检索结果-内蒙古大学图书馆

A Monte Carlo simulation based approach to a priori performance prediction for target detection and recognition in cluttered synthetic aperture radar imagery

A Monte Carlo simulation based approach to a priori performa...

引用

iee target tracking 2004: algorithms and applications

作者： Z. Knowles D. Parker Combat and Mission Systems Department BAE Systems Air Systems Preston UK

Multi-sensor systems for wide area surveillance and tracking are an area of increasing interest for civil and military applications. In order to design these systems to reliably achieve a specification, performance models are required for each of the system components, to allow synthesis of the overall system performance. The work presented in this paper addresses the problem of a performance model for the target detection and recognition performance of a SAR sensor component in a surveillance system. A Monte Carlo simulation based approach is described which is used to predict the receiver operating characteristic (ROC) as a function of the target, the clutter background and the sensor specification for a template matching recognition algorithm. Some initial results from an experimental validation trial are presented and it is concluded that there is sufficient similarity between the current model's predictions of performance and the actual performance achieved with representative real data to encourage further development work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online learning with kernels

引用

ieeE TRANSACTIONS ON SIGNAL PROCESSING 2004年第8期52卷 2165-2176页

作者： Kivinen, J Smola, AJ Williamson, RC Australian Natl Univ Res Sch Informat Sci & Engn Canberra ACT 0200 Australia

Kernel-based algorithms such as support vector machines have achieved considerable success in various problems in batch setting, where all of the training data is available in advance. Support vector machines combine the so-called kernel trick with, the large margin idea. There has been little use of these methods in an online setting suitable for real-time applications. In this paper, we consider online learning in a reproducing kernel Hilbert space. By considering classical stochastic gradient descent within a feature space and the use of some straightforward tricks, we develop simple and computationally efficient algorithms for a wide range of problems such as classification, regression, and novelty detection. In addition to allowing the exploitation of the kernel trick in an online setting, we examine the value of large margins for classification in the online setting with a drifting target. We derive worst-case loss bounds, and moreover, we show the convergence of the hypothesis to the minimizer of the regularized risk functional. We present some experimental results that support the theory as well as illustrating the power of the new algorithms for online novelty detection.

关键词： classification condition monitoring large margin classifiers novelty detection regression reproducing kernel Hilbert spaces Stochastic gradient descent tracking

来源：评论

学校读者我要写书评

暂无评论

Tutorial on multisensor management and fusion algorithms for target tracking

Tutorial on multisensor management and fusion algorithms for...

引用

Proceedings of the 2004 American Control Conference (AAC)

作者： Kalandros, Michael K. Trailović, Lidija Pao, Lucy Y. Bar-Shalom, Yaakov Air Defense Systems Department Johns Hopkins Applied Physics Lab. Johns Hopkins Road Laurel MD 20723-6099 Department of Electrical Engineering University of Colorado Boulder CO 80309-0425 Department of Electrical Engineering University of Connecticut Storrs CT 06269-1157

ISBN: (纸本)0780383354

This paper provides an introduction to sensor fusion techniques for target tracking. It presents an overview of common filtering techniques that are effective for moving targets as well as methods of overcoming problems specific to target tracking, such as measurement-to-track association and sensor registration. The computational demand of such algorithms is discussed and various practices, including distributed processing of target tracks and sensor management, are proposed to help reduce this demand. Final comments include a discussion of applications and implementation issues specific to the presented scenarios.

关键词： Sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Development of a generic multi-sensor tracking system for agile radars

Development of a generic multi-sensor tracking system for ag...

引用

iee target tracking 2004: algorithms and applications

作者： G. Davidson S. Symons MWSI QinetiQ Portsdown West UK

The paper details the recent development of a generic tracking system within the Maritime Weapon Systems Integration team at QinetiQ Portsdown West. The tracker has been used to process multiple colocated radars, remote airborne radars and simulated plots. It has also been integrated with an open loop tracking simulation using a high quality radar simulator. The paper highlights some of the problems, and our proposed solutions, when an entire system was developed from scratch. Compared to a 'textbook' implementation (Blackman, S. and Popoli, R., "Design and Analysis of Modern tracking Systems", Artech House, 1999) we have made only small theoretical developments; it is hoped that our work may be of interest to those faced with the practical problems of integrating techniques into a real system for real data. The motivation for the project is that scan based systems are unable to process data from agile radar and are generally unsuitable for phased-array radar systems. A further requirement is that multiple disparate sensors are in service and a development system was required for integration studies. The project is expected to form a central part of QinetiQ's ongoing research into netted sensor applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi sensor tracking function on modern anti-air-warfare (AAW) frigates

Multi sensor tracking function on modern anti-air-warfare (A...

引用

iee target tracking 2004: algorithms and applications

作者： M. Fiorini G. Filoni Alenia Marconi Systems S.p.A. Italy

The paper describes the multi sensor tracking function developed by Alenia Marconi Systems (AMS) (Italy) for the combat management system (CMS) on the new anti-air-warfare (AAW) 'Horizon' frigates (an Italian/French cooperation programme). AMS has already implemented this function on Italian fast patrol boats and it is also implementing it on several other vessels for the Italian Navy. The multi sensor tracking function provides on-board above water sensor data to contribute to the compilation of the tactical picture (TP), a representation of the tactical situation, together with other surveillance information. The other data are not taken into account in the multi sensor tracking process, but contribute within the CMS for building the TP. The AAW frigates are equipped with a complete set of surveillance sensors, comprising several radar systems as well as an interrogation friend-or-foe (IFF) system and an infra red alerting system (IRAS). The multi sensor tracking function performs the following tasks: a) detecting if reports provided by different sensors are the representation of the same real world object (RWO), in the affirmative case correlating reports between them and producing the multi sensor track as the best RWO representation; b) reducing false alarm rate acting on the initialisation function; c) performing the best kinematic parameter estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive discriminative generative model for object tracking 16

