检索结果-内蒙古大学图书馆

Robust video tracking algorithm: a multi-feature fusion approach

IET COMPUTER VISION 2018年第5期12卷 640-650页

作者： Wang, Howard Nguang, Sing Kiong Wen, Jiwei Univ Auckland Dept Elect & Comp Engn Auckland New Zealand Jiangnan Univ Dept Automat Wuxi Peoples R China

This study proposes a novel robust video tracking algorithm consists of target detection, multi-feature fusion, and extended Camshift. Firstly, a novel target detection method that integrates Canny edge operator, three-frame difference, and improved Gaussian mixture model (IGMM)-based background modelling is provided to detect targets. The IGMM-based background modelling divides video frames into meshes to avoid pixel-wise processing. In addition, the output of the target detection is utilised to initialise the IGMM and to accelerate the convergence of iterations. Secondly, low-dimensional regional covariance matrices are introduced to describe video targets by fusing multiple features like pixel location, colour index, rotation and scale invariant features as well as uniform local binary patterns, and directional derivatives. Thirdly, an extended Camshift based on adaptive kernel bandwidth and robust H state estimation is proposed to predict the states of fast moving targets and to reduce the mean shift iterations. Finally, the effectiveness of the proposed tracking algorithm is demonstrated via experiments.

关键词： image fusion feature extraction video signal processing edge detection Gaussian processes mixture models covariance matrices robust video tracking algorithm multifeature fusion approach target detection extended Camshift target detection method Canny edge operator three-frame difference improved Gaussian mixture model IGMM-based background modelling video frames low-dimensional regional covariance matrices video targets multiple feature fusion pixel location colour index scale invariant features local binary patterns directional derivatives adaptive kernel bandwidth robust H state estimation mean shift iteration reduction tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Moving Target tracking algorithm Based on Computer Vision

Research and Application of Moving Target Tracking Algorithm...

引用

2019 7th International Conference on Machinery,Materials and Computing Technology(ICMMCT 2019)

作者： Dong Fei Shaanxi Railway Institute

Computer vision technology has developed rapidly in the current computer world,and the processing methods for video images have also been significantly *** on the computer theory based on Marr,this paper discusses and studies the tracking of moving objects in *** the motion change of the monitored vehicle as an example,the Robert algorithm is used to track the changes of the vehicle during driving,and the multi-association template matching method is used to improve the accuracy of the *** is proved in the experiment that the algorithm in this paper has better precision in the tracking of the vehicle and can meet the current needs for tracking the moving target.

关键词： tracking algorithm image segmentation algorithm machine vision

来源：评论

学校读者我要写书评

暂无评论

tracking Deadtime algorithm for GaN DC/DC Converter 24

Tracking Deadtime Algorithm for GaN DC/DC Converter

引用

24th International Conference on Applied Electronics (AE)

作者： Skarolek, Pavel Lettl, Jiri Czech Tech Univ Fac Elect Engn Dept Elect Drives & Tract Tech 2 Prague 16627 Czech Republic

ISBN: (纸本)9788026108122

The presented method automatically adjusts the deadtime of gallium nitride (GaN) transistors in half-bridge to increase the efficiency. This removes the need of manual measuring and setting the deadtime of the finished converter. The developed algorithm was tested and compared with the fixed deadtime case. The obtained results show that the developed algorithm is achieving higher and more stable efficiency compared to selected fixed deadtime.

关键词： GaN transistor deadtime tracking algorithm DC/DC converter

来源：评论

学校读者我要写书评

暂无评论

Semidefinite programming-based localisation and tracking algorithm using Gaussian mixture modelling

引用

IET COMMUNICATIONS 2017年第16期11卷 2514-2523页

作者： Zhang, Yueyue Zhu, Yaping Xia, Weiwei Yan, Feng Shen, Lianfeng Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Jiangsu Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

