检索结果-内蒙古大学图书馆

Statistical Methods in Video Processing 1

丛书名： Lecture Notes in computer Science

1000年

作者： Dorin Comaniciu Rudolf Mester Kenichi Kanatani David Suter

ISBN: (数字)9783540302124

ISBN: (纸本)9783540239895

The 2nd International Workshop on Statistical Methods in Video Processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on computer vision. A total of 30 papers were submitted to the workshop. Of these, 17 papers were accepted for presentation and included in these proceedings, following a double-blind review process. The workshop had 42 registered participants. The focus of the meeting was on recent progress in the application of - vanced statistical methods to solve computer vision tasks. The one-day scienti?c program covered areas of high interest in vision research, such as dense rec- struction of 3D scenes, multibody motion segmentation, 3D shape inference, errors-in-variables estimation, probabilistic tracking, information fusion, optical ?owcomputation,learningfornonstationaryvideodata,noveltydetectionin- namic backgrounds, background modeling, grouping using feature uncertainty, and crowd segmentation from video. We wish to thank the authors of all submitted papers for their interest in the *** external reviewers for their commitment of time and e?ort in providing valuable recommendations for each submission. We are thankful to Vaclav Hlavac, the General Chair of ECCV 2004, and to Radim Sara, for the local organization of the workshop and registration management. We hope you will ?nd these proceedings both inspiring and of high scienti?c quality.

关键词： Image Processing and computer vision computer Graphics Pattern Recognition Probability and Statistics in computer Science Artificial Intelligence Algorithm Analysis and Problem Complexity

来源：评论

学校读者我要写书评

暂无评论

Learning Predictive State Representations for planning

Learning Predictive State Representations for planning

引用

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： J. A. Stork C. H. Ek D. Kragic Computer Vision and Active Perception Lab Centre for Autonomous Systems KTH Royal Institute of Technology Stockholm Sweden Computer Vision and Active Perception Lab Centre for Autonomous Systems School of Computer Science and Communication KTH Royal Institute of Technology Stockholm Sweden

Predictive State Representations (PSRs) allow modeling of dynamical systems directly in observables and without relying on latent variable representations. A problem that arises from learning PSRs is that it is often hard to attribute semantic meaning to the learned representation. This makes generalization and planning in PSRs challenging. In this paper, we extend PSRs and introduce the notion of PSRs that include prior information (P-PSRs) to learn representations which are suitable for planning and interpretation. By learning a low-dimensional embedding of test features we map belief points of similar semantic to the same region of a subspace. This facilitates better generalization for planning and semantical interpretation of the learned representation. In specific, we show how to overcome the training sample bias and introduce feature selection such that the resulting representation emphasizes observables related to the planning task. We show that our P-PSRs result in qualitatively meaningful representations and present quantitative results that indicate improved suitability for planning.

关键词： Planning History Robots Semantics Predictive models Uncertainty

来源：评论

学校读者我要写书评

暂无评论

RayNet: Learning volumetric 3d reconstruction with ray potentials

arXiv

引用

arXiv 2019年

作者： Paschalidou, Despoina Ulusoy, Ali Osman Schmitt, Carolin Van Gool, Luc Geiger, Andreas Autonomous Vision Group MPI for Intelligent Systems Tübingen Microsoft Computer Vision Lab ETH Zürich KU Leuven Computer Vision and Geometry Group ETH Zürich Max Planck ETH Center for Learning Systems

In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Adaptive control for pivoting with visual and tactile feedback

Adaptive control for pivoting with visual and tactile feedba...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Francisco E. Viña B. Yiannis Karayiannidis Christian Smith Danica Kragic Computer Vision and Active Perception Lab. Centre for Autonomous Systems School of Computer Science and Communication Royal Institute of Technology KTH Stockholm Sweden Computer Vision and Active Perception Lab. Centre for Autonomous Systems School of Computer Science and Communication Chalmers University of Technology Sweden Computer Vision and Active Perception Lab. Centre for Autonomous Systems School of Computer Science and Communication Royal Institute of Technology KTH Sweden

