检索结果-内蒙古大学图书馆

A multiple object tracking approach that combines colour and depth information using a confidence measure

PATTERN RECOGNITION LETTERS 2008年第10期29卷 1504-1514页

作者： Munoz-Salinas, Rafael Aguirre, Eugenio Garcia-Silvente, Miguel Gonzalez, Antonio Univ Cordoba Dept Comp & Numer Anal E-14071 Cordoba Spain Univ Granada Dept Comp Sci & Artificial Intelligence E-18071 Granada Spain

Multiple object tracking is a difficult task, especifically when there is not an explicit model of the object being tracked or when it is not possible to estimate the background of the scene. This paper proposes a novel approach for multiple target tracking. It works without background information and uses an original method that merges colour and depth information. The fusion of both pieces of information is created taking into account a confidence measure about the depth information. The method proposed employs a multiple particle filter approach in which particle weights are modified by an interaction factor in order to avoid the "coalescence" problem. In addition, the method performs as a pure colour-based technique when no disparity information is available, and takes advantage of depth information to enhance tracking whenever it is possible. Our technique is compared with two pure colour-based tracking approaches (the particle filtering method proposed by Nummiaro et al. [Nummiaro, K., Koller-Meier, E., Van Gool, L., 2003. An adaptive color-based particle filter. Image and Vision Computing, 21, 99-110] and the Kalman/mean-shift tracker [Comaniciu, D., Ramesh, V. 2000. Mean shift and optimal prediction for efficient object tracking. In: IEEE International Conference on Image Processing (ICIP'00), vol. 3, pp. 70-73]) and a pure stereo-based approach derived from our problem formulation. The performance of the four algorithms is tested using several colour-with-depth sequences of images showing different coloured targets in complex situations. The results show that our proposal is able to track the targets in case of complex backgrounds and to properly determine the size of their projections in the camera image (while the other methods fail). Besides, the proposed method is fast enough for real-time applications and the use of 3D information helps to track several targets simultaneously without confusing their identities. (C) 2008 Elsevier B.V. All rights reserve

关键词： multiple particle filtering stereo vision colour processing mean-shift condensation algorithm confidence measure

来源：评论

学校读者我要写书评

暂无评论

Improved μ-analysis results by using low-order uncertainty modeling techniques

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2008年第4期31卷 962-969页

作者： Hecker, Simon German Aerosp Ctr DLR D-82234 Wessling Germany

The paper describes some recent enhancements of symbolic factorization techniques for multivariate Laurent polynomial matrices, which are very effective as a preprocessing step for generating linear fractional representations of low order. The symbolic methods are applied to realize a linear fractional representation of full accuracy and probably minimal order for a very complex linear parametric representation of a Research Civil Aircraft Model. The mu-analysis results obtained with the very accurate and low-order linear fractional representation coincide with the robust stability analysis results obtained from a computationally demanding, optimization-based, worst-case search. Furthermore, it is shown that the quality of the it-analysis results depends on the accuracy and order of the underlying model, i.e., the tightest upper and lower bounds are obtained using the most accurate and least-order linear fractional representation.

关键词： Civil Aircraft Hankel Singular Value MATLAB condensation condensation algorithm Monte Carlo Analysis Flight Control Airspeed State Space Systems Wing Planforms

来源：评论

学校读者我要写书评

暂无评论

Genetic condensation for motion tracking

引用

SOFT COMPUTING 2007年第4期11卷 349-354页

作者： Ye, Zhu Liu, Zhi-Qiang City Univ Hong Kong Sch Creat Media Hong Kong Hong Kong Peoples R China

Tracking serves as a means to prepare data for pose estimation and action recognition. The condensation algorithm is a conditional density propagation method for motion tracking. This algorithm combines factored sampling with learned dynamic models to propagate an entire probability distributes for object position and shape over time. It can accomplish highly robust tracking of object motion. However, it usually requires a large number of samples to ensure a fair maximum likelihood estimation of the current state. In this paper, we use the mutation and crossover operators of the genetic algorithm to find appropriate samples. With this approach, we are able to improve robustness, accuracy and flexibility in condensation for visual tracking.

