检索结果-内蒙古大学图书馆

Concatenated edge and co-occurrence feature extracted from Curvelet Transform for human detection

Journal of Information and Computational Science 2011年第4期8卷 662-670页

作者： Han, Hong Fan, Youjian Jiao, L.C. Chen, Zhichao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

An efficient feature extraction method based on the Curvelet Transform for detecting human in static images is proposed in this paper. The edge features can be extracted with the block-based statistical information of each sub-band coefficients, and then the texture feature can be extracted from the co-occurrence matrixes of the lowest-frequency sub-band coefficients, all the extracted features are concatenated as the final feature vector of the images. All the training and test data are from the INRIA and MIT human dataset. The classification results with test data show that the proposed feature extraction method is suitable for human detection. From the detection results, it can be seen that, the detection accuracy of the proposed method is higher, meanwhile the false positive rate is lower than the Histograms of Oriented Gradients (HOG) method. Copyright © 2011 Binary Information Press.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Fabric defect detection using undecimated wavelet transform

引用

Information Technology Journal 2011年第9期10卷 1701-1708页

作者： Bi, Mingde Sun, Zhigang Department of Control Science and Engineering Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology 1037 Luoyu Road 430074 Hubei Wuhan China

In this study, a new fabric defect detection algorithm base on undecimated wavelet transform is proposed. The selection scheme of wavelet decomposition scales is investigated to set the decomposition scales adaptively to the fabric texture. The objective of the scheme is to enhance the energy of defective region and attenuate the energy of non-defective region. And the performance of detection results with different number of decomposition scales is also discussed. A simple and computationally effective data fusion scheme combined with amplitudes division of wavelet coefficients is used to fuse data from multiple scales together. And several features based on defective energy estimation are extracted from fused image. By examining the extracted features the proposed algorithm can provide not only the location of defects but also some detailed information about them which can be used for defect recognition and classification. Experimental results of real fabric defects are provided to validate the effectiveness and robustness of the defect detection algorithm. © 2011 Asian Network for Scientific Information.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Echo state Networks Based Method for Harmonic Extraction in Shunt Active Power Filters

Echo State Networks Based Method for Harmonic Extraction in ...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Jinbang Xu Jun Yang Feng Liu Zhixiong Zhang Anwen Shen Department of Control Science & Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science & Technology Wuhan China

With the wide use of power conversion devices, harmonic currents are being injected into the power grid. Shunt Active Power Filters (SAPF) is a power electronic device to compensate the harmonic currents caused by nonlinear loads. As the foundation of the harmonics recognition and compensation, harmonic extraction techniques are becoming more and more important. This paper proposes a new harmonic extraction method based on the Echo state Networks (ESN). ESN is a new type of Recurrent Neural Networks (RNN), which has much faster training speed than other types of RNN. To evaluate the dynamic system modeling capability of the ESN, the ESN with different dynamic reservoir size are discussed. The performance of the ESN based harmonic extraction method is compared with traditional methods and method based on multilayer perceptron networks (MLP). The ESN algorithm is trained and tested in MATLAB.

关键词： Harmonic analysis Power harmonic filters Training Training data Reservoirs Neurons

来源：评论

学校读者我要写书评

暂无评论

ANN-based control Method Implemented in a Voltage Source Converter for Industrial Micro-grid

ANN-based Control Method Implemented in a Voltage Source Con...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Jinbang Xu Zhizhuo Wu Xuan Yang Jie Ye Anwen Shen Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Department of Control Science & Technology Huazhong University of Science & Technology Wuhan China

With more and more attention on the grid current harmonic in recent years, many control schemes of the Pulse Width Modulation Voltage Source Converter (PWM-VSC) have been investigated. Conventional PI controller has shown limitations such as sensitivity to load and system parameter variation. Even the stability of the system can be threatened under a large and sudden load change. In this paper, the practical situation of a VSC for industrial Micro Grid (MG) is considered and an Artificial neural network (ANN) based control method is employed to solve the problem. Meanwhile, an on-line parameter tuning algorithm is introduced for its advantage of self-tuning and system character identification. The proposed control scheme is verified through simulation based on SABER software. The simulation results have shown the advantage of the proposed method and the performance of the parameter tuning session.

关键词： Voltage control Artificial neural networks Power conversion Regulators Voltage measurement Frequency control

来源：评论

学校读者我要写书评

暂无评论

Deformation prediction of landslide based on genetic-simulated annealing algorithm and BP neural network

Deformation prediction of landslide based on genetic-simulat...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Huangqiong Chen Zhigang Zeng Department of Control Science and Engineering Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

In this paper, a modified method for landslide prediction is presented. This method is based on the back propagation neural network(BPNN), and we use the combination of genetic algorithm and simulated annealing algorithm to optimize the weights and biases of the network. The improved BPNN modeling can work out the complex nonlinear relation by learning model and using the present data. This paper demonstrates that the revised BPNN modeling can be used to predict and calculate landslide deformation, quicken the learning speed of network and improve the predicting precision. Applying this thinking and method into research of some landslide in the Three Gorges reservoir, the validity and practical value of this model can be demonstrated. And it also shows that the dynamic prediction of landslide deformation is very crucial.

