard Neumann Erik Berger Jan Peters Heni Ben Amor Department of Computer Science Technische Universitat Darmstadt 64289 Darmstadt Germany Department of Mathematics and Computer Science Technische Universitat Bergakademie Freiberg 09599 Freiberg Germany Institute for Robotics and Intelligent Machines Georgia Institute of Technology GA 30332 USA

ISBN: (纸本)9781479969357

Learning motor skills for robots is a hard task. In particular, a high number of degrees-of-freedom in the robot can pose serious challenges to existing reinforcement learning methods, since it leads to a high-dimensional search space. However, complex robots are often intrinsically redundant systems and, therefore, can be controlled using a latent manifold of much smaller dimensionality. In this paper, we present a novel policy search method that performs efficient reinforcement learning by uncovering the low-dimensional latent space of actuator redundancies. In contrast to previous attempts at combining reinforcement learning and dimensionality reduction, our approach does not perform dimensionality reduction as a preprocessing step but naturally combines it with policy search. Our evaluations show that the new approach outperforms existing algorithms for learning motor skills with high-dimensional robots.

关键词： Robots Aerospace electronics Mathematical model Learning (artificial intelligence) Vectors Equations Joints

来源：评论

学校读者我要写书评

暂无评论

Opening remarks

2016 International Conference on Advances in Human Machine I...

引用

2016 International Conference on Advances in Human Machine Interaction, HMI 2016 2016年

作者： Nagaraja, Ch. Swamy, J. Nagendra Rajendra, J. Khan, M.S. Vishwanath Reddy, D.S. Manjunath, N. Dillmann, Ruediger Tarn, Tzyh Jong Zhao, Qianchuan Ammi, Mehdi Zuberek, Wlodek M. Sandhu, P.S. Patthira Newman, K. De Silva Liyanage, Chandratilak Hassan, Sohair Aly Aly Sun, Kien Wen Rahman, Md. Moshiur Ordoño, E. Evangelista Sharma, R.K. Mishra, Preeti Chandel, B.S. Singla, Ekta Petric, Tadej Zhong, Yu Jiglar, Janson Alemzadeh, Kazem Asokan, T. Tripathi, Animesh Tripathi, Manoj Ram, Swaminath Shrma, M.K. Panday, P.N. Kumar, Devendra Hinchey, Mike Stilman, Boris Suraj, Zbigniew Pal, Sankar K. Sasi, Sreela Rajan, Deepu Marshall, Roger G. Abraham, Ajith Peter S, David Paul, Vargheese Gopakumar, V. Dustdar, Schahram Soto, Sebastián Ventura Rausch, Andreas Angelis, Lefteris Nelson, Andrew L. Botzheim, Janos Bernardino, Heder Soares Zboril, Frantisek Ane, Bernadetta Kwintiana Maeda, Toshiyuki Sakalauskas, Virgilijus Hann, Garenth Lim King Samek, Jan Romero Salguero, José Raúl Varghese, Kuruvilla Kriksciuniene, Dalia Mathew, Jimson Reif, Wolfgang Mauri, Giancarlo Cabrerizo Lorite, Francisco Javier Özcan, Ender Cho, Sung-Bae Paily, Roy P. Rezankova, Hana Tudjarov, Boris Hong, Wei-Chiang De Oliveira, José Valente Flores Romero, Juan Jose Oskouei, Rozita Jamili Cicchetti, Antonio Roy, Chanchal Segura, Sergio Samuel, C. Mallet, Frédéric Mernik, Marjan Punnekkat, Sasikumar Waseemulla, A. Sri Devaraj Urs Educational Trust Bangalore India R. L. Jalappa Institute of Technology Doddaballapur Bangalore India Humanoids and Intelligence Systems Lab Kalsruhe Germany Electrical and Systems Engineering Washington University in St. Louis United States Deputy Director of Center for Intelligent and Networked Systems Department of Automation Tsinghua University Beijing China Department of Computer Science CNRS/LIMSI Lab AMI Group France Memorial University St. John'sNL Canada RBIT and Bio-Technology India LR University Thailand University of Colorado at Boulder Boulder United States Faculty of Science University of Brunei Brunei University of Kuala Lumpur Malaysia National Chiao Tung University Taiwan EPR Centre Bangladesh Mapua Institute of Technology Philippines ARO CWC Lucknow India Mpec Kanpur India DSC DBS Kanpu India Indian Institute of Technology Ropar India Jozaf Stefan Institute Department of Automation Biocyernetics and Robotics Ljubljana Slovenia Robotics Institute Carnegie Mellon University Pittsburgh United States Faculty of Engineering University of Bristol United Kingdom Department of Engineering Design Indian Institute of Technology Madras India Lucknow Uni Lucknow India CSJM Uni Kanpur India UPPCB Lucknow India PCB Roorkee India Awadh Uni Faijabad India Agra Uni Agra India Lero University of Limerick Ireland University of Colorado Denver United States University of Rzeszow Poland Indian Statistical Institute Kolkata India Gannon University PA United States Nanyang Technical University Singapore Singapore Plymouth State University NH United States MIR Labs United States Cochin University of Science and Technology India State Project Facilitation Unit TEQIP Kerala India Technical University of Vienna Austria University of Cordoba Spain Clausthal University of Technology Germany Aristotle University of Thessaloniki Greece Androtics LLC TucsonAZ United States Tokyo Metropolitan University Japan Federal Unive

来源：评论

学校读者我要写书评

暂无评论

Visual landmark selection for mobile robot navigation

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2013年第3期40卷 134-142页

作者： Gorbenko, Anna Popov, Vladimir Ural Federal University Department of Intelligent Systems Robotics of Mathematics and Computer Science Institute 620083 Ekaterinburg Russia

