检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： N. Mekuz K.G. Derpanis J.K. Tsotsos Department of Computer Science and Center for Vision Research (CVR) York University Toronto ONT Canada

ISBN: (纸本)0769525210

An often overlooked problem in matching lies in selecting an appropriate step size. The selection of the step size for real-time applications is critical both from the point of view of computational efficiency and detection performance. Current systems set the step size in an ad hoc manner. This paper describes an algorithm for selecting the step size based on a theoretical worst case analysis. We have implemented this adaptive step size method in an object detection algorithm. Experimental evaluation demonstrates the effectiveness of our proposed algorithm

关键词： Algorithm design and analysis Computational efficiency Object detection computer vision computer science Application software Stereo image processing Stereo vision Image reconstruction Optical devices

来源：评论

学校读者我要写书评

暂无评论

Automatic gesture recognition for intelligent human-robot interaction

Automatic gesture recognition for intelligent human-robot in...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Seong-Whan Lee Center for Artificial Vision Research Department of Computer Science and Engineering Korea University Seoul South Korea

An intelligent robot requires natural interaction with humans. Visual interpretation of gestures can be useful in accomplishing natural human-robot interaction (HRl). Previous HRI researches were focused on issues such as hand gesture, sign language, and command gesture recognition. However, automatic recognition of whole body gestures is required in order to operate HRI naturally. This can be a challenging problem because describing and modeling meaningful gesture patterns from whole body gestures are complex tasks. This paper presents a new method for spotting and recognizing whole body key gestures at the same time on a mobile robot. Our method is simultaneously used with other HRI approaches such as speech recognition, face recognition, and so forth. In this regard, both of execution speed and recognition performance should be considered. For efficient and natural operation, we used several approaches at each step of gesture recognition; learning and extraction of articulated joint information, representing gesture as a sequence of clusters, spotting and recognizing a gesture with HMM. In addition, we constructed a large gesture database, with which we verified our method. As a result, our method is successfully included and operated in a mobile robot

关键词： Intelligent robots Mobile robots Humans Handicapped aids Biological system modeling Speech recognition Face recognition Data mining Hidden Markov models Databases

来源：评论

学校读者我要写书评

暂无评论

Robust control of a humanoid robot using a bio-inspired approach based on central pattern generators, reflexes, and proprioceptive feedback

Robust control of a humanoid robot using a bio-inspired appr...

引用

IEEE International Conference on robotics and Biomimetics

作者： Sebastian Bartsch Frank Kirchner Department of Mathematics and Computer Science Robotics Lab University of Brethemen Bremen Germany Department of Mathematics and Computer Science Robotics Lab and German Research Center for Artificial Intelligence Robotic Lab University of Brethemen Bremen Germany

This paper presents a biologically inspired control approach for the locomotion of humanoid robots based on a central pattern generator concept with additional balancing behavior which was tested on BIN-HUR, a modified Kondo KHR-1 robot equipped with a custom-made micro-controller board. The software concept is built up on a new behavior-based microkernel named Monster.

关键词： Robust control Humanoid robots Feedback Frequency Legged locomotion Servomechanisms Pulse width modulation Intelligent sensors Leg Test pattern generators

来源：评论

学校读者我要写书评

暂无评论

Towards Face Recognition at a Distance

Towards Face Recognition at a Distance

引用

2006 IET Conference on Crime and Security

作者： Simon J.D. Prince James Elder Y. Hou M. Sizinstev E. Olevskiy Department of Computer Science University College London UK Center for Vision Research York University Toronto Canada

Current face recognition algorithms require the tacit cooperation of users, who must position themselves in a small area of space and face the camera. Face recognition in uncontrolled conditions, such as in security camera footage presents two extra challenges. First, it is difficult to capture good quality images of faces in this setting. Second, the pose of the face is relatively uncontrolled which causes most face recognition algorithms to fail. In this paper, we present a series of solutions to address these problems. High quality face images are captured using a foveated wide field sensor, in which a narrow-field camera is directed towards faces using information from a static wide-field camera. Feature points corresponding to the eyes/nose etc. are accurately localized and face shape is normalized. A novel algorithm is introduced to identify these (typically non-frontal) faces from a test gallery of frontal faces. Results are demonstrated to be superior to contemporary approaches

