基于层次因子图的智能车环境感知和态势认知模型

为了提升智能车的环境认知能力,根据数据信息的抽象化程度不同提出一种基于层次因子图的智能车环境感知和态势认知模型.首先,基于人类驾驶认知的分层记忆机理,按照被处理信息由低到高的抽象层次,将环境认知分为环境目标感知和态势认知两大任务模块,提出层次化框架;然后,确定层次因子图的拓扑结构并实现层次因子图模型,目标感知层具体体现为多源信息融合和目标跟踪,态势认知层具体体现为车辆变道等态势预测;最后,基于PreScan仿真环境数据、NGSIM真实驾驶数据集及DBNet自动驾驶实测数据集3种数据,验证所提出方法的有效性,并与现有的卡尔曼滤波方法和隐马尔科夫模型方法进行比较,以验证层次因子图在跟踪、融合、态势预测正确率和准确率方面的优势.     

The Velocity Snake: Deformable Contour for Tracking in Spatio-Velocity Space

We present a new active contour model for boundary tracking and position prediction of nonrigid objects, which results from applying a velocity control to the class of elastodynamical contour models, known as snakes. The proposed control term minimizes an energy dissipation function which measures the difference between the contour velocity and the apparent velocity of the image. Treating the image video-sequence as continuous measurements along time, it is shown that the proposed control results in robust tracking. This is in contrast to the original snake model which is proven to have tracking errors relative to image (object) velocity, thus resulting in high sensitivity to image clutter. The motion estimation further allows for position prediction of nonrigid boundaries. Based on the proposed control approach, we propose a new class of real time tracking contours, varying from models with batch-mode control estimation to models with real time adaptive controllers.     

A graphical model for audiovisual object tracking

We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it by developing a new algorithm for tracking a moving object in a cluttered, noisy scene using two microphones and a camera. Our model uses unobserved variables to describe the data in terms of the process that generates them. It is therefore able to capture and exploit the statistical structure of the audio and video data separately, as well as their mutual dependencies. Model parameters are learned from data via an EM algorithm, and automatic calibration is performed as part of this procedure. Tracking is done by Bayesian inference of the object location from data. We demonstrate successful performance on multimedia clips captured in real world scenarios using off-the-shelf equipment.     

Scene Aware Detection and Block Assignment Tracking in crowded scenes

How far can human detection and tracking go in real world crowded scenes? Many algorithms often fail in such scenes due to frequent and severe occlusions as well as viewpoint changes. In order to handle these difficulties, we propose Scene Aware Detection (SAD) and Block Assignment Tracking (BAT) that incorporate with some available scene models (e.g. background, layout, ground plane and camera models). The SAD is proposed for accurate detection through utilizing 1) camera model to deal with viewpoint changes by rectifying sub-images, 2) a structural filter approach to handle occlusions based on a feature sharing mechanism in which a three-level hierarchical structure is built for humans, and 3) foregrounds for pruning negative and false positive samples and merging intermediate detection results. Many detection or appearance based tracking systems are prone to errors in occluded scenes because of failures of detectors and interactions of multiple objects. Differently, the BAT formulates tracking as a block assignment process, where blocks with the same label form the appearance of one object. In the BAT, we model objects on two levels, one is the ensemble level to measure how it is like an object by discriminative models, and the other one is the block level to measure how it is like a target object by appearance and motion models. The main advantage of BAT is that it can track an object even when all the part detectors fail as long as the object has assigned blocks. Extensive experiments in many challenging real world scenes demonstrate the efficiency and effectiveness of our approach.     

Tracking in object action space

In this paper we focus on the joint problem of tracking humans and recognizing human action in scenarios such as a kitchen scenario or a scenario where a robot cooperates with a human, e.g., for a manufacturing task. In these scenarios, the human directly interacts with objects physically by using/manipulating them or by, e.g., pointing at them such as in “Give me that…”. To recognize these types of human actions is difficult because (a) they ought to be recognized independent of scene parameters such as viewing direction and (b) the actions are parametric, where the parameters are either object-dependent or as, e.g., in the case of a pointing direction convey important information. One common way to achieve recognition is by using 3D human body tracking followed by action recognition based on the captured tracking data. For the kind of scenarios considered here we would like to argue that 3D body tracking and action recognition should be seen as an intertwined problem that is primed by the objects on which the actions are applied. In this paper, we are looking at human body tracking and action recognition from a object-driven perspective. Instead of the space of human body poses we consider the space of the object affordances, i.e., the space of possible actions that are applied on a given object. This way, 3D body tracking reduces to action tracking in the object (and context) primed parameter space of the object affordances. This reduces the high-dimensional joint-space to a low-dimensional action space. In our approach, we use parametric hidden Markov models to represent parametric movements; particle filtering is used to track in the space of action parameters. We demonstrate its effectiveness on synthetic and on real image sequences using human-upper body single arm actions that involve objects.     

