基于背景建模和动态分块的目标跟踪

MeanShift算法在做目标跟踪时不能解决混乱背景和严重的局部遮挡的问题。因此,本文提出了一种新的目标跟踪算法来解决这两个问题。该算法首先利用最大化后验概率在MeanShift跟踪框架内融入背景信息,然后在跟踪过程中根据候选区域和模板区域的相似度结合空间金字塔技术对目标进行动态分块,使得目标能够克服背景的干扰并保留一定的几何结构信息。实验结果表明,相比于MeanShift算法,新提出的算法能够克服混乱背景和严重的局部遮挡,有效地跟踪目标。     

重叠视野域内多摄像机目标交换算法

多摄像机之间重叠视野区域内目标交接问题是实现多摄像机监控系统持续目标跟踪的关键,传统方法是在摄像机重叠视野区域内采用特征匹配方法或基于视野分界线的目标交接算法。但是特征匹配计算量较大,受摄像机参数设置因素影响较大,实用性不高。而基于视野分界线的目标交接算法由于新目标的检测存在延时,仅利用该方法来实现一致性标号容易出错。近年来,出现了利用投影不变量,计算目标在相邻摄像机中的投影位置来进行目标交接的方法,取得较好效果。但在多个目标相距较近的情况下,投影过程中产生的误差会造成目标对应错误。文中提出一种投影不变量     

基于摄像机运动控制的实时对象检测与跟踪算法

提出了一种基于摄像机运动控制的实时运动对象检测与跟踪算法.该算法首先采用非参数核密度估计方法在复杂的动态背景条件下检测运动对象区域;然后由CamShift算法计算跟踪目标的位置,并采用Kalman滤波预测对象的运动信息来控制摄像机的运动,能够准确地跟踪对象并有效解决了背景中的部分遮挡问题.在SonyRZ25网络摄像机上完成了对象的实时检测与跟踪,对多个室内和室外场景的实验验证了所提出方法的实用性和有效性.     

基于卡尔曼滤波器的运动目标跟踪算法

为了有效解决运动目标遮挡时目标信息容易丢失从而导致跟踪失败的问题,提出一种基于卡尔曼滤波器的运动目标跟踪算法。该算法首先利用高斯混合模型的背景差分法,结合空间邻域的相关性信息得到运动目标图像,然后通过建立帧间关系矩阵将跟踪情况分为5种状态分别进行处理,这5种状态是新目标出现、目标匹配、目标遮挡、目标分离和目标消失。采用卡尔曼滤波器预测目标参数,建立目标在下一帧中的预测信息。当运动目标相互遮挡时,在卡尔曼滤波器预测区域内采用交叉搜索法实现多个运动目标的精确匹配。通过多个视频序列测试,该算法能够获得良好的跟踪结果。     

一种尺度自适应的粒子滤波跟踪算法

针对复杂背景下目标发生旋转、遮挡、尺度变化和摄像机运动时不能实时跟踪到目标的问题,将最佳核窗宽方法和信息量度量方法相结合,用于粒子滤波框架中.各个粒子通过均值偏移来搜索峰值,同时加入了相应的遮挡策略.实验结果表明,该算法在目标发生旋转、遮挡后仍能很好地跟踪到目标.同时跟踪窗能随目标尺度的大小变化作相应调整,大大提高了算法的实时性和稳健性.     

一种改进的长时间压缩感知跟踪算法

压缩感知跟踪(CT)算法具有简单、高效、实时的优点,但是却存在着跟踪窗口尺寸不能自适应变化,无法有效处理遮挡以及跟踪失败后的目标再发现等问题.为了解决上述问题,提出了一种改进的长时间压缩感知跟踪算法.所提出的算法采用多尺度的目标外观再匹配方法,使得跟踪窗口大小能够适应目标尺寸变化.此外,通过分析滑动窗口内跟踪窗口图像的整体特征变化来判定目标是否发生遮挡.为了解决跟踪器漂移问题,采用Haar特征在线生成检测器,实现目标的再发现.实验结果表明提出的算法相比原CT算法具有更好的鲁棒性和准确性.     

基于贝叶斯理论的分布式多视角目标跟踪算法

 为了有效解决传统单视角跟踪难于处理的目标遮挡问题,本文提出了一种分布式多视角目标跟踪算法. 该算法首先基于贝叶斯理论,为多视角目标跟踪问题建立了分布式数据融合的概率框架;并利用粒子滤波器对所需后验概率进行近似,提出了自适应的观测模型和状态转移模型. 各摄像机能够并行化地进行数据采集、处理、融合,而无需集中式处理单元;能够有效避免遮挡造成的误差传递,提高跟踪算法的鲁棒性. 实验证明了本文算法的有效性.     

