检索结果-南通市图书馆

第26届中国控制与决策会议

作者： Tao Zhang Shumin Fei College of Automation Electronic Engineering Qingdao University of Sciences and Technology School of automation Southeast University

ISBN: (纸本)9781479937097

A robust tracking algorithm based on the particle filter with multi-cue adaptive fusion is proposed which can overcome the shortcoming of single visual cue in complex environments. The color and the texture based on the discrete wavelet transform（DWT） are used to describe the tracking target. The weights are adaptively adjusted using the democratic integration according to the current tracking situations, which increases the reliability of observation and improves the robustness of observation model. Due to the use of reliable cues for tracking, the shortcoming of single cue in complex scenes is improved. Meanwhile, the noise variance of each cue is updating to increase the discrimination of each cue. During designing particle filter based tracking algorithm, the likelihood model is constructed depending on adaptive cue fusion mechanism, thus enhancing the robustness of tracking algorithm. The experiments show that the result of better tracking are obtained in circumstances that the target is arbitrarily moving or rotating, partially or completely occlusion, as well as the light changes. When the target with similar color appears, the tracking algorithm with the texture model can distinguish the target with the background.

关键词： Particle Filter Multiple cue data fusion target tracking

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

target tracking method based on the fusion of structured SVM and KCF algorithm

Target tracking method based on the fusion of structured SVM...

引用

第32届中国控制与决策会议

作者： Lei Huan Ma Jingqi Lu Xingjian Guangdong Institute of Intelligent Manufacturing Guangdong Key Laboratory of Modern Control Technology

Aiming at the drift problem of traditional KCF(kernelized correlation filter) target tracking algorithm caused by scale change and fast movement,a tracking method based on the fusion of structured SVM(support vector machine)and KCF algorithm is proposed.Combined with the location and scale information of the tracking target,a structured SVM classification and prediction model is established to replace the ridge regression filtering method in KCF,train the samples collected by cyclic matrix,and solve the problem of not detailed classification.In addition,a search strategy optimization method based on tracking target motion features is proposed to reduce unnecessary search time in dense sampling,further improve the search efficiency and classifier accuracy of traditional KCF algorithm in dense sampling,improve its calculation efficiency and target tracking performance in complex environment.This can solve the problem that the target cannot be accurately tracked due to the drift caused by the change of target scale and fast movement.Experiments show that the algorithm can locate the target area more accurately when the target scale changes and fast movement.Compared with the traditional KCF tracking algorithm,it has better performance and stronger robustness.

关键词： target tracking KCF structured SVM scale change drift

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Full-Rate tracking Algorithm of Maneuvering target Based on Multi-Rate CS and CV Models

A Full-Rate Tracking Algorithm of Maneuvering Target Based o...

引用

2006 CIE International Conference on Radar

作者： Ting Cheng Zishu He Huiyong Li Benyong Liu Department of Electronic Engineering University of Electronic Science and Technology Chengdu 610054 China.

Multi-rate models can realize high quality tracking through decomposing the observations and state model of target to multi-resolution.The interacting multiple model （IMM） algorithm,on the other hand,can effectively track high maneuvering targets.A method of full-rate tracking to a maneuvering target based on multi-rate constant velocity （CV） and current statistical （CS） models is proposed here.Simulation results demonstrate that compared with conventional full-rate IMM algorithm the new method offers a better tracking result.

关键词： multi-rate model interacting multiple model maneuvering target target tracking data fusion

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Bayesian Framework for target tracking in Sensor Networks

A Bayesian Framework for Target Tracking in Sensor Networks

引用

第二十六届中国控制会议

作者： Cheng Yuanguo 1,2,Li Guohui 2 1.Electrical Engineering College,Navy Engineering University,Wuhan 430033,P.R.China 2.Computer College,Huazhong University of Science and Technology,Wuhan 430047,P.R.China

The work described in this paper presents a framework to track a moving target in sensor networks.The framework employs a method based on Bayesian classification to calculate the detection probabilities and proposes a tracking algorithm by defining the moving scope of a target,where the sensors have the higher values of detection probabilities.Experiment re-sults show this scheme is effective.

关键词： Sensor Networks target tracking Bayesian Classification

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Variational Bayesian Kalman filter using natural gradient

引用

Chinese Journal of Aeronautics 2022年第5期35卷 1-10页

作者： Yumei HU Xuezhi WANG Quan PAN Zhentao HU Bill MORAN School of Automation Northwestern Polytechnical UniversityXi’an 710072China The Key Laboratory of Information Fusion Technology Ministry of EducationXi’an 710072China Department of Electrical and Electronic Engineering The University of MelbourneMelbourneVIC 3010Australia School of Engineering RMIT UniversityMelbourneVIC 3000Australia School of Computer and Information Engineering Henan UniversityKaifeng 475001China

We propose a technique based on the natural gradient method for variational lower bound maximization for a variational Bayesian Kalman filter.The natural gradient approach is applied to the Kullback-Leibler divergence between the parameterized variational distribution and the posterior density of interest.Using a Gaussian assumption for the parametrized variational distribution,we obtain a closed-form iterative procedure for the Kullback-Leibler divergence minimization,producing estimates of the variational hyper-parameters of state estimation and the associated error covariance.Simulation results in both a Doppler radar tracking scenario and a bearing-only tracking scenario are presented,showing that the proposed natural gradient method outperforms existing methods which are based on other linearization techniques in terms of tracking accuracy.

