检索结果-内蒙古大学图书馆

Learning and recognizing behavioral patterns using position and posture of human body and its application to detection of irregular states

引用

Systems and Computers in Japan 2005年第13期36卷 45-56页

作者： Aoki, Shigeki Iwai, Yoshio Onishi, Masaki Kojima, Atsuhiro Fukunaga, Kunio Graduate School of Engineering Osaka Prefecture University Sakai 599-8531 Japan Bio-Mimetic Control Research Center RIKEN Nagoya 463-0003 Japan Library and Science Information Center Osaka Prefecture University Sakai 599-8531 Japan Department of Electronic Control Engineering Kumamoto National College of Technology Japan Robotics Society of Japan Japan Sharp Corporation Japan Bio-Mimetic Control Research Center RIKEN Japan IEEJ Japan Image and Information Media Society Faculty of Liberal Arts and Sciences Osaka Prefecture University Japan Information Processing Society Japan Society for Artificial Intelligence Department of Informatics Faculty of Engineering Institute of Systems Control and Information Engineers Japan IEEE

It is generally considered that human behavior includes both regularities and habits. In this paper, the regularities and habits of behavior are called the behavioral pattern, and we wish to learn and recognize them. The conventional approaches considered behavioral patterns but used only infrared sensors or information about whether electrical appliances were on or off. Thus, it was difficult to recognize in detail how a person was performing motions in the room. In order to realize a procedure for the detailed recognition of motion in ordinary environments, on the other hand, a large number of models must be prepared beforehand. To deal with this problem, this paper proposes the following technique. Motions conducted in the learning period are automatically classified and individual models are constructed. Then, motions can be recognized in detail without preparing a large number of models, and behavioral patterns can be recognized by considering the sequence of motions. In experiments, human motions and behavioral patterns in an indoor environment were learned and recognized, and the effectiveness of the method was demonstrated. © 2005 Wiley Periodicals, Inc.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Sequential updating algorithm for extracting the basis of Karhunen-Loeve transformation

Sequential updating algorithm for extracting the basis of Ka...

引用

2004 International Conference on Image Processing, ICIP 2004

作者： Qu, Yanyun Zheng, Nanning Li, Cuihua Yuan, Zejian Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Computer Science Department Xiamen University China

ISBN: (纸本)0780385543

Karhunen-Loeve transformation (KLT) is a popular method for dimensional reduction and feature extraction in image analysis, signal processing, automatic control systems, and so on, while the drawback of the KLT is expensive computation. In this paper, we propose a novel updating algorithm for KLT, the rank-k updating algorithm, which has advantages especially for image sequences: it is faster than batch algorithm, it can handle the dynamic database, and it does not save the entire database. Furthermore it makes the active learning and recognition possible in computer vision. Finally we analyze the computational complexity and error of the algorithm. We also show its application in face analysis. The experimental results demonstrate the efficiency of our algorithm. © 2004 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Merging ratio images based realistic object class re-rendering

Merging ratio images based realistic object class re-renderi...

引用

IEEE International Conference on Image Processing

作者： Fu Yun Institute of Artificial Intelligence & Robotics Xi'an Jiaotong University China

ISBN: (纸本)0780385543

The merging ratio image (MRI) for realistic object class re-rendering is presented and applied to human face image. We focus on the Lambertian object class and utilize a uniform ratio image scheme - merging ratio image - to merge the expression ratio image, ageing ratio image, and illumination ratio image (quotient image), which exhibits a new facial model quality. Given a single face image and some other photorealistic face examples with distinct attributes, such as aged wrinkles, expressive feature motions, and certain lighting conditions, we generate expressive expressions, natural ageing, rejuvenating and varying illuminations with MRI rendering technique. Experimental results demonstrate the attractive properties of our method with some face examples from MPI Caucasian face database and AI&R Asian face database.

关键词： Merging Lighting Aging Reflectivity Humans Face Rendering (computer graphics) Magnetic resonance imaging Image databases Spatial databases

来源：评论

学校读者我要写书评

暂无评论

Training and assessment of psychomotor skills for performing laparoscopic surgery using BEST-IRIS virtual reality training simulator

Training and assessment of psychomotor skills for performing...

引用

4th Medicine Meets Virtual Reality Proceedings 1996, MMVR 1996

作者： Makam, Ramesh Rajan, C.S. Brendon, Tulip Shreedhar, V. Saleem, K. Shrivastava, Sangeeta Sudarshan, R. Naidu, C.R.J. Prakash Bangalore Endoscopic Surgery Training Institute and Research Centre A v Hospital Patalamma Temple Street Basavanagudi Bangalore 560 004 India Institute for Robotics and Intelligent Systems Centre for Artificial Intelligence and Robotics Rajbhavan Circle High Grounds Bangalore 560 001 India

ISBN: (纸本)1586034049

In this article, we present the results of a pilot study that examined the performance of people training on a Virtual Reality based BEST-IRIS Laparoscopic Surgery Training Simulator. The performance of experienced surgeons was examined and compared to the performance of residents. The purpose of this study is to validate the BEST-IRIS training simulator. It appeared to be a useful training and assessment tool.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

True single view point multi-resolution catadioptric system for intelligent vehicle

True single view point multi-resolution catadioptric system ...