In this study, the authors propose a semidefinite programming (SDP)-based localisation and tracking algorithm, which mitigates the non-line-of-sight (NLOS) error of range measurement and calibrates the accumulative error within the inertial sensing data. Both the range measurement in a mixed line-of-sight/NLOS environment and the step length estimated from inertial sensing information are approximated parametrically using Gaussian mixture modelling, and a maximum-likelihood estimator (MLE) is formulated to obtain the optimal position estimation. Since the Gaussian mixture models are non-linear functions of positions, the MLE is a non-convex problem, which global optimum is difficult to attain. Then, the non-convex MLE is transformed into an SDP-based localisation and tracking problem, relying on Jensen's inequality and semidefinite relaxation. Thus, a sub-optimal solution to the original MLE can be achieved. Moreover, the Cramer-Rao lower bound is also derived to serve as a performance indicator for localisation errors. The simulation and experimental results demonstrate the performance of the proposed algorithm. Compared with the existing algorithms, the proposed algorithm owns the best localisation accuracy, and can achieve a sub-metre level accuracy to a root mean square error of 0.46m in the real deployments.

关键词： mathematical programming Gaussian processes mixture models maximum likelihood estimation mean square error methods semidefinite programming tracking algorithm localisation algorithm Gaussian mixture modelling SDP NLOS error inertial sensing data maximum-likelihood estimator MLE optimal position estimation nonlinear functions Jensen's inequality semidefinite relaxation root mean square error

来源：评论

学校读者我要写书评

暂无评论

A new UAV ship-tracking algorithm

引用

IFAC-PapersOnLine 2017年第1期50卷 13090-13095页

作者： Garcia-Aunon, Pablo Santos Peñas, Matilde García, Jesus Manuel de la Cruz School of Industrial Engineering Technical University of Madrid Madrid28006 Spain Computer Sciences University Complutense of Madrid Madrid28040 Spain Faculty of Physics University Complutense of Madrid Madrid28040 Spain

For several applications involving Unmanned Aerial Vehicles (UAVs), a moving target must the tracked and followed autonomously. Several algorithms have been already proposed, mainly based on three different strategies, assuming in most of the cases the target trajectory known in advanced. We here propose a new algorithm and compared it with a well known and widely used control tracking algorithm in a ship-tracking scenario. Our proposal is derived from the qualitative analysis of the system response when a UAV low level controller is implemented. Besides, these algorithms depend on various parameters, which normally are tuned based on the experience. We also present a methodological way of tuning the parameters of these types of control algorithms based on the kinematic analysis of the movement, the control effort and the error while tracking the target. This method has been proved efficient and general, and it may be used for similar problems and control algorithms. © 2017

关键词： Aircraft detection Aircraft control Antennas Control engineering Kinematics Parameter estimation Ships Tuning Unmanned aerial vehicles (UAV) Control effort Kinematic Analysis Low level controllers Moving targets Qualitative analysis System response Target trajectory tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

A new UAV ship-tracking algorithm

A new UAV ship-tracking algorithm

引用

20th World Congress of the International-Federation-of-Automatic-Control (IFAC)

作者： Garcia-Aunon, Pablo Santos Penas, Matilde de la Cruz Garcia, Jesus Manuel Tech Univ Madrid Sch Ind Engn Madrid 28006 Spain Univ Complutense Madrid Comp Sci E-28040 Madrid Spain Univ Complutense Madrid Fac Phys E-28040 Madrid Spain

关键词： tracking algorithm UAV kinematic analysis qualitative analysis control tuning

来源：评论

学校读者我要写书评

暂无评论

Research on Particle Filter tracking algorithm Based on Multi-Feature Covariance Matrix 3

Research on Particle Filter Tracking Algorithm Based on Mult...

引用

3rd IEEE International Conference on Control, Automation and Robotics (ICCAR)

作者： Du, Yunming San, Linna Tian, Jing Yan, Bingbing Jiamusi Univ Coll Informat & Elect Technol Jiamusi Heilongjiang Pr Peoples R China Jiamusi Univ Coll Mech Engn Jiamusi Heilongjiang Pr Peoples R China

ISBN: (纸本)9781509060887

Aiming at the problem that the particle filter target tracking based on single feature is vulnerable to environmental impacts and is difficult to deal with the size scaling and rotation changes, this paper proposes a particle filter tracking algorithm based on covariance matrix. The algorithm uses the covariance matrix to fuse multiple features of the target in the framework of particle filter, which improves the adaptability of the algorithm. By introducing the covariance integral graph, the dimension of particle computation is effectively reduced, which reduces the computational cost of the algorithm and improves the real-time performance. The processing efficiency of the algorithm is effectively improved through the mean value calculation in covariance to remove the noise. Simulation experiment results show that the proposed algorithm is robust to the target tracking under the condition of illumination change, environmental disturbance and scale change.