一种改进的Camshift目标跟踪方法

为了解决单特征在目标跟踪中无法准确描述目标的问题,提出了一种多特征融合的实时目标跟踪方法。该方法将角点特征、轮廓特征融入传统的Camshift算法中,结合原有的颜色特征对目标进行描述。解决了传统算法易受同色物体干扰,抗遮挡性能差等问题。实验结果表明,该方法能够实现对目标的实时跟踪,当目标遮挡的时间较短时能够很好地识别目标,具有较高的鲁棒性。     

基于局部二值模式的改进时空上下文跟踪算法

基于时空上下文(Spatial-Temporal Context,STC)的跟踪算法与大部分传统算法相比,在实时性方面具有明显的优势.通过实验发现,STC算法存在由变形和遮挡引起的跟踪精度下降问题.针对该问题,提出了一种改进方法,该方法在原STC算法的基础上引入局部二值模式(Local Binary Pattern,LBP)和遮挡检测机制,利用LBP特征来代替灰度特征,当跟踪器检测出目标发生遮挡时,停止分类器参数的更新.对于满足线性运动的目标,利用卡尔曼滤波器对其进行位置预测以解决目标发生遮挡后的定位问题.实验证明,所提出的改进算法能有效提升目标跟踪精度,针对遮挡情况下的目标也展现出较高的鲁棒性.     

基于图像签名算法的视觉目标跟踪算法北大核心CSCD

针对视觉目标跟踪算法中存在的快速运动、尺度变化、形变和遮挡问题,提出基于图像签名算法的视觉目标跟踪算法。该算法以相关滤波算法为基础,通过多种特征构建目标的外观模型,提高了算法的跟踪精确度和稳健性;为了解决严重遮挡情况下的目标重定位问题,利用图像签名算法计算图像的稀疏显著性区域,获取候选目标的位置,通过分类器对候选目标进行重排名,实现目标重定位;采用尺度池策略和自适应模板更新策略,解决跟踪中的尺度变化问题和跟踪漂移问题。利用标准数据集测试所提算法的性能,结果表明,所提算法在跟踪成功率和精确度上均优于传统的相关滤波算法,能较好地解决快速运动、尺度变化、形变和遮挡情况下的目标跟踪问题。     

基于改进ORB算法无重叠视野域的目标交接

介绍了基于ORB（Oriented FAST and Rotated BRIEF）算法的无重叠视野域的目标交接。当目标离开摄像机1视野域时,利用ORB算法提取目标特征点,待匹配特征点通过PROSAC（Progressive Sample Consensus）算法剔除外点,保留有价值的特征点。当目标进入摄像机2视野域时,通过Vibe（Visual Background extractor）算法获取进入摄像机2的运动目标,并提取待确认运动目标的特征点,去除外点并与摄像机1视野域提取的特征点做匹配,匹配率达到阈值则表示目标一致,完成目标交接并进行跟踪。实验结果表明,文献提出的方案能够实现目标在多摄像机视野域间的快速交接。     

采用地平面约束的双目PTZ主从跟踪方法

在视频监控领域,包含PTZ（pan-tilt-zoom）相机的双目主从系统可以同时获取跟踪目标的全景信息和高分辨率信息,因此得到了广泛研究与应用。针对智能视频监控的需求,提出了一种基于地平面约束的双目PTZ主从跟踪方法。该方法分为离线标定和在线实时跟踪两个阶段。离线阶段,利用两相机不同视角间的目标匹配关系计算地平面所诱导的单应矩阵,提出了一种从两相机同步视频流中自动估计单应矩阵的方法,该方法与传统方法相比具有不需要标定物和人工干预的优点,然后采用匹配特征点的方法估计相机的主点和等效焦距。在线实时跟踪时,通过单应变换建立主从相机之间的坐标关联,并利用离线阶段标定的主点和等效焦距估计从相机控制参数,从而实现主从跟踪。与其他算法相比,该方法可以应用于宽基线的情形,能够适应目标深度的变化,满足了实时性的要求。室内、外场景的多组实验验证了所提方法的有效性。     

Multicamera Tracking of Articulated Human Motion Using Shape and Motion Cues

We present a completely automatic algorithm for initializing and tracking the articulated motion of humans using image sequences obtained from multiple cameras. A detailed articulated human body model composed of sixteen rigid segments that allows both translation and rotation at joints is used. Voxel data of the subject obtained from the images is segmented into the different articulated chains using Laplacian Eigenmaps. The segmented chains are registered in a subset of the frames using a single-frame registration technique and subsequently used to initialize the pose in the sequence. A temporal registration method is proposed to identify the partially segmented or unregistered articulated chains in the remaining frames in the sequence. The proposed tracker uses motion cues such as pixel displacement as well as 2-D and 3-D shape cues such as silhouettes, motion residue, and skeleton curves. The tracking algorithm consists of a predictor that uses motion cues and a corrector that uses shape cues. The use of complementary cues in the tracking alleviates the twin problems of drift and convergence to local minima. The use of multiple cameras also allows us to deal with the problems due to self-occlusion and kinematic singularity. We present tracking results on sequences with different kinds of motion to illustrate the effectiveness of our approach. The pose of the subject is correctly tracked for the duration of the sequence as can be verified by inspection.      

