Online adaptive feature weighting for spatiogram-bank tracking

In this paper, we introduce a new adaptive feature weighting framework for multi-modal tracking. Our proposed tracker can compactly and efficiently handle multiple sources of tracking data, such as colour, brightness, gradient orientation and thermal infrared, and adaptively weight the sources based on their reliability for tracking. The adaptive weight selection mechanism is inspired by the state-of-the-art Collins tracker, but instead of treating the tracked object as a bag of features, it takes advantage of the spatial information using a global object model. Additionally, our tracker incorporates scale into the weight selection process and is shown to outperform the Collins tracker in an extensive video evaluation.     

Local motion feature aided ground moving target tracking with GMTI and HRR measurements

Tracking ground moving targets with ground moving target indicator (GMTI) measurements only could face a potential problem of losing tracks or track mingling, if the targets move together within the range of GMTI sensing uncertainty for an extended period of time. We propose a remedy for this problem by using local motion features extracted from high resolution range (HRR) profiles to assist data association. Unlike other HRR features, the new local motion features carry both spatial and temporal information and are ideal for feature aided tracking. A probabilistic logic based tracker is developed for local motion feature aided tracking.     

一种新的统计仿射不变量

本文在充分分析了现有各种仿射不变量的基础上，提出了一种新的统计仿射不变量，它对于发生尺度变化、旋转、扭曲和平移的目标具有不变性。实验结果表明，相对于传统的仿射不变量，在目标轮廓分割不完整或噪声污染的情况下，仍能够保持较高的稳健性，同时克服了基于轮廓的小波方法和傅立叶级数等方法对目标轮廓出现缺陷时的不足，
，在图像目标识别中具有实用价值。     

综合颜色和轮廓曲线特征的图像检索方法研究

传统的基于内容图像检索（CBIR）及跟踪算法主要利用图像的颜色、纹理等特征进行相似性比较,但大量的实验和应用也表明利用颜色和纹理进行图像相似性比较在空间结构和对象形状上难以精确控制,致使图像检索经常出现一些不可预料的结果。为了提高图像在形状、颜色及纹理上的检索精度,提出了一种综合颜色和图像轮廓曲线特征的检索方法。该方法分割图像并提取图像中感兴趣对象的轮廓,对提取的轮廓进行仿射变换及最小值化处理,经处理后的轮廓带有边缘的完整信息,具有几何不变性;利用聚类的颜色信息,提取主聚类的直方图,所提取的直方图不仅包含了主聚类的颜色信息也包含了该聚类的空间位置信息。利用检索对象与被检索对象的颜色距离直方图及轮廓曲线距离偏差的加权平均度量检索及被检索对象的相似性。实验结果表明,针对基于感兴趣对象的图像检索问题,给出了一种具有高度检索精度的算法。     

Foundations of semi-differential invariants

This paper elaborates the theoretical foundations of a semi-differential framework for invariance. Semi-differential invariants combine coordinates and their derivatives with respect to some contour parameter at several points of the image contour, thus allowing for an optimal trade-off between identification of points and the calculation of derivatives. A systematic way of generating complete and independent sets of such invariants is presented. It is also shown that invariance under reparametrisation can be cast in the same framework. The theory is illustrated by a complete analysis of 2D affine transformations. In a companion paper (Pauwels et al. 1995) these affine semi-differential invariants are implemented in the computer program FORM (Flat Object Recognition Method) for the recognition of planar contours under pseudo-perspective projection.Post-doctoral Research Fellow of the Belgian National Fund for Scientific Research (N.F.W.O.).     

带宽自适应的Mean-Shift跟踪算法研究

针对图像跟踪中目标的尺度和旋转变化,将Lindeberg的尺度理论与Mean-Shift算法结合起来,提出了一种带宽自适应Mean-Shift跟踪算法。该算法在Mean-Shift的框架下,将尺度和旋转量与平移量同等看待,通过求解核函数带宽,计算出目标的变化参数,最终精确定位目标。另外,引入SAD算法对目标进行先期粗略定位,克服了目标做无规律大位移运动时Mean-Shift算法跟踪效果不佳的问题,同时也降低了Mean-Shift算法的迭代收敛次数。大量实验仿真表明,该算法对目标的仿射变化、非刚性形态变化,以及无规律的大位移运动具有有效性和鲁棒性。     