Convolutional restricted Boltzmann machines learning for robust visual tracking

It is a critical step to choose visual features in object tracking. Most existing tracking approaches adopt handcrafted features, which greatly depend on people’s prior knowledge and easily become invalid in other conditions where the scene structures are different. On the contrary, we learn informative and discriminative features from image data of tracking scenes itself. Local receptive filters and weight sharing make the convolutional restricted Boltzmann machines (CRBM) suit for natural images. The CRBM is applied to model the distribution of image patches sampled from the first frame which shares same properties with other frames. Each hidden variable corresponding to one local filter can be viewed as a feature detector. Local connections to hidden variables and max-pooling strategy make the extracted features invariant to shifts and distortions. A simple naive Bayes classifier is used to separate object from background in feature space. We demonstrate the effectiveness and robustness of our tracking method in several challenging video sequences. Experimental results show that features automatically learned by CRBM are effective for object tracking.     

基于多外观模型的自适应加权目标跟踪算法*

偏最小二乘(PLS)跟踪算法忽略特征间及外观模型间的差异,容易受到光照、遮挡等因素的影响,降低目标的跟踪精度.针对上述问题,文中提出基于多外观模型的自适应加权目标跟踪算法(AWMA).首先使用PLS对目标区域逐步建立多个外观模型.然后根据各外观模型中特征的重要性及目标的显著度建立自适应权重的综合模型,融合多个外观模型完成目标与样本的误差分析.最后使用粒子滤波实现目标跟踪.实验表明,文中算法能更有效地过滤噪声数据,提高目标跟踪的鲁棒性和时间性能.     

一种改进的基于颜色直方图的实时目标跟踪算法

基于颜色直方图的目标跟踪算法主要是利用彩色图像的颜色直方图信息,在获得颜色直方图水平投影和垂直投影的基础上,综合考虑运动预测和帧间的相似性,确定目标的位置,并结合模板更新的思想不断自适应地调整被跟踪目标的模板,从而实现对目标的跟踪,本文提出了的算法在原有的基于颜色直方图的目标跟踪算法的基础上,进行了两个方面的改进：（1）提出一种改进的直方图定义,使本算法能更好地实现小且目标物体的跟踪;（2）采用双模板更新与匹配的方法,使本算法对突变情况具有更强的鲁棒性。实验证明,本算法在保证跟踪准确度的同时,可以满足实时跟踪的要求。     

CAMSHIFT与基于核的目标跟踪算法的比较与分析

CAMSHIFT和基于核的目标跟踪是两种经典的基于Mean Shift的目标跟踪算法,它们的实现过程有许多类似之处。为了说明在实际应用中如何选择合理的跟踪方案,从目标模型、候选模型、核函数、迭代过程等方面对二者进行了深入的比较和分析,指出了二者的特点和区别,对于正确理解和使用这两种方法将会有一定的帮助。     

Dynamic Template Tracking and Recognition

In this paper we address the problem of tracking non-rigid objects whose local appearance and motion changes as a function of time. This class of objects includes dynamic textures such as steam, fire, smoke, water, etc., as well as articulated objects such as humans performing various actions. We model the temporal evolution of the object’s appearance/motion using a linear dynamical system. We learn such models from sample videos and use them as dynamic templates for tracking objects in novel videos. We pose the problem of tracking a dynamic non-rigid object in the current frame as a maximum a-posteriori estimate of the location of the object and the latent state of the dynamical system, given the current image features and the best estimate of the state in the previous frame. The advantage of our approach is that we can specify a-priori the type of texture to be tracked in the scene by using previously trained models for the dynamics of these textures. Our framework naturally generalizes common tracking methods such as SSD and kernel-based tracking from static templates to dynamic templates. We test our algorithm on synthetic as well as real examples of dynamic textures and show that our simple dynamics-based trackers perform at par if not better than the state-of-the-art. Since our approach is general and applicable to any image feature, we also apply it to the problem of human action tracking and build action-specific optical flow trackers that perform better than the state-of-the-art when tracking a human performing a particular action. Finally, since our approach is generative, we can use a-priori trained trackers for different texture or action classes to simultaneously track and recognize the texture or action in the video.     