关键词：

来源：评论

学校读者我要写书评

暂无评论

A visual servoing approach for tracking features in urban areas using an autonomous helicopter

A visual servoing approach for tracking features in urban ar...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： L. Mejias P. Campoy S. Saripalli G.S. Sukhatme Computer Vision Group Universidad Politécnica de Madrid Madrid Spain Robotic Embedded Systems Laboratory Center for Robotics and Embedded Systems Department of Computer Science University of Southern California Los Angeles CA USA

The use of unmanned aerial vehicles (UAVs) in civilian and domestic applications is highly demanding, requiring a high-level of capability from the vehicles. This work addresses the design and implementation of a vision-based feature tracker for an autonomous helicopter. Using vision in the control loop allows estimating the position and velocity of a set of features with respect to the helicopter. The helicopter is then autonomously guided to track these features (in this case windows in an urban environment) in real time. The results obtained from flight trials in a real world scenario demonstrate that the algorithm for tracking features in an urban environment, used for visual servoing of an autonomous helicopter is reliable and robust

关键词： Visual servoing Urban areas Helicopters Aircraft navigation Machine vision Control systems Unmanned aerial vehicles Global Positioning System computer vision Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Learning predictive state representations using non-blind policies 06

Learning predictive state representations using non-blind po...

引用

ICML 2006: 23rd International Conference on Machine Learning

作者： Bowling, Michael McCracken, Peter James, Michael Neufeld, James Wilkinson, Dana Department of Computing Science University of Alberta Edmonton Alta. T6G 2E8 Canada AI and Robotics Group Technical Research Dept. Toyota Technical Center Ann Arbor MI United States School of Computer Science University of Waterloo Waterloo Ont. Canada

ISBN: (纸本)1595933832

Predictive state representations (PSRs) are powerful models of non-Markovian decision processes that differ from traditional models (e.g., HMMs, POMDPs) by representing state using only observable quantities. Because of this, PSRs can be learned solely using data from interaction with the process. The majority of existing techniques, though, explicitly or implicitly require that this data be gathered using a blind policy, where actions are selected independently of preceding observations. This is a severe limitation for practical learning of PSRs. We present two methods for fixing this limitation in most of the existing PSR algorithms: one when the policy is known and one when it is not. We then present an efficient optimization for computing good exploration policies to be used when learning a PSR. The exploration policies, which are not blind, significantly lower the amount of data needed to build an accurate model, thus demonstrating the importance of non-blind policies.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Wide Dynamic Range vision for Robot Eyes based on Double Capturing Scheme

Wide Dynamic Range Vision for Robot Eyes based on Double Cap...

引用

IEEE SENSORS

作者： Sung-Kee Park Jin Heon Kim Intelligent Robotics Research Center Korea Institute of Science and Technology Seoul South Korea Department of Computer Engineering Seokyeong University Seoul South Korea

A new method of combining double captured images to extend dynamic range is proposed in this paper. Two images taken with long and short exposure times respectively are combined by proposed DSPA (difference & slant based pixel adjustment) algorithm, dynamically varying weighted averaging scheme to present a scene of wide dynamic range. Compared with the previous works using multiple capturing, our approach captures only twice to facilitate practical implementation. It is characterized by simple arithmetic operations which can be easily implemented by a small H/W. Compared with the previous double capturing scheme, it shows enhanced contrast which contains more edge information, easy control of resultant effects while still retaining simple architectural merit. The test results for the several scenes show it has logarithmic convergence characteristics and more edge quantity compared to the previous works.