结合轮廓与形状特征的仿射形状匹配

目的 针对仿射变换下形状匹配中存在的描述子对形状的描述能力不足,以及描述子计算耗时大的问题,改进基于所有图像点投影的方法,提出一种利用轮廓计算投影面积的仿射形状匹配算法。方法 该算法分为粗匹配和精匹配两个阶段。粗匹配阶段以CSS角点作为备选特征点,首先统计轮廓投影面积分布作为特征点描述子;然后利用动态规划蚁群算法匹配两幅图片公共特征点序列,并将匹配好的特征点序列记为对应的新特征点;最后采用该新特征点划分目标曲线,得到对应的轮廓曲线;这一阶段的目的是对形状的筛选以及寻找一致的轮廓特征点,同时完成轮廓曲线的划分。精匹配阶段,采用小波仿射不变描述子,对粗匹配阶段匹配代价最小的5%的目标进行对应曲线匹配,得到精匹配阶段的匹配代价,从而实现对仿射目标的识别;精匹配弥补了描述子对轮廓细节描述不足的问题。结果 算法的平均检索速度比传统基于形状投影分布描述子提高44.3%,在MPEG-7图像库上的检索效果为98.65%,在MPEG-7仿射图像库上的查准率与查全率综合评价指标比传统的基于形状投影分布描述子高3.1%,比形状上下文高25%。结论 本文算法匹配效果好,效率高,抗噪性强,解决了仿射描述子计算速度慢、描述能力不足的问题,能有效地应用于仿射形状匹配与检索领域。     

Trackability as a cue for potential obstacle identification and 3-D description

In many man-made environments, obstacles in the path of a mobile robot can be characterized asshallow, that is, they have relatively small extent in depth compared to the distance from the camera. We present a framework for segmenting shallow structures from their background over a sequence of images. Shallowness is first quantified asaffine describability. This is embedded in a tracking system within which hypothesized model structures undergo a cycle of prediction and model-matching. Structures emerge either as shallow or nonshallow based on theiraffine trackability. Two major contributions of this work are (i) aggregate object tracking based on 3-D motion and structure constraints in constrast with traditional primitive feature tracking based on image motion heuristics, and (ii) use of temporal behavior for object segmentation and 3-D reconstruction.     

Combining object and feature dynamics in probabilistic tracking

Objects can exhibit different dynamics at different spatio-temporal scales, a property that is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image features that are then used as inputs to a system for tracking the object using a global dynamic model. Approximate local dynamics may be brittle—point trackers drift due to image noise and adaptive background models adapt to foreground objects that become stationary—and constraints from the global model can make them more robust. We propose a probabilistic framework for incorporating knowledge about global dynamics into the local feature extraction processes. A global tracking algorithm can be formulated as a generative model and used to predict feature values thereby influencing the observation process of the feature extractor, which in turn produces feature values that are used in high-level inference. We combine such models utilizing a multichain graphical model framework. We show the utility of our framework for improving feature tracking as well as shape and motion estimates in a batch factorization algorithm. We also propose an approximate filtering algorithm appropriate for online applications and demonstrate its application to tasks in background subtraction, structure from motion and articulated body tracking.     

Pose robust face tracking by combining view-based AAMs and temporal filters

Active appearance models (AAMs) are useful for face tracking for the advantages of detailed face interpretation, accurate alignment and high efficiency. However, they are sensitive to initial parameters and may easily be stuck in local minima due to the gradient-descent optimization, which makes the AAM based face tracker unstable in the presence of large pose deviation and fast motion. In this paper, we propose to combine the view-based AAMs with two novel temporal filters to overcome the limitations. First, we build a new view space based on the shape parameters of AAMs, instead of the model parameters controlling both the shape and appearance, for the purpose of pose estimation. Then the Kalman filter is used to simultaneously update the pose and shape parameters for a better fitting of each frame. Second, we propose a temporal matching filter which is twofold. The inter-frame local appearance constraint is incorporated into AAM fitting, where the mechanism of the active shape model (ASM) is also implemented in a unified framework to find more accurate matching points. Moreover, we propose to initialize the shape with correspondences found by a random forest based local feature matching. By introducing the local information and temporal correspondences, the twofold temporal matching filter improves the tracking stability when confronted with fast appearance changes. Experimental results show that our algorithm is more pose robust than basic AAMs and some state-of-art AAM based methods, and that it can also handle large expressions and non-extreme illumination changes in test video sequences.     

无锚双注意力孪生网络的视觉跟踪

针对跟踪过程中因光照变化、快速运动及尺度变化等造成的角点定位精准度下降问题,受SiamCAR的跟踪框架启发提出一种无锚双注意力孪生网络的视觉跟踪算法.首先,算法的主干网络采用ResNet-50并结合增强多层融合特征图进行特征提取,充分利用网络浅层特征的定位信息和深层次的语义信息,提高算法对目标特征的语义理解能力;然后,构建混合注意力模块缓解无锚跟踪器角点定位不准确问题,提高算法的跟踪准确性和定位精度;最后,在GOT10K、UAV123、LaSOT等数据集上进行广泛实验,并与当前的先进跟踪器进行比较,该算法可以较好地抵抗光照变化、快速运动及尺度变化等多种复杂因素带来的影响,同时,在多项评测指标上获得了良好的跟踪性能.     

