检索结果-内蒙古大学图书馆

Multi-sensor measurement adaptive filtering algorithm in measurement uncertainty

Journal of Information and Computational Science 2012年第4期9卷 843-851页

作者： Hu, Zhentao Fu, Chunling Liu, Xianxing Laboratory of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China Basic Experiment Teaching Center Henan University Kaifeng 475004 China

The reliable estimation of system state in multi-sensor uncertainty is always the hot and knotty issue of nonlinear filtering theory. Aiming to the reasonable utilization of measurement information, a novel multi-sensor measurement adaptive filtering algorithm is proposed in this paper. Firstly, Combining with the construction of measurement likelihood and maximize principle, the equivalent measurement are affirmed. Next, the selection and fusion of measurement without disturbance influence are accomplished by the introduction of statistic distance among the measurements, which can realize the optimization of equivalent measurement to some extend. The new method improves the adverse influence of disturbance in multi-sensor information fusion process, and retains the litter computational complexity relative to the distributed fusion structure. The theoretical analysis and experimental results show the efficiency of the proposed algorithm. Copyright © 2012 Binary Information Press.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Unifying Gradients to Improve Real-World Robustness for Deep Networks

arXiv

引用

arXiv 2022年

作者： Wu, Yingwen Chen, Sizhe Fang, Kun Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University 800 Dongchuan Road Shanghai China Institute of Image Processing and Pattern Recognition The MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University 800 Dongchuan Road Shanghai China

The wide application of deep neural networks (DNNs) demands an increasing amount of attention to their real-world robustness, i.e., whether a DNN resists black-box adversarial attacks, among which score-based query attacks (SQAs) are most threatening since they can effectively hurt a victim network with the only access to model outputs. Defending against SQAs requires a slight but artful variation of outputs due to the service purpose for users, who share the same output information with SQAs. In this paper, we propose a real-world defense by Unifying Gradients (UniG) of different data so that SQAs could only probe a much weaker attack direction that is similar for different samples. Since such universal attack perturbations have been validated as less aggressive than the input-specific perturbations, UniG protects real-world DNNs by indicating attackers a twisted and less informative attack direction. We implement UniG efficiently by a Hadamard product module which is plug-and-play. According to extensive experiments on 5 SQAs, 2 adaptive attacks and 7 defense baselines, UniG significantly improves real-world robustness without hurting clean accuracy on CIFAR10 and imageNet. For instance, UniG maintains a model of 77.80% accuracy under 2500-query Square attack while the state-of-the-art adversarially-trained model only has 67.34% on CIFAR10. Simultaneously, UniG outperforms all compared baselines in terms of clean accuracy and achieves the smallest modification of the model output. The code is released at https://***/snowien/UniG-pytorch. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Gait Planning and Motion Control Based on Vrep Simulation for Quadruped Robot 5

Gait Planning and Motion Control Based on Vrep Simulation fo...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Zhou, Linqi Chen, Zhihua Liu, Jun Liu, Zhi Chen, Yumeng Zhang, Liting Nanchang Hangkong University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Moe Key Lab of Nondestructive Testing Technology Nanchang330063 China Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing100081 China

ISBN: (纸本)9798350307320

Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability margin is proposed. Firstly, the robot model and kinematics modeling are introduced. Secondly, the robot's foot static and dynamic gait were planned and the foot trajectory was designed. Finally, two types of gait of the robot were simulated using Vrep simulation software, and the differences in stability and speed between the coordinated gait with speed and stability in the static and dynamic gait of a 12 degree of freedom robot were analyzed, verifying the effectiveness of the gait control method proposed in this paper. © 2023 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

image Representation via Sub-dictionary based Sparse Coding

Image Representation via Sub-dictionary based Sparse Coding

引用

International Joint Conference on Neural Networks

作者： Bingxin Xu Qian Yin Ping Guo Hongzhe Liu Beijing Key Laboratory of Information Service Engineering Beijing Union University Image Processing and Pattern Recognition Laboratory Beijing Normal University

ISBN: (纸本)9781509006212

In this paper, a sub-dictionary based sparse coding method is proposed for image representation. The novel sparse coding method substitutes a new regularization item for L1-norm in the sparse representation model. The proposed sparse coding method involves a series of sub-dictionaries. Each sub-dictionary contains all the training samples except for those from one particular category. For the test sample to be represented, all the sub-dictionaries should linearly represent it apart from the one that does not contain samples from that label, and this sub-dictionary is called irrelevant sub-dictionary. This new regularization item restricts the sparsity of each sub-dictionary's residual, and this restriction is helpful for classification. The experimental results demonstrate that the proposed method is superior to the previous related sparse representation based classification.