In this work we present an adaptive control approach for pivoting, which is an in-hand manipulation maneuver that consists of rotating a grasped object to a desired orientation relative to the robot's hand. We perform pivoting by means of gravity, allowing the object to rotate between the fingers of a one degree of freedom gripper and controlling the gripping force to ensure that the object follows a reference trajectory and arrives at the desired angular position. We use a visual pose estimation system to track the pose of the object and force measurements from tactile sensors to control the gripping force. The adaptive controller employs an update law that accommodates for errors in the friction coefficient, which is one of the most common sources of uncertainty in manipulation. Our experiments confirm that the proposed adaptive controller successfully pivots a grasped object in the presence of uncertainty in the object's friction parameters.

关键词： Friction Force Grippers Robot kinematics Planning Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Curvature oriented clustering of sparse motion vector fields

Curvature oriented clustering of sparse motion vector fields

引用

2012 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2012

作者： Guevara, Alvaro Conrad, Christian Mester, Rudolf Section of Systems Neuroscience Technische Universität Dresden Germany Lab. J.W.Goethe-Universität Frankfurt Germany Computer Vision Laboratory EE Dept. Linköping University Sweden

ISBN: (纸本)9781467318303

We present an approach to unveil the underlying structure of dynamic scenes from a sparse set of local flow measurements. We first estimate those measurements at carefully selected locations, and subsequently group them into a finite set of different dense flow field hypotheses. These flow fields are represented as parametric functional models, and the number of flow models (=clusters) is determined by an information-theory based approach. Methodically, the grouping task is a two-step clustering scheme, whose intra-cluster modeling step exploits prior knowledge on real flow fields by enforcing low curvature, and the individual covariance matrices of the sparse local flow measurements are introduced in a principled way. The method has been tested successfully on both stereo and general motion sequences from the standard Middlebury database. © 2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

From object categories to grasp transfer using probabilistic reasoning

From object categories to grasp transfer using probabilistic...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Marianna Madry Dan Song Danica Kragic Computer Vision and Active Perception Lab Center for Autonomous Systems KTH Royal Institute of Technology Sweden

In this paper we address the problem of grasp generation and grasp transfer between objects using categorical knowledge. The system is built upon an i) active scene segmentation module, able of generating object hypotheses and segmenting them from the background in real time, ii) object categorization system using integration of 2D and 3D cues, and iii) probabilistic grasp reasoning system. Individual object hypotheses are first generated, categorized and then used as the input to a grasp generation and transfer system that encodes task, object and action properties. The experimental evaluation compares individual 2D and 3D categorization approaches with the integrated system, and it demonstrates the usefulness of the categorization in task-based grasping and grasp transfer.

关键词： Cognition Robots Kernel

来源：评论

学校读者我要写书评

暂无评论

Infrastructure-based calibration of a multi-camera rig

Infrastructure-based calibration of a multi-camera rig

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Lionel Heng Mathias Bürki Gim Hee Lee Paul Furgale Roland Siegwart Marc Pollefeys Computer Vision and Geometry Lab ETH Zürich Switzerland Autonomous Systems Lab Zürich ETH Switzerland

The online recalibration of multi-sensor systems is a fundamental problem that must be solved before complex automated systems are deployed in situations such as automated driving. In such situations, accurate knowledge of calibration parameters is critical for the safe operation of automated systems. However, most existing calibration methods for multisensor systems are computationally expensive, use installations of known fiducial patterns, and require expert supervision. We propose an alternative approach called infrastructure-based calibration that is efficient, requires no modification of the infrastructure, and is completely unsupervised. In a survey phase, a computationally expensive simultaneous localization and mapping (SLAM) method is used to build a highly accurate map of a calibration area. Once the map is built, many other vehicles are able to use it for calibration as if it were a known fiducial pattern. We demonstrate the effectiveness of this method to calibrate the extrinsic parameters of a multi-camera system. The method does not assume that the cameras have an overlapping field of view and it does not require an initial guess. As the camera rig moves through the previously mapped area, we match features between each set of synchronized camera images and the map. Subsequently, we find the camera poses and inlier 2D-3D correspondences. From the camera poses, we obtain an initial estimate of the camera extrinsics and rig poses, and optimize these extrinsics and rig poses via non-linear refinement. The calibration code is publicly available as a standalone C++ package.