引用

International Conference on Intelligent Transportation

作者： Qing Li Nanning Zheng Lin Ma Hong Cheng Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

The vision system mounted in intelligent vehicle could require high resolution in certain azimuth direction and wide field of view to meet safety for autonomous or assistant driving, but few vision systems with these characteristics exists. A true single viewpoint multi-resolution elliptical cone catadioptric system with 180 degree horizontal field of view is suggested in order to provide higher resolution in lookahead direction and less in lateral direction. An elliptical cone is used as catoptric element and conventional perspective camera is used as dioptric element. The single viewpoint of the catadioptric system is proved and its vertical and horizontal resolution, and vertical field of view are calculated by pinhole imaging model and geometric optics image formation model. Experimental results verify the ability of multi-resolution of the system.

关键词： Intelligent vehicles Layout artificial intelligence Intelligent robots Vehicle driving Cameras Solid modeling Machine vision Geometrical optics Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-DSP based intelligent vehicle vision system and software & hardware co-realization

Multi-DSP based intelligent vehicle vision system and softwa...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Tie Liu Nanning Zheng Hong Cheng Zhengbei Xing Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (纸本)0780382730

Machine vision system is one of the most important components of intelligent vehicles, and the software and hardware co-realization is critical for the vision navigation of intelligent vehicles. This work presents the multi-DSP realization for intelligent vehicle vision system, analyzes and illustrates the software and hardware co-realization. Based on the software framework and the data flow of the machine vision system, we propose the software implementation for the host computer and DSP terminals. In particular, a road detection algorithm and its multi-DSP realization are presented. Simulated in real environments, the system is stable and its real-time performance is satisfactory.

关键词： Intelligent vehicles Machine vision Software systems Hardware Navigation Computer vision Data flow computing Digital signal processing Roads Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of high speed arithmetic encoder [image coding applications]

Design of high speed arithmetic encoder [image coding applic...

引用

International Conference on Solid-State and Integrated Circuit Technology

作者： Mei Kuizhi Zheng Nanning Yao Ji Liu Yuehu The Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (纸本)078038511X

Focusing on the problem of path waiting or path circulation that existed in updating of the context table and the renorme and byteout procedure in the realization of the conventional arithmetic encoder in JPEG2000, a 3-step pipeline architecture is used on an FPGA to get high speed encoding. A method of updating the CX table is proposed, and a circuit with short delay is also implemented to detect the left zeros of the A-register. Multiplexers are adopted to accelerate the random left shift operation, and parallel processing based on data dependency is used to optimize the RTL code to shorten the main critical path. Finally, the updating of the logic of the context table is fully discussed. Experimental result show the encoder can work up to 107 MHz on Altera's EP1S25B672C7 and the critical path is 4.6 ns when synthesized in synopsys DC by the TSMC 0.25 /spl mu/m library.

关键词： Arithmetic Image coding Pipelines Field programmable gate arrays Encoding Circuits Delay Multiplexing Acceleration Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Lane boundary detection using an adaptive randomized Hough transform

Lane boundary detection using an adaptive randomized Hough t...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Qing Li Nanning Zheng Hong Cheng Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (纸本)0780382730

To detect lane boundaries robustly, R channel and B channel of color road image were used to form a gray level image. Size of the gray image was reduced and Sobel operator with very low threshold was used to produce gray edge image. In adaptive randomized Hough transform, pixels of gray edge image were sampled randomly according to their weights corresponding to their gradient magnitude. 3D parametric space of parabolic curve was reduced to 2D and two parameters were estimated by use of gradient direction, then another parameter was used to verify the estimated parameters by adaptive threshold value. Such lane markings can be detected accurately and robustly. Experimental results in different condition prove the validity of the method.

关键词： Roads Transforms Image edge detection Vehicle detection Cameras Robustness Parameter estimation Equations artificial intelligence Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Throat microphone signal for speaker recognition 8

Throat microphone signal for speaker recognition

引用

8th International Conference on Spoken Language Processing, ICSLP 2004

作者： Shahina, A. Yegnanarayana, B. Kesheorey, M.R. Speech and Vision Laboratory Department of Computer Science and Engg. Indian Institute of Technology Madras Chennai600 036 India Center for Artificial Intelligence and Robotics Bangalore560 001 India

Speaker recognition systems perform better when clean speech signals are used for the task. In the presence of high levels of background noise, speech recorded from a close speaking microphone will be degraded and hence the performance of the speaker recognition system. Use of a transducer held at the throat results in a signal that is clean even in a noisy environment. This paper discusses the prospect of using such signals for speaker recognition. A study of a text-independent speaker recognition system based on features extracted from speech simultaneously recorded using a throat microphone and a close-speaking microphone in clean and simulated noisy conditions is conducted. Autoassociative neural networks are used to model the speaker characteristics based on the vocal tract system and excitation source features represented by weighted linear prediction cepstral coefficients and linear prediction residual, respectively. The results of experimental studies show that the speech collected from the throat microphone can be used for tasks like speaker recognition, especially in noisy conditions.

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

Updating algorithm for extracting the basis of Karhunen-Loeve transform in nonzero mean data

Updating algorithm for extracting the basis of Karhunen-Loev...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Qu Yanyun Zheng Nanning Li Cuihua Yuan Zejian Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Department of Computer Science Xiamen University Xiamen China

Karhunen-Loeve transform (KLT) is a popular method for dimensional reduction and feature extraction in image analysis, signal processing and automatic control systems and so on. The drawback of the KLT is expensive computation. So the efficient updating algorithms were proposed in signal processing and numerical linear algebra. The updating algorithms make the active learning and recognition possible. But they mainly deal with zero mean data. In this paper, we propose an updating algorithm for KLT for nonzero mean data. And we also show its application in face analysis. The experimental results demonstrate the efficiency of our algorithm.

关键词： Data mining Karhunen-Loeve transforms Signal processing Signal processing algorithms Vectors robotics and automation Linear algebra Image sequence analysis Principal component analysis Face recognition

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：