关键词： tracking algorithm particle filter multiple feature fusion covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Fuzzy train tracking algorithm for the energy efficient operation of CBTC equipped metro lines

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2016年 53卷 19-31页

作者： Carvajal-Carreno, William Cucala, Asuncion P. Fernandez-Cardador, Antonio Pontifical Comillas Univ Inst Res Technol 23 Alberto Aguilera St Madrid 28015 Spain

In CBTC (Communications-Based Train Control) operated metro lines, headway can be reduced by taking advantage of the system's train track continuous communication, thus increasing transport capacity. When a train runs close enough to the preceding one, a tracking algorithm is triggered to control the distance between the trains. The following train receives the LMA (limit of movement authority) via radio, which is updated periodically as the preceding train runs. Besides transport capacity, one of railway operators' main goals is the reduction of energy consumption, for environmental and economic reasons. This paper firstly shows that the existing basic CBTC tracking algorithm is not energy efficient, due to the application of short braking traction cycles. It then proposes a new efficient algorithm that makes use of coast (null traction) command, and models the uncertainty associated with the speed of the preceding train. This fuzzy algorithm is compared to the basic one in terms of energy consumption, running time and steady state interval (resulting tracking interval). Simulation results show that the proposed, fuzzy tracking algorithm provides important energy savings with minor influence on running time and steady state interval. This algorithm is suitable for implementation in on-board CBTC equipment to reduce the energy consumption of traffic operation. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Energy-efficiency tracking algorithm Fuzzy parameters CBTC signaling system Moving block Train simulation Ecodriving ATO

来源：评论

学校读者我要写书评

暂无评论

An eddy tracking algorithm based on dynamical systems theory

引用

OCEAN DYNAMICS 2016年第11期66卷 1415-1427页

作者： Conti, Daniel Orfila, Alejandro Mason, Evan Sayol, Juan Manuel Simarro, Gonzalo Balle, Salvador UIB CSIC IMEDEA Miquel Marques 21 Esporles 07190 Spain CSIC ICM Passeig Maritim Barceloneta 37-49 E-08003 Barcelona Spain

This work introduces a new method for ocean eddy detection that applies concepts from stationary dynamical systems theory. The method is composed of three steps: first, the centers of eddies are obtained from fixed points and their linear stability analysis;second, the size of the eddies is estimated from the vorticity between the eddy center and its neighboring fixed points, and, third, a tracking algorithm connects the different time frames. The tracking algorithm has been designed to avoid mismatching connections between eddies at different frames. Eddies are detected for the period between 1992 and 2012 using geostrophic velocities derived from AVISO altimetry and a new database is provided for the global ocean.

关键词： Coherent structures Global ocean Mesoscale eddies Dynamical systems theory Stability analysis of fixed points tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

Path-tracking algorithm for Intelligent Transportation Systems

引用

IEEE LATIN AMERICA TRANSACTIONS 2016年第6期14卷 2934-2939页

作者： Quintero, Y. A. Patino, G. Aedo, J. E. Univ Antioquia UdeA Medellin Colombia

This paper describes a path tracking algorithm implemented in an Intelligent Transportation System in order to validate if a vehicle is following properly a certain path previously assigned. The algorithm is based on a geometrical analysis and GPS data specified to trace in real-time the current position of the vehicle according to a previous digital map of the path to be tracked. As a case study, the tracking algorithm has been developed following the regulations of the public transportation of Medellin, important Colombian city with a large number of public buses and a significant complexity in the mobility within the city.

关键词： Geometrical Analysis Global Positioning System Intelligent Transportation System Map Matching On-board Navigation System Real-Time System tracking algorithm

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：