关键词： Dynamic range Robot vision systems Eyes Layout Intelligent robots Cameras Intelligent sensors Robot sensing systems Pixel Charge coupled devices

来源：评论

学校读者我要写书评

暂无评论

Multi-subregion-based probabilistic approach to pose-invariant face recognition

引用

Systems and computers in Japan 2006年第8期37卷 68-76页

作者： Yamada, Akihiko Kanade, Takeo SANYO Electric Co. Ltd. R and D Headquarters Osaka 573-8534 Japan Robotics Institute Carnegie Mellon University Pittsburgh PA 15213 Human Ecology Research Center Department of Computer Science and Robotics Carnegie Mellon University

Current automatic facial recognition systems are not robust to changes in illumination, pose, facial expression, and occlusion. In this paper, in order to address the problem of pose change, we propose an algorithm based on a probabilistic approach to face recognition that takes into account the pose difference between probe and gallery images. By using a large facial image database, the CMU PIE database, which contains images of the same set of people taken from many different angles, we have developed a probabilistic model of how facial features change as the pose changes. This model enables us to make our face recognition system more robust to changes of pose in the probe image. The experimental results show that this approach achieves a better recognition rate than conventional face recognition methods over a much larger range of poses. For example, when the gallery contains only images of a frontal face and the probe image varies its pose orientation, the recognition rate shows less than a 10% difference until the probe pose begins to differ by more than 45°, whereas the recognition rate of a PCA-based method begins to drop at differences as small as 10°, and that of a representative commercial system begins to drop at 30°. © 2006 Wiley Periodicals, Inc.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

An adaptive neuro-fuzzy system for color image segmentation

引用

Journal of the Indian Institute of science 2006年第5期86卷 493-506页

作者： Deshmukh, Kanchan Shinde, G.N. M.G.M's College of Computer Science and Information Technology Near Airport Nanded 431 605 India Y.M. Research Center VIP Road Nanded 431 605 India Department of Electronics Computer Vision Lab. Indian Institute of Technology Kharagpur 721 302 India C/o Amit V. Nandedkar H. No. 49. 'Sheshsmuruti' Ashok Nagar Nanded 431 605 India

Image segmentation and object extraction plays an important role in image analysis and computer vision. In this paper, we propose a novel technique for color image segmentation called 'adaptive neuro-fuzzy color image segmentation (ANFCIS)'. The proposed system consists of multilayer perception (MLP)-like network which performs color image segmentation using multilevel thresholding. Threshold values for detecting clusters and their labels are found automatically using fuzzy C-means (FCM) clustering technique. Fuzzy entropy is used as a tool to decide the number of clusters. ANFCIS uses saturation and intensity planes of HSV (hue, saturation, intensity) color space for segmentation. Neural network is employed to find the number of objects automatically from an image. The major advantage of this method is that it does not require a priori knowledge to segment a color image. The algorithm is found to be robust and relatively computationally inexpensive for large variety of color images. Experimental results have demonstrated the effectiveness and efficiency of the proposed method. © Indian Institute of science.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Semi-Automatic Lymph Node Segmentation in LN-MRI

Semi-Automatic Lymph Node Segmentation in LN-MRI

引用

IEEE International Conference on Image Processing

作者： G. Unal G. Slabaugh A. Ess A. Yezzi T. Fang J. Tyan M. Requardt R. Krieg R. Seethamraju M. Harisinghani R. Weissleder Siemens Corporate Research Intelligent Vision and Reasoning Princeton NJ USA Computer Science Department Swiss Federal Institute of Technology Zurich Switzerland School of ECE Georgia Institute of Technology Atlanta GA USA Siemens Med-MIR Medical Solutions Erlangen Germany Siemens Medical Solutions Med-MR Malvern PA USA Center For Molecular Imaging Research Massachusetts General Hospital Harvard University Boston MA USA

Accurate staging of nodal cancer still relies on surgical exploration because many primary malignancies spread via lymphatic dissemination. The purpose of this study was to utilize nanoparticle-enhanced lymphotropic magnetic resonance imaging (LN-MRI) to explore semi-automated noninvasive nodal cancer staging. We present a joint image segmentation and registration approach, which makes use of the problem specific information to increase the robustness of the algorithm to noise and weak contrast often observed in medical imaging applications. The effectiveness of the approach is demonstrated with a given lymph node segmentation problem in post-contrast pelvic MRI sequences.

关键词： Lymph nodes Image segmentation Biomedical imaging Medical diagnostic imaging Cancer Feature extraction Magnetic resonance imaging Shape Oncological surgery Nanoparticles

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：