A Probabilistic Model-adaptive Approach for Tracking of Motion with Heightened Uncertainty

International Journal of Control, Automation and Systems - This paper presents an approach for state tracking in scenarios where motion is highly uncertain. The proposed approach improves on...     

A Coordinate-Invariant Approach to Multiresolution Motion Analysis

Multiresolution motion analysis has gained considerable research interest as a unified framework to facilitate a variety of motion editing tasks. Within this framework, motion data are represented as a collection of coefficients that form a coarse-to-fine hierarchy. The coefficients at the coarsest level describe the global pattern of a motion signal, while those at fine levels provide details at successively finer resolutions. Due to the inherent nonlinearity of the orientation space, the challenge is to generalize multiresolution representations for motion data that contain orientations as well as positions. Our goal is to develop a multiresolution analysis method that guarantees coordinate-invariance without singularity. To do so, we employ two novel ideas: hierarchical displacement mapping and motion filtering. Hierarchical displacement mapping provides an elegant formulation to describe positions and orientations in a coherent manner. Motion filtering enables us to separate motion details level-by-level to build a multiresolution representation in a coordinate-invariant way. Our representation facilitates multiresolution motion editing through level-wise coefficient manipulation that uniformly addresses issues raised by motion modification, blending, and stitching.     

Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation

We present a novel variational approach for segmenting the image plane into a set of regions of parametric motion on the basis of two consecutive frames from an image sequence. Our model is based on a conditional probability for the spatio-temporal image gradient, given a particular velocity model, and on a geometric prior on the estimated motion field favoring motion boundaries of minimal length.Exploiting the Bayesian framework, we derive a cost functional which depends on parametric motion models for each of a set of regions and on the boundary separating these regions. The resulting functional can be interpreted as an extension of the Mumford-Shah functional from intensity segmentation to motion segmentation. In contrast to most alternative approaches, the problems of segmentation and motion estimation are jointly solved by continuous minimization of a single functional. Minimizing this functional with respect to its dynamic variables results in an eigenvalue problem for the motion parameters and in a gradient descent evolution for the motion discontinuity set.We propose two different representations of this motion boundary: an explicit spline-based implementation which can be applied to the motion-based tracking of a single moving object, and an implicit multiphase level set implementation which allows for the segmentation of an arbitrary number of multiply connected moving objects.Numerical results both for simulated ground truth experiments and for real-world sequences demonstrate the capacity of our approach to segment objects based exclusively on their relative motion.     

A Multi-Orientation Analysis Approach to Retinal Vessel Tracking

This paper presents a method for retinal vasculature extraction based on biologically inspired multi-orientation analysis. We apply multi-orientation analysis via so-called invertible orientation scores, modeling the cortical columns in the visual system of higher mammals. This allows us to generically deal with many hitherto complex problems inherent to vessel tracking, such as crossings, bifurcations, parallel vessels, vessels of varying widths and vessels with high curvature. Our approach applies tracking in invertible orientation scores via a novel geometrical principle for curve optimization in the Euclidean motion group SE(2). The method runs fully automatically and provides a detailed model of the retinal vasculature, which is crucial as a sound basis for further quantitative analysis of the retina, especially in screening applications.     

A Neural Network Approach to Tracking Eye Position

The design of a neural network based eye tracker is presented. A series of experiments with counterpropagation neural networks convert synthetic video images into eye coordinates by an enhanced feed-forward neural network with multiple winning hidden layer nodes. Difficulties encountered during the design process are discussed. The results show that accurate, fine-grained tracking of a human's eye position is possible by processing the video image collected from a goggle-mounted miniature charge-coupled device (CCD) camera.     

A Hybrid Approach to Nonconformance Tracking and Recovery

The nonconformance diagnosis problem has been a major issue facing industry and academia over the years. Research has been carried out on technologies for different aspects of nonconformance diagnosis such as nonconformance monitoring, prediction, prevention, classification, tracking, and recovery. Despite these advances, nonconformance tracking and recovery still receive many concerns due to the fact that they are knowledge intensive and experience-based tasks, which in complex manufacturing environments can sometimes be beyond the capabilities of skilled operators and engineers. In addition, the existing systems for nonconformance tracking and recovery are usually special purpose systems. They lack the capabilities to migrate to new working domains. This paper proposes a generic intelligent nonconformance tracking and recovery (GINTR) system. In conjunction with computational intelligent techniques such as Artificial Neural Networks (ANN) and Genetic Algorithm (GA), the system identifies the root causes of a nonconformance and provides timely corrective actions. The drive towards designing such a system is motivated by the need to implement a generic base of system capabilities that is reliable, economical, scalable, and provides a stable foundation for migrating the system to different domains.     

