Incremental Learning for Robust Visual Tracking

Visual tracking, in essence, deals with non-stationary image streams that change over time. While most existing algorithms are able to track objects well in controlled environments, they usually fail in the presence of significant variation of the object’s appearance or surrounding illumination. One reason for such failures is that many algorithms employ fixed appearance models of the target. Such models are trained using only appearance data available before tracking begins, which in practice limits the range of appearances that are modeled, and ignores the large volume of information (such as shape changes or specific lighting conditions) that becomes available during tracking. In this paper, we present a tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target. The model update, based on incremental algorithms for principal component analysis, includes two important features: a method for correctly updating the sample mean, and a forgetting factor to ensure less modeling power is expended fitting older observations. Both of these features contribute measurably to improving overall tracking performance. Numerous experiments demonstrate the effectiveness of the proposed tracking algorithm in indoor and outdoor environments where the target objects undergo large changes in pose, scale, and illumination.     

一种机器人轨迹的鲁棒跟踪控制

把基于拉格朗日方程的n关节机器人动力学模型,转化成了一线性状态方程.基于这种线性状态方程,利用李雅普诺夫函数方法分别针对机器人标称模型和有外界不确定性干扰时,设计前馈控制器和反馈控制器,使得机器人的实际运动轨迹在标称模型下,指数收敛于所给定的期望运动轨迹;在有外界不确定性干扰时,它与期望轨迹的误差是终值有界的.并且,针对后者所提出的控制律进行仿真.仿真结果表明,这种连续鲁棒控制律对于机器人系统存在外界不确定性干扰时是十分有效的.     

一类具有不确定的互联大系统分散鲁棒输出跟踪控制器设计

针对一类具有不确定的互联大系统,研究了使受控系统鲁棒稳定和渐近跟踪参考输入的分散鲁棒跟踪控制器的设计问题,并对具有分散反馈控制器的闭环大系统,给出了其鲁棒稳定以及渐近跟踪的证明。     

基于反馈线性化同步伺服电机鲁棒跟踪控制

为了保证具有不确定非线性的PM同步伺服电机驱动系统的稳定性,确保闭环系统的输出准确跟踪期望输出并减少不确定项对该驱动系统的影响,利用Lyapunov稳定性理论,设计了一种基于反馈线性化的鲁棒跟踪控制器,并作了相应的仿真研究。仿真结果表明,该控制器不仅确保闭环系统的输出按指数规律跟踪期望输出,而且保证闭环系统状态的一致最终有界。该控制器设计简单,易于实现,具有很好的实用性。     

Design of a Robust Adaptive Neural Tracking Controller

A robust neural tracking controller is designed based on the conic sector theory. An adaptive dead zone scheme is employed to enhance robustness of the system. The proposed algorithm does not require knowledge of either the upper bound of disturbance or the bound on the norm of the estimate parameter. A complete convergence proof is provided based on the sector theory to deal with the nonlinear system. Simulation results are presented to control a two-link direct drive robot and show the performance of the tracking controller.     

Pruning Based Robust Backpropagation Training Algorithm for RBF Network Tracking Controller

A pruning based robust backpropagation training algorithm is proposed for the online tuning of the Radial Basis Function(RBF) network tracking control system. The structure of the RBF network controller is derived using a filtered error approach. The proposed method in this paper begins with a relatively large network, and certain neural units of the RBF network are dropped by examining the estimation error increment. A complete convergence proof is provided in the presence of disturbance.     

Robust Tracking Using Foreground-Background Texture Discrimination

This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting. This work was done while the first author was at the Intelligent Sensory Information Systems group, Faculty of Science, University of Amsterdam, The Netherlands.     

An Intelligent Robust Tracking Control for a Class of Electrically Driven Mobile Robots

This paper addresses the problem of designing robust tracking control for a class of uncertain wheeled mobile robots actuated by brushed direct current motors. This class of electrically‐driven mechanical systems consists of the robot kinematics, the robot dynamics, and the wheel actuator dynamics. Via the backstepping technique, an intelligent robust tracking control scheme that integrates a kinematic controller and an adaptive neural network‐based (or fuzzy‐based) controller is developed such that all of the states and signals of the closed‐loop system are bounded and the tracking error can be made as small as possible. Two adaptive approximation systems are constructed to learn the behaviors of unknown mechanical and electrical dynamics. The effects of both the approximation errors and the unmodeled time‐varying perturbations in the input and virtual‐input weighting matrices are counteracted by suitably tuning the control gains. Consequently, the robust control scheme developed here can be employed to handle a broader class of electrically‐driven wheeled mobile robots in the presence of high‐degree time‐varying uncertainties. Finally, a simulation example is given to demonstrate the effectiveness of the developed control scheme.     

