A local-motion-based probabilistic model for visual tracking

Color-based tracking is prone to failure in situations where visually similar targets are moving in a close proximity or occlude each other. To deal with the ambiguities in the visual information, we propose an additional color-independent visual model based on the target's local motion. This model is calculated from the optical flow induced by the target in consecutive images. By modifying a color-based particle filter to account for the target's local motion, the combined color/local-motion-based tracker is constructed. We compare the combined tracker to a purely color-based tracker on a challenging dataset from hand tracking, surveillance and sports. The experiments show that the proposed local-motion model largely resolves situations when the target is occluded by, or moves in front of, a visually similar object.     

A probabilistic integrated object recognition and tracking framework

This paper describes a probabilistic integrated object recognition and tracking framework called PIORT, together with two specific methods derived from it, which are evaluated experimentally in several test video sequences. The first step in the proposed framework is a static recognition module that provides class probabilities for each pixel of the image from a set of local features. These probabilities are updated dynamically and supplied to a tracking decision module capable of handling full and partial occlusions. The two specific methods presented use RGB color features and differ in the classifier implemented: one is a Bayesian method based on maximum likelihood and the other one is based on a neural network. The experimental results obtained have shown that, on one hand, the neural net based approach performs similarly and sometimes better than the Bayesian approach when they are integrated within the tracking framework. And on the other hand, our PIORT methods have achieved better results when compared to other published tracking methods in video sequences taken with a moving camera and including full and partial occlusions of the tracked object.     

Combining intensional with extensional query evaluation in tuple independent probabilistic databases

In this paper, we prove that a query plan is safe in tuple independent probabilistic databases if and only if its every answer tuple is tree structured in probabilistic graphical models. We classify hierarchical queries into core and non-core hierarchical queries and show that the existing methods can only generate safe plans for core hierarchical queries. Inspired by the bucket elimination framework, we give the sufficient and necessary conditions for the answer relation of every candidate sub-query to be used as a base relation. Finally, the proposed algorithm generates safe plans for extensional query evaluation on non-boolean hierarchical queries and invokes the SPROUT algorithm [24] for intensional query evaluation on boolean queries. A case study on the TPC-H benchmark reveals that the safe plans of Q7 and Q8 can be evaluated efficiently. Furthermore, extensive experiments show that safe plans generated by the proposed algorithm scale well.     

A decentralized probabilistic approach to articulated body tracking

We present a novel decentralized probabilistic approach to visual tracking of articulated objects. Analyzing articulated motion is challenging because (1) the high degrees of freedom potentially demands tremendous computation, and (2) the solution is confronted by the numerous local optima existed in a high dimensional parametric space. To ease these problems, we propose a decentralized approach that analyzes limbs locally and reinforces the spatial coherence among them at the same time. The computational model of the proposed approach is based on a dynamic Markov network, a generative model which characterizes the dynamics, the image observations of each individual limb, as well as the spatial coherence among them. Probabilistic mean field variational analysis provides an efficient computational diagram to obtain the approximate inference of the motion posteriors. We thus design the mean field Monte Carlo (MFMC) algorithm, where a set of low dimensional particle filters interact with one another and solve the high dimensional problem collaboratively. We also present a variational maximum a posteriori (MAP) algorithm, which has a rigorous theoretic foundation, to approach to the optimal MAP estimate of the articulated motion. Both algorithms achieve linear complexity w.r.t. the number of articulated subparts and have the potential of parallel computing. Experiments on human body tracking demonstrate the significance, effectiveness and efficiency of the proposed methods.     

Automatic model-based 3D object recognition by combining feature matching with tracking

We propose a vision-based robust automatic 3D object recognition, which provides object identification and 3D pose information by combining feature matching with tracking. For object identification, we propose a robust visual feature and a probabilistic voting scheme. An initial object pose is estimated using correlations between the model image and the 3D CAD model, which are predefined, and the homography, byproduct of the identification. In tracking, a Lie group formalism is used for robust and fast motion computation. Experimental results show that object recognition by the proposed method improves the recognition range considerably. Sungho Kim received the B.S. degree in Electrical Engineering from Korea University, Korea in 2000 and the M.S. degree in Electrical Engineering and Computer Science from Korea Advanced Institute of Science and Technology, Korea in 2002. He is currently pursuing his Ph.D. at the latter institution, concentrating on 3D object recognition and tracking. In So Kweon received the Ph.D. degree in robotics from Carnegie Mellon University, Pittsburgh, PA, in 1990. Since 1992, he has been a Professor of Electrical Engineering at KAIST. His current research interests include human visual perception, object recognition, real-time tracking, vision-based mobile robot localization, volumetric 3D reconstruction, and camera calibration. He is a member of the IEEE, and Korea Robotics Society (KRS).     