Tracking deformable and occluded objects using particle filtering and GVF-Snake

An adaptive object tracking algorithm based on particle filtering and a modified Gradient Vector Flow (GVF) Snake is proposed for tracking moving and deforming objects. The original contours of objects are obtained by using the background differencing method, and the true contours of objects can be con-verged by means of the powerful searching ability of a modified GVF-Snake. Finally, an Energetic Particle Filtering (EPF) algorithm is obtained by combining particle filtering and a modified GVF-Snake, and by us-ing K-means and the EPF algorithm, multiple objects can be tracked. The proposed tracking tactic for par-tially occluded objects can effectively improve its anti-occlusion ability. Experiments show that this algorithm can obtain better tracking effect even though the tracked object is occluded.     

People tracking in an environment with multiple depth cameras: A skeleton-based pairwise trajectory matching scheme

This paper proposes a pairwise trajectory matching scheme from multiple cameras for people tracking, handling the mistracking situations caused by occlusion events occurred in one of the cameras. In a multiple cameras environment, a geometric calibration process is necessary for the co-plane of the overlapping field of views from different cameras as the initial step. Once the geometry is calibrated, according to the 2D positions of the analyzed foot joints from the depth cameras. Homography transformation is applied to project the detected foot points from different views into a synergistic virtual bird’s eye view for people tracking. At the virtual bird’s eye view, the people tracking results from each of the cameras based on Kalman filter are fused according to the proposed pairwise trajectory matching scheme. The contribution of this paper is trifold: (1) The proposed hand-gesture-triggered calibration process with temporally synchronization capability can effectively build and calibrate the geometry in a region of interest. (2) The proposed interleaving-based skeleton obtaining and moving average based valid skeleton determination can extend the skeleton tracking capability to track more people. (3) The proposed pairwise trajectory matching scheme effectively manages occlusion situations happened in one of the depth cameras. In addition, in the extensive experimental results, the proposed method can track up to six simultaneously freely moving persons in the field of view, with affordable complexity for real-time applications. Furthermore, the infrared-based depth cameras track people satisfactorily from bright to extremely dark environments.     

Handoff effect on packet reservation multiple access (PRMA) in microcellular system

Packet reservation multiple access (PRMA) has been proposed for third-generation wireless information networks by D.J. Goodman and S.X. Wei (see ibid., vol.40, p.170-6, 1991). The mobile-initiated handoff has been proposed to disperse the base station (BS) burden, which is increased by the small microcell radius. However, increased contentions, due to handoff, affect the overall performance of PRMA, even though these frequent handoffs do not burden the BS. We analyze the handoff effect on PRMA performance under a microcellular system, both voice-only and combined voice-and-data systems. A steady state voice-terminal model with handoff is proposed. System-equilibrium equations are derived using the proposed model. The system performance is evaluated, using a Markov analysis method, in terms of packet-dropping probability, data-packet delay, and throughput. The change of performance under handoff show the impact of handoff on PRMA.     

基于主分量寻踪的鲁棒视觉跟踪

传统子空间跟踪易受到模型漂移的影响而导致跟踪失败.针对此问题,本文提出一种基于主分量寻踪的鲁棒视觉跟踪方法.该方法以多个模板张成的子空间作为目标表观模型,利用主分量寻踪求解候选目标的误差分量,在粒子滤波框架下利用候选目标的误差分量估计最优状态参数.为了适应目标表观变化并克服模型漂移,本文提出一种模板更新方法.当跟踪结果与目标模板相似时,该方法利用跟踪结果更新目标模板,否则利用跟踪结果的低秩分量更新目标模板.在多个具有挑战性的图像序列上的实验结果表明:与现有跟踪方法相比,文中的跟踪方法具有较优的跟踪性能.     

多目标环境中的认知雷达跟踪方法

研究了多目标环境中的认知雷达目标跟踪问题,提出了一种基于波形优化和快速粒子滤波的多目标跟踪方法。在量测模型中,基于采样的接收数据建立量测方程,以克服多目标跟踪中的数据关联问题;在状态模型中,与量测模型相匹配,联合估计目标运动状态（位置、速度）和散射系数。为实现多目标跟踪和提高跟踪性能,从联合收发自适应处理角度出发设计跟踪算法和发射波形:1）接收自适应。由于量测数据的维数以及跟踪模型的非线性程度较高,为实现对多目标的有效跟踪以及降低跟踪算法的运算复杂度,采用改进的粒子滤波方法对目标状态进行实时估计;2）发射自适应。考虑到信噪比与跟踪性能关系以及量测模型的特点,基于最优信噪比准则实现了对发射波形的优化。仿真结果表明文中所提出的跟踪方法能够有效的跟踪上目标,且所设计的自适应波形的跟踪性能优于传统固定波形。