关键词： tracking condensation algorithm factored sampling genetic algorithm metropolis algorithm

来源：评论

学校读者我要写书评

暂无评论

A computational model for C-elegans locomotory behavior:: Application to multiworm tracking

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2007年第10期54卷 1786-1797页

作者： Roussel, Nicolas Morton, Christine A. Finger, Fern P. Roysam, Badrinath Rensselaer Polytech Inst Dept Elect Comp & Syst Engn NSF Ctr Subsurface Sensing & Imaging Syst Troy NY 12180 USA Rensselaer Polytech Inst Dept Elect & Comp Syst Engn Troy NY 12180 USA Rensselaer Polytech Inst Dept Biol Troy NY 12180 USA

computational approach is presented for modeling and quantifying the structure and dynamics of the nematode C elegans observed by time-lapse microscopy. Worm shape and conformations are expressed in a decoupled manner. Complex worm movements are expressed in terms of three primitive patterns-peristaltic progression, deformation, and translation. The model has been incorporated into algorithms for segmentation and simultaneous tracking of multiple worms in a field, some of which may be interacting in complex ways. A recursive Bayesian filter is used for tracking. Unpredictable behaviors associated with interactions are resolved by multiple-hypothesis tracking. Our algorithm can track worms of diverse sizes and conformations (coiled/uncoiled) in the presence of imaging artifacts and clutter, even when worms are overlapping with others. A two-observer performance assessment was conducted over 16 image sequences representing wild-type and uncoordinated mutants as a function of worm size, conformation, presence of clutter, and worm entanglement. Overall detected tracking failures were 1.41 %, undetected tracking failures were 0.41 %, and segmentation errors were 1.11% of worm length. When worms overlap, our method reduced undetected failures from 12% to 1.75%, and segmentation error from 11% to 5%. Our method provides the basis for reliable morphometric and locomotory analysis of freely behaving worm populations.

关键词： C. elegans condensation algorithm functional modeling high-throughput multi-object tracking

来源：评论

学校读者我要写书评

暂无评论

Coupled hidden markov models for robust EO/IR target tracking

Coupled hidden markov models for robust EO/IR target trackin...

引用

IEEE International Conference on Image Processing (ICIP 2007)

作者： Gai, Jiading Li, Yong Stevenson, Robert L. Univ Notre Dame Dept Elect Engn Notre Dame IN 46556 USA

ISBN: (纸本)9781424414369

Augmenting Electro-Optical (EO) based target tracking systems with Infrared (IR) modality has been shown to be effective in increasing the accuracy rate of the tracking system. A key issue in designing such a multimodal tracking system is how to combine information observed from different sensor types in a systematic way to obtain desirable performance. In this paper, we present an investigation into integrating EO and IR sensors within Hidden Markov Model (HMM) based frameworks. We propose to use a Coupled Hidden Markov Model (CHMM) to improve upon the existing fusion schemes. Another contribution is that we propose to use a robust t-distribution based subspace representation in the CHMM to model appearance changes of the target. Numerical experiments demonstrate that the proposed CHMM tracking system has improved performance over other integration schemes for situations where the target object is corrupted by noise or occlusion.

关键词： coupled hidden markov model target tracking subspace representation t-distribution condensation algorithm

来源：评论

学校读者我要写书评

暂无评论

Tracking objects using particle filters

Tracking objects using particle filters

引用

49th International Symposium ELMAR

作者： Senji, Ivan Kalafatic, Zoran IN2 Marohniceva 1-1 Zagreb 10000 Croatia Univ Zagreb Fac Elect & Comp Engn Zagreb 10000 Croatia

ISBN: (纸本)9789537044053

This paper describes an implementation of particle filter tracker based on condensation algorithm. The filter processes measurements as they become available in a standard predict-update loop. The prediction phase uses the available dynamic model to predict the probability density function in the next time step, by applying both the deterministic and stochastic component of the model to all samples. In the update phase the new measurement is used to update the probability density function by updating the weight of each sample. The goal of this work was to investigate the possibilities of object tracking without learning a dynamic motion model. Changes to the basic algorithm have been implemented that can help to improve the tracking performance by using more than one motion model and more than one predict-update iteration per measurement.

关键词： particle filter condensation algorithm probability density function dynamic model

来源：评论

学校读者我要写书评

暂无评论

Real-time hand gesture recognition using pseudo 3-D hidden markov model

Real-time hand gesture recognition using pseudo 3-D hidden m...