基于目标分块多特征核稀疏表示的视觉跟踪

大多数现有的基于稀疏表示的跟踪器仅采用单个目标特征来描述感兴趣的目标,因而在处理各种复杂视频时不可避免会出现跟踪不稳定的情况。针对这个问题,提出一种基于多特征联合稀疏表示的粒子滤波跟踪算法。该算法的主要思想是对随时间不断更新的字典模板和抽样粒子的局部块依据其位置进行分类,用字典中所有类别块对抽样粒子的局部块进行稀疏表示,而仅用与字典中具有相同类别的局部块及表示系数进行重构,根据重构误差构建似然函数以确定最佳粒子（候选目标）,实现对目标的精确跟踪。该方法不仅实现了局部块的结构稀疏性,而且充分考虑了粒子之间的依赖关系,提高了跟踪精度。将算法进一步推广到采用基于核的多种特征描述,经混合范数约束并利用 KAPG （kernelizable accelerated proximal gradient ）方法求解联合特征的稀疏系数。定性和定量的实验结果均表明该算法在目标发生遮挡、旋转、尺度变化、快速运动、光照变化等各种复杂情况下,依然可以准确地跟踪目标。     

Robust H∞ Tracking Control of Uncertain Robotic Systems with Periodic Disturbances

This paper addresses the problem of designing robust tracking control for a large class of uncertain robotic systems. A more general model of the external disturbance is employed in the sense that the external disturbance can be expressed as the sum of a modeled disturbance and an unmodeled disturbance, for example, any periodic disturbance can be expressed in this general form. An adaptive neural network system is constructed to approximate the behavior of unknown robot dynamics. An adaptive control algorithm is designed to estimate the behavior of the modeled disturbance, and in turn the robust H_∞ control algorithm is required to attenuate the effects of the unmodeled disturbance only. Consequently, an intelligent adaptive/robust tracking control scheme is constructed such that an H_∞ tracking control is achieved in the sense that all the states and signals of the closed‐loop system are bounded and the effect due to the unmodeled disturbance on the tracking error can be attenuated to any preassigned level. Finally, simulations are provided to demonstrate the effectiveness and performance of the proposed control algorithm.     

基于多模型及SVM的单人脸跟踪系统

针对彩色视频中的人脸检测与跟踪问题，使用运动模型和自适应肤色模型，从图像中快速提取出人脸候选区，然后利用基于先验规则和SVM的方法进行确认。对于被确认的人脸，建立一个人脸状态记录表，通过位置预测，使用三步搜索法进行人脸区域色度特征匹配跟踪。实验表明，本文提出的方法，在复杂的环境中，能实时地、精度较高地跟踪自由运动的人脸。     

Hybrid Control Scheme for Robust Tracking of Two-Link Flexible Manipulator

A hybrid control scheme is proposed to stabilize the vibration of a two-link flexible manipulator while robustness of Variable Structure Control (VSC) developed for rigid manipulators is maintained for controlling the joint angles. The VSC law alone, which is designed to accomplish only the asymptotic decoupled joint angle trajectory tracking, does not guarantee the stability of the flexible mode dynamics of the links. In order to actively suppress the flexible link vibrations, hybrid trajectories for the VSC are generated using the virtual control force concept, so that robust tracking control of the flexible-link manipulator can also be accomplished. Simulation results confirm that the proposed hybrid control scheme can achieve more robust tracking control of two-link flexible manipulator than the conventional control scheme in the presence of payload uncertainty.     

Hybrid Control Scheme for Robust Tracking of Two-Link Flexible Manipulator

The hybrid control scheme is proposed to stabilize the vibration of a two-link flexible manipulator while the robustness of Variable Structure Control (VSC) developed for rigid manipulators is maintained for controlling the joint angles. The VSC law alone, which is designed to accomplish only the asymptotic decoupled joint angle trajectory tracking, does not guarantee the stability of the flexible mode dynamics of the links. In order to actively suppress the flexible link vibrations, hybrid trajectories for the VSC are generated using the virtual control force concept, so that robust tracking control of the flexible-link manipulator can also be accomplished. Simulation results confirm that the proposed hybrid control scheme can achieve more robust tracking control of two-link flexible manipulator than the conventional control scheme in the presence of payload uncertainty.     

非线性系统的神经网络鲁棒自适应跟踪控制

针对一类具有未知非线性函数和未知虚拟系数非线性函数的二阶非线性系统,提出了一种神经网络鲁棒自适应输出跟踪控制方法.用李雅普诺夫稳定性分析方法证明了本文的神经网络自适应控制器能够使受控系统内的所有信号均为有界.选择的神经网络权值调整规律可以防止自适应控制中的参数漂移.     