心脏序列图像运动估计新方法:基于广义模糊梯度矢量流场的形变曲线运动估计与跟踪

应用动态轮廓线模型(ACM)解决心脏运动估计问题是该领域的主要研究方法之一．采用经典外力和传统ACM模型对感兴趣边缘进行搜索及跟踪时，普遍存在模型的局部适应性程度不高的缺陷．为解决这一挑战性难题，该文提出了广义模糊梯度矢量流(GFGVF)的概念，并构造出一组新的Snake平衡方程，该方程可对心脏内部边缘逐帧进行鲁棒跟踪．为进一步跟踪每一特征点的运动，该文将前一步的轮廓跟踪结果作为似然条件，结合一致性和连续性先验条件，通过最大后验概率(MAP)的方法对整个过程进行了优化计算．通过对MR及CT两类心脏序列图像进行运动跟踪实验并对计算结果进行多种比较，此方法显示了较好的鲁棒性．     

红外成像运动目标识别与跟踪方法研究

针对运动目标红外成像噪声大的特点,给出了一个用于红外序列图像模式识别与跟踪的设计方法。其中重点介绍了用复合方法去除图像中的红外噪声,以及根据飞行目标的运动特性,给出了抽取平移不变性和旋转不变性模式特征的方法,同时还给出了一个基于时间相关性原理的目标跟踪新方法     

磁偶极子跟踪的渐进贝叶斯滤波方法

提出一种新的非线性滤波器应用于磁偶极子目标跟踪问题.建立了跟踪问题的状态空间模型, 在此基础上, 从高斯矩近似误差的角度分析了现有卡尔曼滤波更新在磁偶极子跟踪中的问题.对此, 将贝叶斯更新过程等效为求解连续时间上的渐进贝叶斯问题, 在线性高斯条件下推导了其解析解, 表明渐进贝叶斯更新可等效为定常系统的Kalman-Bucy滤波器; 进一步采用一阶Taylor展开得到非线性近似解表达式, 导出一种渐进贝叶斯滤波器, 从理论上分析了与现有方法的异同.仿真与实测磁目标跟踪试验结果表明, 渐进贝叶斯滤波器具有良好的精度和收敛性, 能够有效抑制磁目标跟踪中由于大初始误差导致的性能下降和滤波发散, 且计算效率与扩展卡尔曼滤波器相当, 适于实际应用.     

一种新的FAST-Snake目标跟踪方法

提出一种新的FAST-Snake目标跟踪方法,利用改进的FAST角点特征匹配来估计目标轮廓在帧间的全局仿射变换,将投影轮廓点作为Snake模型的初始化轮廓.为提高跟踪实时性,在Snake能量模型中定义了先验约束能,并用限定搜索方向的贪婪算法（Greedy algorithm）实现局部轮廓优化.实验包括三维目标数据库及真实场景视频,验证了提出方法的均方误差（Means quare error,MSE）及收敛速度评估均优于对比算法,并具备对复杂运动及局部遮挡的适应能力.     

A Probabilistic Approach to Tracking Moving Targets With Distributed Sensors

Tracking a moving target is a difficult task in a distributed sensor network due to the lack of knowledge of the target's motion and signal noises. Several existing approaches use only sensory information or may require accurate target's motion models. In this paper, we present a Markovian approach that combines dynamically estimated target's motion models with received sensory information. The approach localizes a target by using the estimated motion models and the provided sensory model. We characterize probabilistic conditions under which the estimation accuracy increases if more sensors are used, and the estimations converge to the target's real position asymptotically. Our experimental analysis shows that our approach leads to substantially more accurate and robust location estimations than the previous approaches using only sensory information, and it is competitive with the standard Markov localization approach.     

一种基于多分辨率的图像跟踪算法

提出了一种基于多分辨率的图像处理方法，图像在不同分辨率的层上进行处理，从而获得较快的处理速度，同时保证了一定的鲁棒性。     

基于掩模金字塔的高精度全局运动估计算法

在视频序列的全局运动估计中,前景运动对象的存在常常会大幅度地降低估计的精度,为此提出一种对前景对象自适应的高精度全局运动估计算法.该算法以像素块为单位,利用块内外点的比重判定前景区域,同时引入马尔可夫聚类方法进行后处理,有效地提高了运动对象的定位精度;通过对目标函数引入权重系数增强对残差的鲁棒性,以进一步提高算法的估计精度.此外,基于像素掩模的3层金字塔构建序列图像,并将改进的梯度方法引入到优化过程中,提高了算法的实时性.对不同运动类型的标准视频序列的实验结果表明,该算法有效地提高了全局运动估计的精度和速度.     