关键词： image representation Sparse coding sparse representation-based classification Linearly

来源：评论

学校读者我要写书评

暂无评论

A general framework for machine vision: hierarchical token grouping

A general framework for machine vision: hierarchical token g...

引用

International Symposium on Speech, image processing and Neural Networks

作者： Qian Huang Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing MI USA

ISBN: (纸本)078031865X

While the view of constructive and hierarchical vision prevails, the issues of cooperation and competition among individual modules become crucial. These issues are directly related to one of the most important aspects in computer vision research: integration. A major source of difficulty in developing a consistent and systematic integration formalism is the heterogeneity existing in modules, in information, and in knowledge. The author exploits, using the central theme of grouping, the homogeneous characteristics in vision problem solving and proposes a general framework, called hierarchical token grouping, that facilitates vision problem solving by providing a consistent and systematic environment for integrating modules, cues, and knowledge, all in a globally coherent mechanism.< >

关键词： Machine vision Problem-solving Computer vision Organizing pattern recognition image processing Laboratories Computer science Gratings Humans

来源：评论

学校读者我要写书评

暂无评论

Generalized stochastic tube model: Tracking 3D blood vessels in MR images 12

Generalized stochastic tube model: Tracking 3D blood vessels...

引用

12th IAPR International Conference on pattern recognition - Conference B: pattern recognition and Neural Networks, ICPR 1994

作者： Huang, Qian Stockman, George C. IBM Research Division Almaden Research Center 650 Harry Road San JoseCA95120-6099 United States Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East LansingMI48824 United States

ISBN: (纸本)0818662700

This paper addresses the issue of tracking tubular objects, particularly blood vessels from MR images. A model-based approach is adopted. The generalized stochastic tube (GST) model is developed which is an extension of our previously proposed Generalized Tube (GT) model. Transitions among adjacent tubes are explicitly parameterized. Integrated with a bivariate Gaussian density function adopted to model the blood flow within cross sections, the GST model is applied to tracking blood vessels in MRA volumetric data. Experimental results on both synthetic data with different degrees of Gaussian noise and real MRA data demonstrated that simultaneously utilizing both models yields robust performance under noisy conditions. © 1994 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Algorithm Based on Improved MobileViT Network 8

Face Forgery Detection Algorithm Based on Improved MobileViT...

引用

8th International Conference on Intelligent Computing and Signal processing, ICSP 2023

作者： Wang, Tiantian Lu, Xiaoqi Inner Mongolia University of Science and Technology School of Information Engineering Baotou014010 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou014010 China Inner Mongolia University of Technology Institute of Information Engineering Hohhot010051 China

ISBN: (纸本)9798350302455

DeepFakes blur the boundaries between reality and forgery, resulting in the collapse of exiting credit system, causing immeasurable consequences for national security and social order. Through analysis of existing face forgery techniques, it is found that most generation techniques rely on random noise distribution, and global information will be lost after up sampling. Therefore, we propose a deepfake detection algorithm based on improved MobileViT, which uses CNN local space biasing and the global space representation of the Transformer network to learn the local features and global representation of forged faces, respectively. Coordinate attention is introduced to obtain directional perception and position sensitive information, making the model locate synthetic traces of fake faces better and fusion local and global representation more effectively. For the improved generalization of the model, with the GELU activation function to solve the problem of neuron death. Our model achieved 96.2% on FF++(C23) datasets, and 93.7%,94.1%,96.3%,87.9% on DF, F2F, FS, and NT datasets, respectively. Comparing with previous methods, our model has shown detection robustness and better generalization. © 2023 IEEE.