关键词： Terrain factors Prediction algorithms Biological neural networks Artificial neural networks Annealing Predictive models Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Denosing 3D Ultrasound images by Non-local Means Accelerated by GPU

Denosing 3D Ultrasound Images by Non-local Means Accelerated...

引用

International Conference on intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Song Hu WenGuang Hou Department of Biomedical Engineering Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China HuaZhong University of Science and technology Wuhan China

In Ultrasound imaging, speckle noise is the most serious problem which affects the performance of images. Non-local mean filter is a nice method to remove the speckle noise, but the algorithm' computational complexity makes it's a highly time-consuming method. In many applications like image-guided surgical intervention, real-time de-noising is required. This paper implements a NLM method accelerated by GPU for real-time denoising of 3D ultrasound images. The experimental results show the proposed accelerated de-noising method is efficient in terms of denoising quality and real-time.

关键词： Graphics processing unit Three dimensional displays Ultrasonic imaging Noise reduction Biomedical imaging Filtering algorithms Speckle

来源：评论

学校读者我要写书评

暂无评论

Optimal control of nonlinear system based on linear extended state observer

Optimal control of nonlinear system based on linear extended...

引用

作者： Xu, Zhicai Wang, Zhishen Wang, Yongji Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9789881725592

Systems with unknown nonlinear characteristics and unknown disturbances are linearized using dynamic feedback linearization based on linear extended state observer. Also a method for the parameter regulation is presented. And then for a given performance index, an optimal control law is designed using LQR theory. Finally numerical simulation results demonstrate that this control method can meet the performance requirement with good robustness. © 2011 Chinese Assoc of Automati.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Approximate Jacobian control of robot manipulators without joint velocity measurements

Approximate Jacobian control of robot manipulators without j...

引用

IEEE International Conference on Cyber Technology in Automation, control, and intelligent Systems

作者： Xinwu Liang Xinhan Huang Min Wang Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan Hubei China

So far, all of the approximate Jacobian controllers for robot manipulators proposed in the literatures have assumed that the exact joint velocity measurements are available. In this paper, we propose alternative controller designs without the use of joint velocity measurements. To provide the joint velocities used by the controllers, we introduce the well-known sliding mode observers to estimate the robot manipulator states. In addition, Lyapunov analysis is presented to show that the combined controller-observer designs can achieve asymptotical stability in the sliding patch. Simulation results are also presented to show the performance of the proposed methods.

关键词： Joints Jacobian matrices Velocity measurement Observers Manipulators Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Brain Activity during Walking in Patient with Spinal Cord Injury

Brain Activity during Walking in Patient with Spinal Cord In...

引用

2011 International Symposium on Bioelectronics and Bioinformatics(第二届国际生物医学电子学与生物信息学学术会议 ISBB 2011)

作者： Jiping He Xu Jiang Li Wei Huang Yue member of Image Processing and Intelligent Control Key Laboratory of Education Ministry of China De student of Department of Control Science and Engineering Huazhong University of Science and Technol

The capacity for walking is an important assessment to reflect the ability about how the patients who have movement disorders to control their lower limbs. Electroencephalography (EEC), which can describe brain activities, has been widely used in the field of neural engineering. The present study investigates 2D scalp topography mapping while the subjects perform gait-like movements with the assistance of a dynamic tilt table. Based on the result, we concluded that the motor function and the most nerve circuit of lower limbs in spinal cord injury (SCI) patients in level D are as normal as healthy human.

关键词： Scalp Electroencephalography Legged locomotion Surfaces Humans Spinal cord Electrodes

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of motor imagery EEG signals based on wavelet packet decomposition

Feature extraction of motor imagery EEG signals based on wav...

引用

IEEE/ICME International Conference on Complex Medical Engineering, CME

作者： Dingyin Hu Wei Li Xi Chen Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Department of Control Science and Engineering Huazhong University of Science & Technology Wuhan China 430074

Feature extraction in brain-computer interface (BCI) work is an important task that significantly affects the success of brain signal classification. In this paper, a feature extraction method of electroencephalographic (EEG) signals based on wavelet packet decomposition (WPD) is used. The coefficients mean of wavelet packet decomposition and wavelet packet energy of special sub-bands are employed as the original features. The Fisher discriminant analysis (FDA) is used to measure the separabilities of those features. The features which had a higher separability will be considered as effective ones and then the final feature vector are formed. A feature vector is obtained by combining the selected features from six channels. Then, the features are classified by using the k-nearest neighbor (k-NN) algorithm. We obtained significant improvement for the speed and accuracy of the classification for data set Ia, which is a typical representative of one kind of BCI competition 2003 data. The classification results have proved the effectiveness of the proposed method.

关键词： Feature extraction Classification algorithms Electroencephalography

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：