A large number of landmarks selection techniques has been proposed. However, finding optimal solutions requires to solve some hard problems. In this paper, we consider the P- minimum overlapping region decomposition problem that was proposed for landmarks selection. This problem is NP-complete. We describe an approach to solve the problem optimally. This approach is based on an explicit reduction from the problem to the satisfiability problem. Also, we consider some greedy algorithms for solution of the problem.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

On the constrained longest common subsequence problem

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2013年第4期40卷 266-273页

作者： Gorbenko, Anna Ural Federal University Department of Intelligent Systems Robotics of Mathematics and Computer Science Institute 620083 Ekaterinburg Russia

The problem of the longest common subsequence is a classical distance measure for strings. There have been several attempts to accommodate longest common subsequences along with some other distance measures. There are a large number of different variants of the problem. In this paper, we consider the constrained longest common subsequence problem for two strings and arbitrary number of constraints. In particular, we consider an explicit reduction from the problem to the satisfiability problem and present experimental results for different satisfiability algorithms. It should be noted that different regularities in experimentally obtained data reveal important information about the underlying physical system. In this paper, we consider the problem of systematic monitoring of passenger flows. In particular, we use constrained longest common subsequences for tracking the image features.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards Practical Visual Servoing in robotics

Towards Practical Visual Servoing in Robotics

引用

Canadian Conference on computer and Robot vision, CRV

作者： Romeo Tatsambon Fomena Camilo Perez Quintero Mona Gridseth Martin Jagersand Computer Vision and Robotics Research Group Department of Computing Science University of Alberta Edmonton AB Canada

ISBN: (纸本)9781467364096

Visual servoing was introduced in robotics nearly 4 decades ago. However until now, there are still only a handful of known examples of application of this technique in addressing real word robotics problems such as disaster response, assistance for elderly or handicapped people, etc. As the world is moving towards the use of robotics to improve quality of life, it is time to assess the challenges involved in applying visual servoing to solve real world problems. This paper presents an overview of these challenges, by asking the question what are the missing components for practical visual servoing? and by providing practical possible solutions for these components. Illustration of these challenges and our current practical solutions are given using our 7-DoFs Barrett WAM Arm.

关键词： Visual servoing Visualization Cameras Target tracking Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Multi-robot forest coverage for unweighted terrain

引用

AIP Conference Proceedings 2013年第1期1558卷 2083-2086页

作者： Vladimir Popov Ural Federal University Department of Intelligent Systems and Robotics Mathematics and Computer Science Institute Lenin st. 51 620083 Ekaterinburg Russia

Different planning problems for mobile robots are of considerable interest for many years. Frequently, such problems require to solve different hard computational problems. Multi-robot forest coverage is one of such computational problems. In this paper, we consider an efficient approach to solve the problem of multi-robot forest coverage for unweighted terrain. In particular, we consider an explicit reduction from the decision version of the problem of multi-robot forest coverage for unweighted terrain to the satisfiability problem. For different satisfiability algorithms, the results of computational experiments are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Process Model Parameterisation in Posegraphs

Process Model Parameterisation in Posegraphs

引用

American Control Conference

作者： Simon J. Julier Zhaojie Ju Department of Computer Science University College London UK S Intelligent Systems and Biomedical Robotics Group at the University of Portsmouth UK

ISBN: (纸本)9781479901777

Through propagating information over time, process models serve a vital in any multi-time step estimation algorithm. However, they can introduce nonlinearities which can significantly degrade the performance of an estimator. In this paper, we investigate the impact of the parameter-isation of the process model in posegraph-based formulations of filtering and estimation algorithms. Exploiting the flexibility and conditional independence structure of a posegraph, we develop two formulations of a process noise model of a vehicle - one in Euclidean space, the other in polar space. Using moment-matching, we develop exact closed form solutions for the first two moments of a Gaussian distribution propagated through both models. We analyse the effects of both formulations in the context of a Simultaneous Localisation and Mapping (SLAM) problem. We show that, by representing the "arc-like" nature of the prediction error more accurately, the polar form is more accurate, more robust, and is less computationally expensive than the Euclidean form.

关键词： process prediction Euclidean Euclidean procedural model parameterization Gaussian distribution simultaneous localization and mapping Conditional Independence Euclidean space Error of prediction nonlinearity Filtration

来源：评论

学校读者我要写书评

暂无评论

Fast and robust landmark tracking in x-ray locomotion sequences containing severe occlusions

Fast and robust landmark tracking in x-ray locomotion sequen...

引用

17th Annual Workshop on vision, Modeling and Visualization, VMV 2012

作者： Amthor, M. Haase, D. Denzler, J. Computer Vision Group Department of Mathematics and Computer Science Friedrich Schiller University of Jena Germany

ISBN: (纸本)9783905673951

Recent advances in the understanding of animal locomotion have proven it to be a key element of many fields in biology, motion science, and robotics. For the analysis of walking animals, high-speed x-ray videography isemployed. For a biological evaluation of these x-ray sequences, anatomical landmarks have to be located in each frame. However, due to the motion of the animals, severe occlusions complicate this task and standard tracking methods can not be applied. We present a robust tracking approach which is based on the idea of dividing a template into sub-templates to overcome occlusions. The difference to other sub-template approaches is that we allow soft decisions for the fusion of the single hypotheses, which greatly benefits tracking stability. Also, we show how anatomical knowledge can be included into the tracking process to further improve the performance. Experiments on real datasets show that our method achieves results superior to those of existing robust approaches. © 2012 The Eurographics Association.

关键词： Animals

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：