Adaptive discriminative generative model for object tracking

引用

16th European Conference on Artificial Intelligence, ECAI 2004

作者： Lin, Ruei-Sung Yang, Ming-Hsuan Levinson, Stephen E. University of Illinois at Urbana-Champaign United States Honda Research Institute United States

ISBN: (纸本)9781586034528

This paper presents an adaptive visual learning algorithm for object tracking. We formulate a novel discriminative generative framework that generalizes the conventional Fisher Linear Discriminant algorithm with a generative model and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target class from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or environment lighting condition does not significantly change as time progresses, our method adapts the discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in different situations. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

Wideband DOA estimation algorithms for multiple target detection and tracking using unattended acoustic sensors

Wideband DOA estimation algorithms for multiple target detec...

引用

Conference on Unattended/Unmanned Ground, Ocean and Air Sensor Technologies and applications VI

作者： Azimi-Sadjadi, MR Pezeshki, A Scharf, LL Hohil, M Informat Syst Technol Inc Ft Collins CO 80521 USA

ISBN: (纸本)0819453404

The problem of detection, tracking and localization of multiple wideband sources (ground vehicles) using unattended passive acoustic sensors is considered in this paper. Existing methods typically fail to detect, resolve and track multiple closely spaced sources in tight formations, especially in the presence of clutter and wind noise. In this paper, several existing wideband direction of arrival (DOA) estimation algorithms are extended and applied to this problem. A modified version of the Steered Covariance Matrix (STCM) algorithm is presented that uses a two-step search process. To overcome the problems of existing DOA estimation methods, new wideband versions of the narrowband Capon beamforming method are proposed that use various algorithms for combining power spectra from different frequency bins. These methods are then implemented and benchmarked on a real acoustic signature data set that contains multiple ground targets moving in tight formations.

关键词： DOA estimation sparse sensor arrays steered covariance matrix Capon beamforming

来源：评论

学校读者我要写书评

暂无评论

The relationship between shape under similarity transformations and shape under affine transformations

The relationship between shape under similarity transformati...

引用

7th Conference on Mathematics of Data/Image Coding, Compression, and Encryption

作者： Stiller, PF Texas A&M Univ College Stn TX 77843 USA

ISBN: (纸本)0819454990

Recent progress in shape theory, including the development of object/image equations for shape matching and shape space metrics (especially object/image metrics), is now being exploited to develop new algorithms for target recognition. This theory makes use of advanced mathematical techniques from algebraic and differential geometry to construct generalized shape spaces for various projection and sensor models, and then uses that construction to find natural metrics that express the distance (difference) between two configurations of object features, two configurations of image features, or an object and an image pair. Such metrics produce the most robust tests for target identification;at least as far as target geometry is concerned. Moreover, they also provide the basis for efficient hashing schemes to do target identification quickly and provide a rigorous foundation for error analysis in ATR.

关键词： target recognition Algorithm development Image sensors algorithms Detection and tracking algorithms Matrices Sensors Error analysis Mathematical modeling Mathematics

来源：评论

学校读者我要写书评

暂无评论

A particle filtering framework with indirect measurements for visual tracking

A particle filtering framework with indirect measurements fo...

引用

8th International Conference on Control, Automation, Robotics and Vision (ICARCV 2004)

作者： Zhang, HH Huang, WM Huang, ZY Zhang, BL Inst Infocomm Res Singapore 119613 Singapore

ISBN: (纸本)0780386531

Particle filtering is a stochastic approach to Bayesian recursive inference. In many computer vision applications with limited number of random samples, however, conventional particle filters may find it difficult to accurately represent the desired aposteriori distribution especially for target objects with narrow likelihood functions. This paper proposes a new particle filtering framework which, by incorporating a special indirect measurement model, can significantly improve the representation capability of the particle set, yielding an accurate estimation of aposteriori distribution for the purpose of tracking. In particular, an add-on resampling technique is proposed to incorporate the indirect measurement. In this way, we can alleviate the problem with large numbers of particles required in conventional particle filtering. Positive experimental results on both synthetic sequences and real world videos are obtained.

关键词： Stochastic control systems

来源：评论

学校读者我要写书评

暂无评论

Optimal design of the variable structure IMM tracking filters using genetic algorithms

Optimal design of the variable structure IMM tracking filter...

引用

2004 ieeE International Conference on Control applications

作者： Vahabian, A. Sedigh, A. Khaki Akhbardeh, A. Electrical and Computer Inistitute Faculty of Eng. Tehran University Amir Abad Tehran Iran Electrical Engineering Department Khaje Nasir Adin Tossi University Tehran Iran Dept. of Electrical Eng. Iran University of Sci. and Technol. Narmak Tehran 16844 Iran

Genetic algorithms for optimization of the multiple model and variable structure estimators are discussed in this paper. The estimation algorithm based on the multiple model and variable structure, are the best approach used in many systems, including maneuvering target tracking, noise recognition, etc. The RAMS algorithm, asserts that a multiple model algorithm consists of three steps: model set adaptation, Initialization of model-based filters, and estimation. The first step, i.e., model set adaptation, is unique for VSMM algorithm and is the only superiority of the VSMM over FSMM. In this paper, after the graph theory is used for this step and the sub-optimal switching digraph algorithm is discussed, we will try to use the genetic algorithm for optimizing the thresholds used in the sub-optimal algorithm. The simulations show the improvement of the system performance when we use the optimal variable structure multiple model approach. © 2004 ieeE.

关键词： Genetic algorithms

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：