关键词： Kullback-Leibler divergence Natural gradient Nonlinear Kalman filter target tracking Variational Bayesian optimization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Imperfect Communication Channel Effect on target tracking Based on Underwater Wireless Sensor Networks

Imperfect Communication Channel Effect on Target Tracking Ba...

引用

第36届中国控制会议

作者： Yaobin Lu Qiang Zhang The 14th Research Institute of China Electronic Technology Group Corporation

ISBN: (纸本)9781538629185

underwater wireless sensor networks（UWSNs） can provide a promising solution to underwater target tracking.However,due to the limited energy and bandwidth resources of UWSNs,only a small part of nodes are allowed to track underwater target at each time step.As far as we know,almost all the existing node selection schemes assume the communication channel between a node and the fusion center is perfect.However,such assumption is hard to satisfy due to the complex underwater environment.Based on the above consideration,this paper study the effect of the imperfect channel on target tracking based on UWSNs.To select the best nodes to track the underwater target,the Posterior Cramer-Rao Lower Bound（PCRLB） considering the imperfect channel is derived.Then a new target tracking scheme considering the imperfect channel is also designed.Finally,a sea experiment is conducted and collected data can verify the validity of our algorithm

关键词： Imperfect communication channel target tracking posterior Cramer-Rao lower bound underwater wireless sensor networks

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Maximum Correntropy Criterion Kalman Filter Based target tracking with State Constraints

Maximum Correntropy Criterion Kalman Filter Based Target Tra...

引用

第三十九届中国控制会议

作者： Yiqun Zou Shuang Zou Xiafei Tang Lingli Yu School of Automation Central South University School of Electrical and Information Engineering Changsha University of Science and Technology

Since the maximum correntropy criterion（MCC） can capture higher moments of the stochastic signal, the maximum correntropy criterion Kalman filter（MCC-KF） behaves well in state estimation under non-gaussian noise compared to the classic KF. If some prior information such as state constraints is known, we can improve the performance of the MCC-KF by the incorporation of state equality constraints. In this paper, we realize this incorporation through estimation projection technique to deal with the linear and nonlinear constraints. The corresponding algorithm is presented as the main contribution of this paper.Applied in the example of target tracking, the algorithm shows its superiority against its classic counterpart.

关键词： Kalman filter maximum correntropy criterion maximum correntropy criterion Kalman filter state equality constraints estimation projection target tracking

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Color target tracking strategy in Binocular stereo vision based on Camshift algorithm

Color target tracking strategy in Binocular stereo vision ba...

引用

第24届中国控制与决策会议

作者： Guo Baiwei1 ,Feng Xiaobin 2 1. School of Aerospace, Beijing Institute of Technology, Beijing 1000812. School of Aerospace, Beijing Institute of Technology, Beijing 100081

Using camshift algorithm to track color target, proposed a strategy worked when the target is lost or parts of it is blocked. By changing the search window’s size, it is possible to achieve real-time capture. Experiments show that this strategy can catch the target quickly and efficiently. Analysis is done for camshift algorithm applied to binocular stereo vision measurement. An efficient tracking process is proposed, using the strategy of catch the target after losing.

关键词： Camshift target tracking Binocular vision

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

UAV Visual target tracking: Research Status,Algorithms and Future Prospect

UAV Visual Target Tracking: Research Status,Algorithms and F...

引用

第40届中国控制会议

作者： Lin Chen Yungang Liu Wenjuan Li Linzhen Yu School of Control Science and Engineering Shandong University

Nowadays the unmanned aerial vehicle(UAV) has been widely used in civilian and military fields, such as target search and tracking, owing to its small size and unique flexibility. Although visual target tracking technology has made remarkable progress, it is still a challenging problem to achieve robust and stable tracking due to various factors in actual complex environment. Firstly, this paper introduces the research status of target tracking, and reviews some classical and latest UAV target tracking algorithms, especially single-UAV and multi-UAV cooperative target tracking algorithms. Then, the UAV datasets and evaluation metrics of target tracking have been introduced. Finally, the future directions of UAV target tracking algorithms are proposed.

关键词： UAV Computer vision Cooperation target tracking

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Improved Average Consensus Scalable Algorithm of target tracking for Wireless Sensor Network

Improved Average Consensus Scalable Algorithm of Target Trac...

引用

第24届中国控制与决策会议

作者： Hui Long 1 , Zhihua Qu 1,2 , Xiaoping Fan 1 ,Shaoqiang Liu 1 1. School of Information Science and Engineering, Central South University, Changsha, Hunan, 4100752. Department of Electrics and Computer Engineering University of Central Florida Orlando, FL 32816-2450, U.S.A.

target tracking is one of the most important applications for wireless sensor networks. In this paper, a scalable dynamical average consensus algorithm of target tracking is proposed. Kalman prediction is employed to help setting tracking cluster through nearest neighbor criterion. Selected sensors, called Tasking sensor nodes, are working locally for target estimate through observation or innovation based consensus distributed kalman filter. In the algorithm, Cluster head is not fusion center, but a ordinary node for choose tasking sensor of next step and forwards current state estimate and corresponding error covariance. Each tasking sensor only requires information from neighboring nodes that will decrease communication bandwidth of overall network. Simulation results show that, compared with central kalman filter algorithm, observation and innovation based consensus distributed kalman filter will get comparable accuracy while it will be more robust due to distributed manner.

关键词： target tracking scalable consensus filter observation-based distributed kalman filter, innovation distributed kalman filter

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：