Salient and non-salient fiducial detection using a probabilistic graphical model

Deformable shape detection is an important problem in computer vision and pattern recognition. However, standard detectors are typically limited to locating only a few salient landmarks such as landmarks near edges or areas of high contrast, often conveying insufficient shape information. This paper presents a novel statistical pattern recognition approach to locate a dense set of salient and non-salient landmarks in images of a deformable object. We explore the fact that several object classes exhibit a homogeneous structure such that each landmark position provides some information about the position of the other landmarks. In our model, the relationship between all pairs of landmarks is naturally encoded as a probabilistic graph. Dense landmark detections are then obtained with a new sampling algorithm that, given a set of candidate detections, selects the most likely positions as to maximize the probability of the graph. Our experimental results demonstrate accurate, dense landmark detections within and across different databases.     

融合目标特征和空间信息的粒子滤波跟踪

传统的基于颜色直方图的粒子滤波跟踪算法不能很好地利用跟踪对象的空间结构信息,因此在邻域颜色相似或目标模型微小变化时,不能取得良好的跟踪效果。提出一种融合目标特征和目标空间位置信息的粒子滤波跟踪算法,该算法鉴于目标空间位置包含跟踪对象一定的结构信息,可以和目标特征互为补充,利用定义的融合目标特征和目标空间位置的度量函数来进行跟踪对象相似度度量,以提高跟踪算法的稳健性和精确性。同时针对粒子滤波计算粒子相似度时可并行的特点,运用OpenMP共享存储并行计算进行粒子滤波跟踪的加速。实验表明,基于融合目标特征和空间信息的粒子滤波跟踪算法能得到更鲁棒的跟踪效果,可以有效地提高目标跟踪的速度。     

Real time 3D face and facial feature tracking

Detecting and tracking human faces in video sequences is useful in a number of applications such as gesture recognition and human-machine interaction. In this paper, we show that online appearance models (holistic approaches) can be used for simultaneously tracking the head, the lips, the eyebrows, and the eyelids in monocular video sequences. Unlike previous approaches to eyelid tracking, we show that the online appearance models can be used for this purpose. Neither color information nor intensity edges are used by our proposed approach. More precisely, we show how the classical appearance-based trackers can be upgraded in order to deal with fast eyelid movements. The proposed eyelid tracking is made robust by avoiding eye feature extraction. Experiments on real videos show the usefulness of the proposed tracking schemes as well as their enhancement to our previous approach.

A consensus-based method for tracking: Modelling background scenario and foreground appearance

Modelling of the background (“uninteresting parts of the scene”), and of the foreground, play important roles in the tasks of visual detection and tracking of objects. This paper presents an effective and adaptive background modelling method for detecting foreground objects in both static and dynamic scenes. The proposed method computes SAmple CONsensus (SACON) of the background samples and estimates a statistical model of the background, per pixel. SACON exploits both color and motion information to detect foreground objects. SACON can deal with complex background scenarios including nonstationary scenes (such as moving trees, rain, and fountains), moved/inserted background objects, slowly moving foreground objects, illumination changes etc.However, it is one thing to detect objects that are not likely to be part of the background; it is another task to track those objects. Sample consensus is again utilized to model the appearance of foreground objects to facilitate tracking. This appearance model is employed to segment and track people through occlusions. Experimental results from several video sequences validate the effectiveness of the proposed method.     

