检索结果-内蒙古大学图书馆

OCEANS'08 MTS/IEEE Kobe-Techno-Ocean'08 - Voyage toward the Future, OTO'08

作者： Nicosevici, Tudor Garcia, Rafael Computer Vision and Robotics Group University of Girona Spain

ISBN: (纸本)9781424421268

This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential Structure from Motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene. ©2008 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards detecting changes in underwater image sequences

Towards detecting changes in underwater image sequences

引用

OCEANS'08 MTS/IEEE Kobe-Techno-Ocean'08 - Voyage toward the Future, OTO'08

作者： Delaunoy, Olivier Gracias, Nuno Garcia, Rafael Computer Vision and Robotics Group University of Girona 17071 Spain

ISBN: (纸本)9781424421268

Detecting changes between images of the same scene taken at different times is of great interest for monitoring and understanding the environment. It is widely used for on-land application but suffers from different constraints. Unfortunately, Change detection algorithms require highly accurate geometric and photometric registration. This requirement has precluded their use in underwater imagery in the past. In this paper, the change detection techniques available nowadays for on-land application were analyzed and a method to automatically detect the changes in sequences of underwater images is proposed. Target application scenarios are habitat restoration sites, or area monitoring after sudden impacts from hurricanes or ship groundings. The method is based on the creation of a 3D terrain model from one image sequence over an area of interest. This model allows for synthesizing textured views that correspond to the same viewpoints of a second image sequence. The generated views are photometrically matched and corrected against the corresponding frames from the second sequence. Standard change detection techniques are then applied to find areas of difference. Additionally, the paper shows that it is possible to detect false positives, resulting from non-rigid objects, by applying the same change detection method to the first sequence exclusively. The developed method was able to correctly find the changes between two challenging sequences of images from a coral reef taken one year apart and acquired with two different cameras. ©2008 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Applications of High Precision Imaging Polarimetry

Applications of High Precision Imaging Polarimetry

引用

4th International Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging, CAe 2008

作者： Neumann, L. Hegedus, R. Horvath, G. Garcia, R. Computer Vision and Robotics Group University of Girona Icrea Spain Department of Biological Physics Biooptics Laboratory Eötvös University Budapest Hungary Computer Vision and Robotics Group University of Girona Spain

ISBN: (纸本)9783905674088

We propose the use of imaging polarimetry for general photography, which is a relatively young technique allowing the determination of polarized components of the light coming from extended objects or scenes. In this paper high resolution and accurate methods are introduced to determine the two linearly polarized components (Q;U) of light. The CIE Luv color space is used in this work to visualize the triplet of (I;Q;U) polarization image components. The structure of this color space is also highly appropriate to represent other attributes of linearly polarized light, such as the polarized intensity, degree and the angle of polarization. The accurately measured polarization components can also be efficiently used for image enhancement. In this direction, a new, polarization-based de-reflection method is proposed. This method is an optimal pixel-wise extension of the widely used photographical polarization filtering. Our method is also capable of amplifying the specular effects. Another application is de-hazing, which removes the linearly polarized component of the haze present in natural scenes, and results in a sharp and color-corrected image. Furthermore, the different combinations of visible and infrared polarization channels enable great possibilities in further de-hazing and to create artistic images. © The Eurographics Association 2008.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Direct Policy Search Reinforcement Learning for Autonomous Underwater Cable Tracking

引用

IFAC Proceedings Volumes 2008年第1期41卷 155-160页

作者： A. El-Fakdi M. Carreras J. Batlle Computer Vision and Robotics Group (VICOROB) University of Girona 17071 Girona Spain

This paper proposes a field application of a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in a cable tracking task. The learning system is characterized by using a Direct Policy Search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV .

关键词： Machine Learning Robot Control Underwater Vehicles

来源：评论

学校读者我要写书评

暂无评论

Online Robust 3D Mapping Using Structure from Motion Cues

Online Robust 3D Mapping Using Structure from Motion Cues

引用

OCEANS - Europe

作者： Tudor Nicosevici Rafael Garcia Computer Vision and Robotics Group University of Girona Spain

This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential structure from motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene.