引用

5th IEEE International Conference on Cognitive Informatics (ICCI 2006)

作者： Binh, Nguyen Dang Ejima, Toshiaki Kyushu Inst Technol Intelligence Media Lab 820-4 Kawazu Iizuka Fukuoka 820 Japan

ISBN: (纸本)9781424404759

In the following work we present a new approach to recognition of hand gesture based on pseudo three-dimensional Hidden Markov Model (P3DHMM), a technique which can integrate spatial as well as temporal derived features in an elegant and efficient way. Additionally, robust and flexible hand gesture tracking using an appearance-based condensation tracker. These allow the recognition of dynamic gestures as well as more static gestures. Furthermore, there has been proposed to improve the overall performance of the approach: Replace Baum-Welch algorithm with clustering algorithm, adding a clustering performance measure to the clustering algorithm and adaptive threshold gesture to remove non-gesture pattern that helps to qualify an input pattern as a gesture. Proposed improving methods along with the P3DHMM was used to develop a complete Japanese Kana hand alphabet recognition system consisting of 42 static postures and 34 hand motions. We obtained a recognition rate of 99.1% in the gesture recognition experiments when compared to P2DHMMs.

关键词： pseudo 3-D Hidden Markov Model hand gesture recognition condensation algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-time object tracking and segmentation using adaptive color snake model

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2006年第2期4卷 236-246页

作者： Seo, KH Shin, JH Kim, W Lee, JJ Korea Adv Inst Sci & Technol Dept Elect Engn & Comp Sci Taejon 305701 South Korea Dong Eui Univ Dept Mechatron Engn Pusan 614714 South Korea

Motion tracking and object segmentation are the most fundamental and critical problems in vision tasks such as motion analysis. An active contour model, snake, was developed as a useful segmenting and tracking tool for rigid or non-rigid objects. In this paper, the development of new snake model called "adaptive color snake model (ACSM)" for segmentation and tracking is introduced. The simple operation makes the algorithm runs in real-time. For robust tracking, the condensation algorithm was adopted to control the parameters of ACSM. The effectiveness of the ACSM is verified by appropriate simulations and experiments.

关键词： active contours condensation algorithm object tracking image segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-time facial pose identification with hierarchically structured ML pose classifier

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2004年第2期18卷 127-142页

作者： Sung, JW Kim, D Pohang Univ Sci & Technol Dept Comp Sci & Engn Pohang 790784 South Korea

Since pose-varying face images form nonlinear convex manifold in high dimensional image space, it is difficult to model their pose distribution in terms of a simple probabilistic density function. To solve this difficulty, we divide the pose space into many constituent pose classes and treat the continuous pose estimation problem as a discrete pose-class identification problem. We propose to use a hierarchically structured ML (Maximum Likelihood) pose classifiers in the reduced feature space to decrease the computation time for pose identification, where pose space is divided into several pose groups and each group consists of a number of similar neighboring poses. We use the condensation algorithm to find a newly appearing face and track the face with a variety of poses in real-time. Simulation results show that our proposed pose identification using the hierarchically structured ML pose classifiers can perform a faster pose identification than conventional pose identification using the flat structured ML pose classifiers. A real-time facial pose tracking system is built with high speed hierarchically structured ML pose classifiers.

关键词： face detection pose identification skin color model condensation algorithm hierarchically structured ML pose classifier

来源：评论

学校读者我要写书评

暂无评论

Tracking multiple objects using the condensation algorithm

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2001年第2-3期34卷 93-105页

作者： Koller-Meier, EB Ade, F Swiss Fed Inst Technol Commun Technol Lab CH-8092 Zurich Switzerland

Some years ago a new tracker, the condensation algorithm, came to be known in the computer vision community. It describes a stochastic approach that has neither restrictions on the system and measurement models used nor on the distributions of the error sources, but it cannot track an arbitrary changing number of objects. In this paper an extension of the condensation algorithm is introduced that relies on a single probability distribution to describe the likely states of multiple objects. By introducing an initialization density, observations can flow directly into the tracking process, such that newly appearing objects can be handled. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： tracking recursive Bayesian filter condensation algorithm Monte Carlo filter Kalman filter

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：