基于改进高斯混合模型的实时运动目标检测与跟踪*

为提高运动目标检测与跟踪的可靠性,提出了一种基于改进高斯混合模型的实时运动目标检测与跟踪算法。该算法建立可自动调节分布数目的高斯混合背景模型,通过背景减除获取前景图像;利用目标相邻帧的连续性分割运动目标;在此基础上将传统的颜色直方图模型进行改进,提高目标颜色分布的可信度,进而根据目标的位置、大小和颜色构造运动目标全局匹配相似度函数,实时完成运动目标检测与跟踪。利用大量的监控视频数据进行验证,结果表明,与传统的检测跟踪算法相比,该算法减少了计算量,提高了复杂背景情况下运动目标检测与跟踪的可靠性。     

随机场中运动一致性的多线索目标跟踪

目的 通过建立各线索间的关联,提高多线索目标跟踪方法的鲁棒性,利用简单而有效的模型使多线索目标跟踪方法的表达和实现变得容易.方法 在不同线索描述下的目标对象间引入运动一致性约束,利用链状结构随机场模型表达不同线索描述下的目标对象及其约束关系,将多线索目标跟踪问题转化为随机场目标函数的简单优化求解.实验中结合亮度直方图、方向梯度直方图和局部二进制模式描述目标对象.结果 15组公测视频序列上的实验结果表明,所提方法相对于多种优秀的目标跟踪方法,在目标受到遮挡、运动模糊、光照变化、背景杂乱等因素干扰时,获得了较低中心位置误差和较高的精度值,反映了所提方法的有效性.结论 运动一致性约束能够较好地增强各线索间的关联,通过链状结构的随机场模型表达该约束关系和各线索描述下的目标对象,在提高跟踪鲁棒性的同时,使跟踪方法的实现变得简单.     

户外环境下抗遮挡的运动目标跟踪方法

针对户外环境光线和气候条件多变以及目标间相互遮挡对目标检测和跟踪的影响,提出了一种基于改进的高斯混合模型方法来检测运动目标,并消除噪声和阴影;同时采用基于Kalman滤波器的预测模型和最大后验概率目标匹配相结合的方法来实现目标的连续跟踪。实验表明,该方法能实现目标的稳定跟踪,且能够处理目标相互遮挡的情况,计算复杂度较低,基本满足实时应用的需求。     

基于运动信息与Hog特征的伪装色移动目标跟踪

针对复杂背景下伪装色运动目标的跟踪问题,提出一种基于运动信息与梯度方向直方图的跟踪方法。通过金字塔光流法获取视频序列中目标运动矢量范围;利用目标区域的灰度特征以及Hog特征构建特征向量,沿着运动主方向在速度大小范围内进行二分法匹配,进而确定目标的准确位置。实验结果表明,针对平缓变化的视频序列,对于颜色色调范围较大或者边缘结构较为明显的伪装色运动目标具有良好的跟踪效果。     

Hand tracking in a natural conversational environment by the interacting multiple model and probabilistic data association (IMM-PDA) algorithm

Traditional image based hand tracking algorithms use a single model Kalman filter to estimate and predict the hand state (position, velocity, and acceleration) and do not consider multiple measurements with noise and false alarms. However, these approaches may fail in the case of large maneuvers and/or a clutter measurement environment. In this paper, we apply the interacting multiple model (IMM) to catch hand maneuvers and the probabilistic data association (PDA) method to process noisy measurements and false alarms. A theoretical framework of image based hand tracking by the IMM-PDA algorithm is set up. Experiment results from several long video segments show that the IMM-PDA algorithm gives a superior performance compared to single model based Kalman filters.     

基于改进运动历史图像的多运动目标实时跟踪

提出了一种利用视频图像对运动目标进行实时检测与跟踪的新方法.该方法利用基于改进的时间片的运动历史图像(tMHI)的灰度阶梯轮廓方法对多个运动目标进行检测,通过卡尔曼滤波器对多目标进行跟踪,并得到了各个运动目标的轨迹曲线,进而实现了对视频图像中多目标的跟踪.同时,该方法对多个目标的遮挡问题获得了明显的改善效果.实验结果表明,该方法能够对复杂场景下的多个目标进行有效的识别和准确的跟踪,系统的实时性强,识别率高,而且该方法对于复杂视频监视系统场景中的光照变化、雨雾等干扰具有较强的稳健性.     