Tracking and Motion Estimation of the Articulated Object: a Hierarchical Kalman Filter Approach

Real-time motion capture plays a very important role in various applications, such as 3D interface for virtual reality systems, digital puppetry, and real-time character animation. In this paper we challenge the problem of estimating and recognizing the motion of articulated objects using theoptical motion capturetechnique. In addition, we present an effective method to control the articulated human figure in realtime.The heart of this problem is the estimation of 3D motion and posture of an articulated, volumetric object using feature points from a sequence of multiple perspective views. Under some moderate assumptions such as smooth motion and known initial posture, we develop a model-based technique for the recovery of the 3D location and motion of a rigid object using a variation of Kalman filter. The posture of the 3D volumatric model is updated by the 2D image flow of the feature points for all views. Two novel concepts – the hierarchical Kalman filter (KHF) and the adaptive hierarchical structure (AHS) incorporating the kinematic properties of the articulated object – are proposed to extend our formulation for the rigid object to the articulated one. Our formulation also allows us to avoid two classic problems in 3D tracking: the multi-view correspondence problem, and the occlusion problem. By adding more cameras and placing them appropriately, our approach can deal with the motion of the object in a very wide area. Furthermore, multiple objects can be handled by managing multiple AHSs and processing multiple HKFs.We show the validity of our approach using the synthetic data acquired simultaneously from the multiple virtual camera in a virtual environment (VE) and real data derived from a moving light display with walking motion. The results confirm that the model-based algorithm works well on the tracking of multiple rigid objects.     

一种综合运动检测和视觉跟踪的智能监控系统

智能监控是当前计算机视觉领域中的热点问题之一。本文提出了一种运动检测与视觉跟踪相结合的智能监控系统,能自动完成轨迹的初始化和终止,能够对数目可变的目标进行自动跟踪。该系统首先利用基于颜色空间模型的阈值化背景减法提取出运动目标,然后结合基于MCMC的颜色粒子滤波器和全局最近邻法对多个目标进行跟踪。并基于OpenCV机器视觉库搭建了智能视频监控平台。实验表明,该系统可以实时有效地检测、跟踪数目变化不定的运动物体。     

一种基于运动轮廓的目标跟踪方法

为了解决目标跟踪中出现的遮挡问题,提出了一种基于运动轮廓的日标跟踪方法.通过对当前帧前面两帧图像统计加权来获得背景,并通过网格化加速了目标检测效率,降低了运算次数;然后采用的背景差分法来提取运动轮廓,通过运动轮廓获取目标相关特征进行跟踪,并采用结合基于运动轮廓色度匹配及卡尔曼滤波预测的方法进行遮挡问题的判断和处理.仿真实验结果表明算法可以准确地跟踪目标,并能很好的处理跟踪时出现的遮挡及互遮挡问题.     

机动目标跟踪的滤波方法研究

目标跟踪应用中,一类常见的混合估计问题是:目标运动建模在直角坐标系下且是非线性的,同时量测数据由传感器直接获得.通常处理该问题的做法是使用推广卡尔曼滤波器,但效果欠佳.为此,通过将无迹变换(UT)和BLUE算法相结合,提出了一种新型的UT-BLUE滤波器.该滤波器首先利用无迹变换对直角坐标系中的目标状态及其协方差作出预测,然后在保持传感器坐标系(极坐标系)下所固有的量测误差的同时,直接对它们作出更新估计.通过仿真, 将UT-BLUE滤波方法和EKF滤波方法进行比较,表明了该滤波方法的有效性和优越性.     