关键词： Cameras Calibration Transforms Three-dimensional displays Computational modeling Vehicles Accuracy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Force/Velocity control for opening unknown doors 1

引用

IFAC Proceedings Volumes 2012年第22期45卷 753-758页

作者： Yiannis Karayiannidis Christian Smith Petter Ögren Danica Kragic Computer Vision and Active Perception Lab. Centre for Autonomous Systems School of Computer Science and Communication Royal Institute of Technology (KTH) SE-100 44 Stockholm Sweden

The problem of door opening is fundamental for robots operating in domestic environments. Since these environments are generally unstructured, a robot must deal with several types of uncertainties associated with the dynamics and kinematics of a door to achieve successful opening. The present paper proposes a dynamic force/velocity controller which uses adaptive estimation of the radial direction based on adaptive estimates of the door hinge's position. The control action is decomposed into estimated radial and tangential directions, which are proved to converge to the corresponding actual values. The force controller uses reactive compensation of the tangential forces and regulates the radial force to a desired small value, while the velocity controller ensures that the robot's end-effector moves with a desired tangential velocity. The performance of the control scheme is demonstrated in simulation with a 2 DoF planar manipulator opening a door.

关键词： door opening force/velocity control adaptive estimation

来源：评论

学校读者我要写书评

暂无评论

Object Finding in Cluttered Scenes Using Interactive Perception

Object Finding in Cluttered Scenes Using Interactive Percept...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Tonci Novkovic Remi Pautrat Fadri Furrer Michel Breyer Roland Siegwart Juan Nieto Autonomous Systems Lab ETH Zurich Switzerland Computer Vision and Geometry Group ETH Zurich Switzerland

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Object finding in clutter is a skill that requires perception of the environment and in many cases physical interaction. In robotics, interactive perception defines a set of algorithms that leverage actions to improve the perception of the environment, and vice versa use perception to guide the next action. Scene interactions are difficult to model, therefore, most of the current systems use predefined heuristics. This limits their ability to efficiently search for the target object in a complex environment. In order to remove heuristics and the need for explicit models of the interactions, in this work we propose a reinforcement learning based active and interactive perception system for scene exploration and object search. We evaluate our work both in simulated and in real-world experiments using a robotic manipulator equipped with an RGB and a depth camera, and compare our system to two baselines. The results indicate that our approach, trained in simulation only, transfers smoothly to reality and can solve the object finding task efficiently and with more than 88% success rate.

关键词： Cameras Task analysis Robot sensing systems Search problems Clutter Detectors

来源：评论

学校读者我要写书评

暂无评论

Estimating the Deformability of Elastic Materials using Optical Flow and Position-based Dynamics

Estimating the Deformability of Elastic Materials using Opti...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Puren Guler Karl Pauwels Alessandro Pieropan Hedvig Kjellstrom Danica Kragic Computer Vision and Active Perception Lab Center for Autonomous Systems School of Computer Science and Communication KTH Royal Institute of Technology

ISBN: (纸本)9781479968862

Knowledge of the physical properties of objects is essential in a wide range of robotic manipulation scenarios. A robot may not always be aware of such properties prior to interaction. If an object is incorrectly assumed to be rigid, it may exhibit unpredictable behavior when grasped. In this paper, we use vision based observation of the behavior of an object a robot is interacting with and use it as the basis for estimation of its elastic deformability. This is estimated in a local region around the interaction point using a physics simulator. We use optical flow to estimate the parameters of a position-based dynamics simulation using meshless shape matching (MSM). MSM has been widely used in computer graphics due to its computational efficiency, which is also important for closed-loop control in robotics. In a controlled experiment we demonstrate that our method can qualitatively estimate the physical properties of objects with different degrees of deformability.

关键词： Deformability Optic Flow Unpredictable behavior physical properties elastic materials Behavior Observation Techniques Robot kinetic simulation computer GRAPHICS MSM Computational efficiency robotics

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：