关键词： National security

来源：评论

学校读者我要写书评

暂无评论

A new approach to finite wordlength coefficient fir digital filter design using the branch and bound technique 10

A new approach to finite wordlength coefficient fir digital ...

引用

2000 10th European Signal processing Conference, EUSIPCO 2000

作者： Belbachir, A.N. Boulerial, B. Belbachir, M.F. Signal and System Laboratory Electronic Institute U.S.T.O. B.P. 1505 El Mnouer Oran Algeria Vienna University of Technology Pattern Recognition and Image Processing Group Favritenstr. 9/1832 ViennaA-1040 Austria

ISBN: (纸本)9789521504433

It has been shown that the branch and bound technique is effective for the design of finite wordlength optimal digital filters. This technique is however expensive in computing time. In this paper, we present a robust branch and bound branching strategy named Sequential and Progressive Search, improving the design of filters on a large wordlength processor in a reasonable computing cost. The details of the algorithm and many examples are given and compared to the other methods. © 2000 EUSIPCO.

关键词： Digital filters

来源：评论

学校读者我要写书评

暂无评论

Interactive object segmentation using iterative adjustable graph cut

Interactive object segmentation using iterative adjustable g...

引用

2011 IEEE Visual Communications and image processing, VCIP 2011

作者： Shi, Ran Liu, Zhi Xue, Yinzhu Zhang, Xiang School of Communication and Information Engineering Shanghai University Shanghai 200072 China Key Laboratory of Advanced Display and System Application Shanghai University Ministry of Education Shanghai 200072 China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China

ISBN: (纸本)9781457713200

Interactive object segmentation is widely used for extracting any user-interested objects from natural images. A common problem with many interactive segmentation approaches is that the object segmentation quality is degraded due to inaccurate object/background seeds provided by the user. This paper proposes an iterative adjustable graph cut to efficiently solve this problem. First, object/background seeds are initialized based on the object segmentation result obtained with the user-specified scribbles as the interactive input. Then, an iterative seed adjustment scheme is exploited to correct inaccurate seeds and extract new suitable seeds via graph cut, in which the balancing weight between energy terms are adaptively updated to protect stable seeds and speedup the iteration process. Finally, suitable seeds are obtained and graph cut is used to segment the objects. Experimental results demonstrate the better segmentation performance of our approach even if user provides rather rough seeds. © 2011 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Modified Numerical Integration Method for Deformable Object Animation

A Modified Numerical Integration Method for Deformable Objec...

引用

Asia Simulation Conference 2007, AsiaSim 2007

作者： Hu, Xinrong Wei, Lan Li, Dehua Dept. of Computer Science and Technology WuHan University of Science and Engineering WuHan 430074 China Institute for Pattern Recognition and Artificial Intelligence State Education Commission Laboratory for Image Processing and Intelligence Control HuaZhong Univ. of Science and Technology WuHan 430074 China

ISBN: (纸本)9783540775997

A satisfied deformable object simulation should be general, accurate, efficient and stable. Explicit, implicit and semi-implicit numerical integration methods have contributed to large performance enhancements in the field of deformable simulation. Cloth is the most representative deformable object. In this paper, we propose an improved embedded Runge-Kutta integration method to solve the deformable simulation that based on classical spring-mass model. Traditional embedded Runge-Kutta methods generally solve ordinary differential equations of deformable object simulation. Most of them tend to concentrate on the efficiency of the simulation process, and not the fidelity of the simulation result. We investigate and determine the extent to which the overall quality must be compromised in order for the stable conditions to be satisfied. The improved Runge-Kutta method proposed in our paper incorporates the fixed time step and adaptive time step in solving cloth motion equations to achieve a controllable error evaluation. Compared with the other Runge-Kutta methods, the proposed method has some advantages for cloth simulation: controllable error evaluation without extra computations, excellent efficiency, good stability and satisfied precision. Experiment demonstrates that this method results in simulation efficiency improvements and is considerable practicable. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Animation

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：