A Sampling-Based Motion Planning Approach to Maintain Visibility of Unpredictable Targets

This paper deals with the surveillance problem of computing the motions of one or more robot observers in order to maintain visibility of one or several moving targets. The targets are assumed to move unpredictably, and the distribution of obstacles in the workspace is assumed to be known in advance. Our algorithm computes a motion strategy by maximizing the shortest distance to escape—the shortest distance the target must move to escape an observer's visibility region. Since this optimization problem is intractable, we use randomized methods to generate candidate surveillance paths for the observers. We have implemented our algorithms, and we provide experimental results using real mobile robots for the single target case, and simulation results for the case of two targets-two observers. Rafael Murrieta-Cid received the B.S degree in Physics Engineering (1990), and the M.Sc. degree in Automatic Manufacturing Systems (1993), both from “Instituto Tecnológico y de Estudios Superiores de Monterrey” (ITESM) Campus Monterrey. He received his Ph.D. from the “Institut National Polytechnique” (INP) of Toulouse, France (1998). His Ph.D research was done in the Robotics and Artificial Intelligence group of the LAAS/CNRS. In 1998–1999, he was a postdoctoral researcher in the Computer Science Department at Stanford University. From January 2000 to July 2002 he was an assistant professor in the Electrical Engineering Department at ITESM Campus México City, México. In 2002–2004, he was working as a postdoctoral research associate in the Beckman Institute and Department of Electrical and Computer Engineering of the University of Illinois at Urbana-Champaign. Since August 2004, he is director of the Mechatronics Research Center in the ITESM Campus Estado de México, México. He is mainly interested in sensor-based robotics motion planning and computer vision. Benjamin Tovar received the B.S degree in electrical engineering from ITESM at Mexico City, Mexico, in 2000, and the M.S. in electrical engineering from University of Illinois, Urbana-Champaign, USA, in 2004. Currently (2005) he is pursuing the Ph.D degree in Computer Science at the University of Illinois. Prior to M.S. studies he worked as a research assistant at Mobile Robotics Laboratory at ITESM Mexico City. He is mainly interested in motion planning, visibility-based tasks, and minimal sensing for robotics. Seth Hutchinson received his Ph. D. from Purdue University in West Lafayette, Indiana in 1988. He spent 1989 as a Visiting Assistant Professor of Electrical Engineering at Purdue University. In 1990 Dr. Hutchinson joined the faculty at the University of Illinois in Urbana-Champaign, where he is currently a Professor in the Department of Electrical and Computer Engineering, the Coordinated Science Laboratory, and the Beckman Institute for Advanced Science and Technology. Dr. Hutchinson is currently a senior editor of the IEEE Transactions on Robotics and Automation. In 1996 he was a guest editor for a special section of the Transactions devoted to the topic of visual servo control, and in 1994 he was co-chair of an IEEE Workshop on Visual Servoing. In 1996 and 1998 he co-authored papers that were finalists for the King-Sun Fu Memorial Best Transactions Paper Award. He was co-chair of IEEE Robotics and Automation Society Technical Committee on Computer and Robot Vision from 1992 to 1996, and has served on the program committees for more than thirty conferences related to robotics and computer vision. He has published more than 100 papers on the topics of robotics and computer vision.     

A Fast Approach for Robot Motion Planning

This paper describes a new approach to robot motion planning that combines the end-point motion planning with joint trajectory planning for collision avoidance of the links. Local and global methods are proposed for end-point motion planning. The joint trajectory planning is achieved through a pseudoinverse kinematic formulation of the problem. This approach enables collision avoidance of the links by a fast null-space vector computation. The power of the proposed planner derives from: its speed; the good properties of the potential function for end-point motion planning; and from the simultaneous avoidance of the links collision, kinematic singularities, and local minima of the potential function. The planner is not defined over computationally expensive configuration space and can be applied for real-time applications. The planner shows to be faster than many previous planners and can be applied to robots with many degrees of freedom. The effectiveness of the proposed local and global planning methods as well as the general robot motion planning approach have been experimented using the computer-simulated robots. Some of the simulation results are included in this paper.     

A Self-Organizing Context-Based Approach to the Tracking of Multiple Robot Trajectories

We have combined competitive and Hebbian learning in a neural network designed to learn and recall complex spatiotemporal sequences. In such sequences, a particular item may occur more than once or the sequence may share states with another sequence. Processing of repeated/shared states is a hard problem that occurs very often in the domain of robotics. The proposed model consists of two groups of synaptic weights: competitive interlayer and Hebbian intralayer connections, which are responsible for encoding respectively the spatial and temporal features of the input sequence. Three additional mechanisms allow the network to deal with shared states: context units, neurons disabled from learning, and redundancy used to encode sequence states. The network operates by determining the current and the next state of the learned sequences. The model is simulated over various sets of robot trajectories in order to evaluate its storage and retrieval abilities; its sequence sampling effects; its robustness to noise and its tolerance to fault.