基于自注意力机制和双向GRU神经网络的深度知识追踪优化模型

针对现有深度知识追踪模型存在输入习题间复杂关系捕获能力弱、无法有效处理长序列输入数据等问题,提出了基于自注意力机制和双向GRU神经网络的深度知识追踪优化模型(KTSA-BiGRU)。首先,将学习者的历史学习交互序列数据映射为实值向量序列;其次,以实值向量序列作为输入训练双向GRU神经网络,利用双向GRU神经网络建模学习者的学习过程;最后,使用自注意力机制捕获练习题之间的关系,根据双向GRU神经网络输出的隐向量和注意力权重计算学习者正确回答下一问题的概率。实验在三个公共数据集上的性能分析优于现有的知识追踪模型,能提高深度知识追踪的预测精度。     

单目视频中无标记的人体运动跟踪

提出一种人体运动跟踪算法,从无关节标记的单目视频中获取人体运动,利用一个带外观模板的人体关节模型,通过学习得到的运动模型及基于外观模型的相似性计算,巧妙地利用粒子滤波的概率密度传播策略鲁棒地跟踪普通单目视频中的人体运动,当出现跟踪丢失时,能在后续序列中自动恢复正确跟踪,且能较好地处理遮挡和自遮挡问题,实验表明,该算法鲁棒性好,跟踪结果令人满意。     

基于隐条件随机场的自适应视频分割算法

视频目标分割是视频监视与视频目标跟踪、视频目标识别以及视频编辑的基础. 本文提出了一种基于隐条件随机场 (Hidden conditional random fields, HCRF) 的自适应视频分割算法, 利用 HCRF 模型对视频序列中的时空邻域关系建模. 使用在线学习的方式对相应的参数进行调整, 实现对时空邻域约束关系的权重调整, 提高视频目标分割细节上的效果. 大量的数据测试表明, 与高斯混合模型 (Gaussian mixture model, GMM) 和联合时空的马尔可夫随机场 (Markov random fields, MRF) 等算法相比, 该算法的分割错误率分别降低了23\%和19\%.     

Improvement of mean shift tracking performance using a convex kernel function and extracting motion information

Color feature is now taken into real consideration as one of the important cues in the area of objects tracking, in image sequences. This feature has attracted considerable attention, in recent years. One of the well-known tools in color feature extraction is to use mean shift (MS) tracking algorithm. The probability of finding the object location in line with this tracking algorithm is somehow desirable, in image sequences, by maximizing the Bhattacharyya coefficient between both objects and corresponding candidate models. Even though the MS tracking algorithm is just known as a popular tool in the field of object tracking, it does not have sufficient merit to be realized in complex environments, i.e., background with object’s similar color, sudden light changes, occlusion types and so on. In such a case, the amount of the present coefficient could truly be decreased, during the tracking process, because of the mentioned environmental problems. A convex kernel function in association with the motion information of video sequences is used in this investigation to improve the MS tracking algorithm for the purpose of overcoming the existing problems. The proposed approach is employed to present the MS kernel function, directly. Thus, by using the investigation in its present form, the capability of the MS kernel is increased. Moreover, by using both color feature and motion information, simultaneously, in comparison with single color feature, noises and also uninterested regions can actually be eliminated. Experimental results on data set illustrate that the proposed approach has an optimum performance in real-time object tracking under the severe conditions.     