Robust Visual Tracking Based on Convolutional Features with Illumination and Occlusion Handing

视觉追踪是在计算机视觉的一个重要区域。怎么处理照明和吸藏问题是一个挑战性的问题。这份报纸论述一篇小说和有效追踪算法处理如此的问题。一方面,一起始的外观总是有的目标清除轮廓,它对照明变化光不变、柔韧。在另一方面,特征在追踪起一个重要作用,在哪个之中 convolutional 特征显示出有利性能。因此,我们采用卷的轮廓特征代表目标外观。一般来说,一阶的衍生物边坡度操作员在由卷检测轮廓是有效的他们与图象。特别, Prewitt 操作员对水平、垂直的边更敏感,当 Sobel 操作员对斜边更敏感时。内在地, Prewitt 和 Sobel 与对方一起是补足的。技术上说,这份报纸设计二组 Prewitt 和 Sobel 边察觉者提取一套完全的 convolutional 特征,它包括水平、垂直、斜的边特征。在第一个框架,轮廓特征从目标被提取构造起始的外观模型。在有这些轮廓特征的试验性的图象的分析以后,明亮的部分经常提供更有用的信息描述目标特征,这能被发现。因此,我们建议一个方法比较候选人样品和我们仅仅使用明亮的象素的训练模型的类似,它使我们的追踪者有能力处理部分吸藏问题。在得到新目标以后,变化以便改编外观,我们建议相应联机策略逐渐地更新我们的模型。convolutional 特征由井综合的 Prewitt 和 Sobel 边察觉者提取了的实验表演能是足够有效的学习柔韧的外观模型。九个挑战性的序列上的众多的试验性的结果证明我们的建议途径与最先进的追踪者比较很有效、柔韧。     

基于人脸检测的人脸跟踪算法

文章提出了一种基于人脸检测技术的人脸跟踪算法。该算法利用前一帧的人脸检测结果预测当前帧中人脸可能的尺度与位置范围,在限定的范围内采用模板匹配与人工神经网分类的方法定位人脸,从而实现快速而可靠的人脸跟踪。由于使用了人脸检测技术,该方法可以自动定位初始人脸。实验表明该方法在具有复杂、动态变化背景的图象序列中是很有效的,速度为5－11Hz,可用于实时性系统。     

家庭服务机器人的人脸检测、跟踪与识别研究

本文介绍了一个用于家庭服务机器人完成人脸检测、跟踪、识别的双目视觉系统。该系统首先采用人脸肤色模型结合相似度来检测人脸;然后通过基于颜色信息的CAMSHIFT算法跟踪运动的人脸;最后利用嵌入式隐马尔可夫模型对人脸进行识别。实验结果表明该系统能自动地检测、跟踪、识别人脸,而且该系统具有较良好的实时性和鲁棒性。     

机器人视觉跟踪轨迹的分级规划方法

针对跟踪轨迹规划对于确保得到连续光滑的跟踪运动的重要性,提出了两级视觉跟踪轨迹规划方法。第一阶段在图像平面上规划运动轨迹,在图像平面上得到的离散规划点映射到机器人关节空间。第二阶段在机器人关节空间中用三次样条函数来连接这些离散点。为了满足实时控制的要求,在图像处理过程中采用窗口技术并抽取边缘特征。建立用于跟踪两维平面运动物体(如随运输带运动的物体)的机器人视觉跟踪控制系统。实验结果表明,跟踪误差渐近地减小到允许的数值范围,所提出的跟踪轨迹规划方法是有效的。     

Robust Visual Tracking by Integrating Multiple Cues Based on Co-Inference Learning

Visual tracking can be treated as a parameter estimation problem that infers target states based on image observations from video sequences. A richer target representation may incur better chances of successful tracking in cluttered and dynamic environments, and thus enhance the robustness. Richer representations can be constructed by either specifying a detailed model of a single cue or combining a set of rough models of multiple cues. Both approaches increase the dimensionality of the state space, which results in a dramatic increase of computation. To investigate the integration of rough models from multiple cues and to explore computationally efficient algorithms, this paper formulates the problem of multiple cue integration and tracking in a probabilistic framework based on a factorized graphical model. Structured variational analysis of such a graphical model factorizes different modalities and suggests a co-inference process among these modalities. Based on the importance sampling technique, a sequential Monte Carlo algorithm is proposed to provide an efficient simulation and approximation of the co-inferencing of multiple cues. This algorithm runs in real-time at around 30 Hz. Our extensive experiments show that the proposed algorithm performs robustly in a large variety of tracking scenarios. The approach presented in this paper has the potential to solve other problems including sensor fusion problems.