基于二值特征和结构化输出支持向量机的目标快速跟踪算法

复杂场景下基于判别式分类器的目标跟踪通常采用复杂的外观表示模型以提高跟踪精度,但影响了算法的实时性。为此,提出一种基于半色调的二值特征来描述目标的外观,在此基础上对结构化输出支持向量机(SVM)的核函数进行改进,实现了判别模型的快速更新和判别;同时提出一种基于分块匹配的判别模型更新策略,保证了跟踪过程中样本的可靠性。在Benchmark数据集上进行的测试实验中,与压缩跟踪(CT)算法、跟踪学习检测(TLD)算法和核化的结构化输出跟踪(Struck)算法相比,在跟踪速度上,该算法分别提高了0.2倍、4.6倍、5.7倍;在跟踪精度上,当重叠率阈值取0.6时,该算法的成功率达到0.62,而其他三种算法的成功率均在0.4以下,当位置误差阈值取10时,该算法的精度为0.72,而其他三种算法精度均小于0.5。实验结果表明该算法在发生光照变化、尺度变化、严重遮挡和突变运动等复杂情况下均具有很好的鲁棒性和实时性。     

运动目标检测中的环境感知与自适应研究

在复杂环境下,任何环境的改变都会对运动目标检测的准确性产生影响。因此提出广义高斯混合模型与背景减除法相结合的算法对运动目标进行检测。该模型可以灵活地感知环境,自适应地处理视频背景模型中背景的环境变化,如光线渐变、背景扰动、阴影和噪声等,而且当光线突变时可以迅速感知并重新建模。此外为了满足实时性,采取每隔3帧进行一次背景更新的策略。实验结果证明本算法在满足实时性的同时,能准确检测出运动目标。     

视频监控中运动物体的检测与跟踪

针对固定摄像头下的交通监控场景,首先给出一种基于分块原理的背景重建算法,克服了平均法重建的背景图像模糊的缺点。然后用减背景方法检测运动物体,并利用数学形态学方法对得到原始前景点作处理,填补了运动物体内部的空洞,减少了噪声点,改善了检测性能。为适应背景的变化,对背景进行自适应更新,并且通过对Meanshift算法的改进提高了跟踪的准确性。实验结果表明,算法在有效检测到运动物体的同时能够快速准确地跟踪运动物体。     

Scalable continuous object detection and tracking in sensor networks

With the advancement of MEMS technologies, sensor networks have opened up broad application prospects. An important issue in wireless sensor networks is object detection and tracking, which typically involves two basic components, collaborative data processing and object location reporting. The former aims to have sensors collaborating in determining a concise digest of object location information, while the latter aims to transport a concise digest to sink in a timely manner. This issue has been intensively studied in individual objects, such as intruders. However, the characteristic of continuous objects has posed new challenges to this issue. Continuous objects can diffuse, increase in size, or split into multiple continuous objects, such as a noxious gas. In this paper, a scalable, topology-control-based approach for continuous object detection and tracking is proposed. Extensive simulations are conducted, which show a significant improvement over existing solutions.     

Online learning and fusion of orientation appearance models for robust rigid object tracking

We introduce a robust framework for learning and fusing of orientation appearance models based on both texture and depth information for rigid object tracking. Our framework fuses data obtained from a standard visual camera and dense depth maps obtained by low-cost consumer depth cameras such as the Kinect. To combine these two completely different modalities, we propose to use features that do not depend on the data representation: angles. More specifically, our framework combines image gradient orientations as extracted from intensity images with the directions of surface normals computed from dense depth fields. We propose to capture the correlations between the obtained orientation appearance models using a fusion approach motivated by the original Active Appearance Models (AAMs). To incorporate these features in a learning framework, we use a robust kernel based on the Euler representation of angles which does not require off-line training, and can be efficiently implemented online. The robustness of learning from orientation appearance models is presented both theoretically and experimentally in this work. This kernel enables us to cope with gross measurement errors, missing data as well as other typical problems such as illumination changes and occlusions. By combining the proposed models with a particle filter, the proposed framework was used for performing 2D plus 3D rigid object tracking, achieving robust performance in very difficult tracking scenarios including extreme pose variations.