A 2D/3D model-based object tracking framework

This paper presents a robust framework for tracking complex objects in video sequences. Multiple hypothesis tracking (MHT) algorithm reported in (IEEE Trans. Pattern Anal. Mach. Intell. 18(2) (1996)) is modified to accommodate a high level representations (2D edge map, 3D models) of objects for tracking. The framework exploits the advantages of MHT algorithm which is capable of resolving data association/uncertainty and integrates it with object matching techniques to provide a robust behavior while tracking complex objects. To track objects in 2D, a 4D feature is used to represent edge/line segments and are tracked using MHT. In many practical applications 3D models provide more information about the object's pose (i.e., rotation information in the transformation space) which cannot be recovered using 2D edge information. Hence, a 3D model-based object tracking algorithm is also presented. A probabilistic Hausdorff image matching algorithm is incorporated into the framework in order to determine the geometric transformation that best maps the model features onto their corresponding ones in the image plane. 3D model of the object is used to constrain the tracker to operate in a consistent manner. Experimental results on real and synthetic image sequences are presented to demonstrate the efficacy of the proposed framework.     

基于视频的三维人体运动跟踪

提出一种结合多种图像特征，在多摄像机环境下跟踪人体运动的方法．通过定义人体模型、摄像机投影模型以及相似性度量模型来得到优化框架下的目标函数，并使用牛顿-高斯优化算法对其进行求解．模拟数据和实际数据的实验表明，文中方法比仅仅使用灰度特征，跟踪结果得到了改善，对比实验结果也优于基于概率算法的退火粒子滤波．     

Multiple model adaptive control for switched linear systems: A two‐layer switching strategy

In this paper, the multiple model adaptive control scheme is first introduced into a class of switched systems. A switched multiple model adaptive control scheme is proposed to improve the transient behavior by resetting the controller parameters. Firstly, a finite‐time parameter identification model is presented, which greatly reduces the number of identification models. Secondly, a two‐layer switching strategy is constructed. The outer layer switching mechanism is to ensure the stability of the switched systems. The inner layer switching mechanism is to improve the transient behavior. Then, by using the constructed jumping multiple Lyapunov functions, the proposed adaptive control scheme guarantees that all the closed‐loop system signals remain bounded and the state tracking error converges to a small ball whose radius can be made arbitrarily small by appropriately choosing the design parameter. Finally, a practical example about model reference adaptive control of an electrohydraulic system using multiple models is given to demonstrate the validity of the main results.     

A Distance Measure and a Feature Likelihood Map Concept for Scale-Invariant Model Matching

This paper presents two approaches for evaluating multi-scale feature-based object models. Within the first approach, a scale-invariant distance measure is proposed for comparing two image representations in terms of multi-scale features. Based on this measure, the maximisation of the likelihood of parameterised feature models allows for simultaneous model selection and parameter estimation.The idea of the second approach is to avoid an explicit feature extraction step and to evaluate models using a function defined directly from the image data. For this purpose, we propose the concept of a feature likelihood map, which is a function normalised to the interval [0, 1], and that approximates the likelihood of image features at all points in scale-space.To illustrate the applicability of both methods, we consider the area of hand gesture analysis and show how the proposed evaluation schemes can be integrated within a particle filtering approach for performing simultaneous tracking and recognition of hand models under variations in the position, orientation, size and posture of the hand. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by pyramid implementations of the proposed concepts.     

鲁棒的自适应尺度和方向的目标跟踪方法

针对在视频序列图像目标跟踪中,跟踪目标尺寸和跟踪目标相对背景运动的方位角都在实时变化,常规目标跟踪算法会引起尺度和方向定位偏差,导致跟踪漂移,甚至跟踪失败问题,提出鲁棒的目标尺度和方向自适应的跟踪方法。在Kalman滤波框架下,通过将运动目标的最小外接矩形信息转化为Kalman滤波参数,对目标运动进行建模。采用基于最小外接矩形的两步块匹配搜索方式实现对目标的中心定位,然后采用增量式搜索匹配方法根据最优尺度和角度的判别条件修正目标尺度和方向角度。通过动态评估不同目标模型在不同跟踪场景中的置信度,对目标模型进行动态更新。使用公用视频图像序列测试,实验结果验证了该方法的有效性。     

机动目标跟踪的机动频率自适应算法

为了更好地跟踪机动目标 ,提出了一种机动目标跟踪的改进方法 .利用目标的跟踪残差 ,求取跟踪滤波器的理论残差方差值 ,再根据统计的残差方差 ,建立了残差的假设检验阀值 .并对其算法进行了具体的推导 ,得出自适应选择机动频率的原则 ,使机动频率与目标的当前状态更接近 .对“当前”模型和改进后的模型进行了仿真 ,仿真结果表明该方法具有更小的跟踪误差 ,是可行和有效的