关键词： Robustness Cameras Layout Motion estimation Proposals Robot vision systems Biology computing computer vision Video sequences Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Hybrid tracking of human operators using IMU/UWB data fusion by a Kalman filter 08

Hybrid tracking of human operators using IMU/UWB data fusion...

引用

3rd ACM/IEEE International Conference on Human-Robot Interaction, HRI 2008

作者： Corrales, J.A. Candelas, F.A. Torres, F. Automatics Robotics and Computer Vision Group Physics Systems Engineering and Signal Theory Department University of Alicante 03690 San Vicente del Raspeig Alicante Spain

ISBN: (纸本)9781605580173

The precise localization of human operators in robotic workplaces is an important requirement to be satisfied in order to develop human-robot interaction tasks. Human tracking provides not only safety for human operators, but also context information for intelligent human-robot collaboration. This paper evaluates an inertial motion capture system which registers full-body movements of an user in a robotic manipulator workplace. However, the presence of errors in the global translational measurements returned by this system has led to the need of using another localization system, based on Ultra-WideBand (UWB) technology. A Kalman filter fusion algorithm which combines the measurements of these systems is developed. This algorithm unifies the advantages of both technologies: high data rates from the motion capture system and global translational precision from the UWB localization system. The developed hybrid system not only tracks the movements of all limbs of the user as previous motion capture systems, but is also able to position precisely the user in the environment. Copyright 2008 ACM.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Towards Detecting Changes in Underwater Image Sequences

Towards Detecting Changes in Underwater Image Sequences

引用

OCEANS 2008 - MTS/IEEE Kobe Techno-Ocean (OCEANS Kobe 2008), vol.2

作者： Olivier Delaunoy Nuno Gracias Rafael Garcia Computer Vision and Robotics Group University of Girona Spain

关键词： Underwater tracking Image sequences Monitoring Photometry Object detection Layout Detection algorithms Image analysis Image sequence analysis Image restoration

来源：评论

学校读者我要写书评

暂无评论

S+T: An algorithm for distributed multirobot task allocation based on services for improving robot cooperation

S+T: An algorithm for distributed multirobot task allocation...

引用

2008 IEEE International Conference on robotics and Automation, ICRA 2008

作者： Viguria, Antidio Maza, Ivan Ollero, Anibal School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA 30332 United States Robotics Vision and Control Group University of Seville 41092 Seville Spain

ISBN: (纸本)9781424416479

In this paper, we present a distributed market-based algorithm called S+T, which solves the multi-robot task allocation (MRTA) problem in applications that require the cooperation among the robots to accomplish all the tasks. If a robot cannot execute a task by itself, it asks for help and, if possible, another robot will provide the required service. In the paper, tasks consisting in transmitting data in real-time that could require communication relay services are considered. On the other hand, the parameters of the algorithm can be adapted to give priority to either the execution time or the energy consumption in the mission. The potential generation of deadlocks associated to the relation between tasks and services is studied, and as an original result, a distributed algorithm that prevent them is proposed. The algorithm has been tested in simulations that illustrate the main features of the S+T algorithm. ©2008 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Assembly/disassembly strategies for service applications

引用

IFAC Proceedings Volumes 2008年第2期41卷 15805-15810页

作者： Puente ST F. Torres C. Díaz Automatics Robotics and Computer Vision Group Physics Systems Engineering and Signal Theory Department University of Alicante Spain

This paper presents a development of assembly/disassembly systems to be applied in service applications. It uses algorithms developed for industrial applications to perform the service tasks. A robotic system to perform service applications in a cooperative environment with a human is used. The system uses product model to perform the task planning, with the designed task the required grasping points to manipulate the objects are computed according the restrictions. Two experimental results of applying the system to service applications are described.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Policy Gradient Based Reinforcement Learning for Real Autonomous Underwater Cable Tracking

Policy Gradient Based Reinforcement Learning for Real Autono...

引用

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Pages 3133-3660

作者： Andres El-Fakdi Marc Carreras Computer Vision and Robotics Group (VICOROB) Institute of Informatics and Applications University of Girona 17074 Girona Spain

ISBN: (纸本)9781424420575

This paper proposes a field application of a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a Direct Policy Search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU~(AUV).

关键词： Robots Underwater cables Vehicles Power cables Artificial neural networks Surges Robot sensing systems

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：