局部特征与全局特征结合的HMM静态手势识别

针对静态手势识别问题,提出了一种综合考虑局部形状与全局轮廓的隐马尔科夫模型(HMM)静态手势识别算法。该算法提取局部形状熵特征与上层轮廓特征分别作为训练数据训练每类手势的HMM参数。测试时,先凭借局部形状熵特征得出初步识别结果,然后根据初步识别结果的模糊性,附加与局部特征互补的上层轮廓特征进行再识别,得出最终识别结果。实验结果表明,该算法对于形状差异占主导地位的手势库有很好的效果,并且将静态手势的空间序列模拟成时间序列使得静态手势识别具有空间尺度不变性;同时该算法合理控制特征维数,一定程度上弱化了HMM训练时间长的弊端,加快了识别的速度。     

Resolving motion correspondence for densely moving points

Studies the motion correspondence problem for which a diversity of qualitative and statistical solutions exist. We concentrate on qualitative modeling, especially in situations where assignment conflicts arise either because multiple features compete for one detected point or because multiple detected points fit a single feature point. We leave out the possibility of point track initiation and termination because that principally conflicts with allowing for temporary point occlusion. We introduce individual, combined, and global motion models and fit existing qualitative solutions in this framework. Additionally, we present a tracking algorithm that satisfies these-possibly constrained-models in a greedy matching sense, including an effective way to handle detection errors and occlusion. The performance evaluation shows that the proposed algorithm outperforms existing greedy matching algorithms. Finally, we describe an extension to the tracker that enables automatic initialization of the point tracks. Several experiments show that the extended algorithm is efficient, hardly sensitive to its few parameters, and qualitatively better than other algorithms, including the presumed optimal statistical multiple hypothesis tracker     

Restricted affine motion compensation and estimation in video coding with particle filtering and importance sampling: a multi-resolution approach

In this paper, we propose a multi-resolution affine block-based tracker for motion estimation and compensation, compatible with existing video coding standards such as H.264 and HEVC. We propose three modifications to traditional motion compensation techniques in video coding standards such as H.264 and HEVC. First, we replace traditional search methods with an efficient particle filtering-based method, which incorporates information from both spatial and temporal continuity. Second, we use a higher order linear model in place of the traditional translation motion model in these standards to efficiently represent complex motions such as rotation and zoom. Third, we propose a multi-resolution framework that enables efficient parameter estimation. Results of extensive experimentation show reduced residual energy and better Peak Signal-to-Noise Ratio (PSNR, hereafter) as compared to H.264/HEVC for instance, especially in regions of complex motion such as zooming and rotation.     

Real-Time Tracking of Visually Attended Objects in Virtual Environments and Its Application to LOD

This paper presents a real-time framework for computationally tracking objects visually attended by the user while navigating in interactive virtual environments. In addition to the conventional bottom-up (stimulus-driven) saliency map, the proposed framework uses top-down (goal-directed) contexts inferred from the user's spatial and temporal behaviors, and identifies the most plausibly attended objects among candidates in the object saliency map. The computational framework was implemented using GPU, exhibiting high computational performance adequate for interactive virtual environments. A user experiment was also conducted to evaluate the prediction accuracy of the tracking framework by comparing objects regarded as visually attended by the framework to actual human gaze collected with an eye tracker. The results indicated that the accuracy was in the level well supported by the theory of human cognition for visually identifying single and multiple attentive targets, especially owing to the addition of top-down contextual information. Finally, we demonstrate how the visual attention tracking framework can be applied to managing the level of details in virtual environments, without any hardware for head or eye tracking.     

A graphical model based solution to the facial feature point tracking problem

In this paper a facial feature point tracker that is motivated by applications such as human-computer interfaces and facial expression analysis systems is proposed. The proposed tracker is based on a graphical model framework. The facial features are tracked through video streams by incorporating statistical relations in time as well as spatial relations between feature points. By exploiting the spatial relationships between feature points, the proposed method provides robustness in real-world conditions such as arbitrary head movements and occlusions. A Gabor feature-based occlusion detector is developed and used to handle occlusions. The performance of the proposed tracker has been evaluated on real video data under various conditions including occluded facial gestures and head movements. It is also compared to two popular methods, one based on Kalman filtering exploiting temporal relations, and the other based on active appearance models (AAM). Improvements provided by the proposed approach are demonstrated through both visual displays and quantitative analysis.     

View-Invariant Analysis of Cyclic Motion

This paper presents a general framework for image-based analysis of 3D repeating motions that addresses two limitations in the state of the art. First, the assumption that a motion be perfectly even from one cycle to the next is relaxed. Real repeating motions tend not to be perfectly even, i.e., the length of a cycle varies through time because of physically important changes in the scene. A generalization of period is defined for repeating motions that makes this temporal variation explicit. This representation, called the period trace, is compact and purely temporal, describing the evolution of an object or scene without reference to spatial quantities such as position or velocity. Second, the requirement that the observer be stationary is removed. Observer motion complicates image analysis because an object that undergoes a 3D repeating motion will generally not produce a repeating sequence of images. Using principles of affine invariance, we derive necessary and sufficient conditions for an image sequence to be the projection of a 3D repeating motion, accounting for changes in viewpoint and other camera parameters. Unlike previous work in visual invariance, however, our approach is applicable to objects and scenes whose motion is highly non-rigid. Experiments on real image sequences demonstrate how the approach may be used to detect several types of purely temporal motion features, relating to motion trends and irregularities. Applications to athletic and medical motion analysis are discussed.