基于稀疏表示的视频目标跟踪研究综述

视频目标跟踪在计算机视觉领域有着广泛应用,由于目标自身和外界环境变化的复杂性和难以预知性,使得复杂场景下鲁棒实时目标跟踪成为一项亟待解决的关键问题.由于视觉信息可以用少量神经元进行稀疏表示,因此稀疏表示已经广泛应用于人脸识别、目标检测和目标跟踪等计算机视觉领域.本文旨在对基于稀疏表示的视频目标跟踪算法进行综述.首先,介绍了基于稀疏表示的视频目标跟踪算法中的字典组成;其次,介绍了稀疏模型的构建及求解算法和模型更新,并对算法复杂度进行了简要分析;然后,对现有公开代码的稀疏表示跟踪算法在测试数据上进行了实验分析,结合算法模型和实验结果对其进行了分析;最后,对基于稀疏表示的视频跟踪算法存在问题进行了讨论,并对未来的研究趋势进行了展望.     

基于外观模型学习的视频目标跟踪方法综述

视频跟踪是机器视觉领域中的热点研究问题,在过去的几十年内得到了广泛研究.为了获得鲁棒的跟踪效果,设计能够适应跟踪目标外观变化的外观模型成为算法研究中的一种重要内容.近年来,将机器学习理论引入外观模型设计中的思想大大推动了视频跟踪研究的发展.为了使读者能够快速了解其发展的趋势并且掌握基于外观模型学习跟踪算法研究的技术,在介绍外观模型学习跟踪算法原理和机制的基础上,重点综述了外观模型学习跟踪方法的研究进展,包括目标特征描述和3类主要目标外观建模方式及其各自研究过程中跟踪方法的对比与分析,进而总结了外观模型学习跟踪算法在理论及应用方面的研究现状,最后提出进一步研究的主要发展内容和趋势.     

视觉单目标跟踪算法综述

目标跟踪技术根据视频上下文信息，建立一个跟踪模型对目标的运动状态进行预测，被广泛用于智能视频监控、自动驾驶、机器人导航、人机交互等多个计算机视觉领域。随着深度学习在语音识别，图像分类以及目标检测等领域的巨大成功，越来越多的研究将深度学习框架应用于目标跟踪任务中。介绍了当前单目标跟踪任务的难点和传统的方法,重点分析了当前基于深度学习的单目标跟踪算法的发展现状，从预训练网络＋相关滤波算法、基于孪生网络的方法、基于卷积神经网络的方法、基于生成对抗网络的方法以及其他深度学习方法几个方面，分别对当前流行的深度学习目标跟踪算法进行了概述。此外，总结了用于评测单目标跟踪算法性能的代表性数据集，列举了最新的研究成果在不同数据集上的实验结果并分析了当前单目标跟踪领域的问题和趋势。     

判别特征回归的鲁棒目标跟踪

目的 近年来,目标跟踪领域取得了很大进步,但是由于尺度变化,运动,形状畸变或者遮挡等造成的外观变化,仍然是目标跟踪中的一大挑战,因而有效的图像表达方法是提高目标跟踪鲁棒性的一个关键因素。方法 从中层视觉角度出发,首先对训练图像进行超像素分割,将得到特征向量集以及对应的置信值作为输入值,通过特征回归的方法建立目标跟踪中的判别外观模型,将跟踪图像的特征向量输入该模型,得到候选区域的置信值,从而高效地分离前景和背景,确定目标区域。结果 在公开数据集上进行跟踪实验。本文算法能较好地处理目标尺度变化、姿态变化、光照变化、形状畸变、遮挡等外观变化;和主流跟踪算法进行对比,本文算法在跟踪误差方面表现出色,在carScale、subway、tiger1视频中能取得最好结果,平均误差为12像素,3像素和21像素;和同类型的方法相比,本文算法在算法效率上表现出色,所有视频的跟踪效率均高于同类型算法,在carScale视频中的效率,是同类算法效率的32倍。结论 实验结果表明,本文目标跟踪算法具有高效性和鲁棒性,适用于目标发生外观变化时的目标跟踪问题。目前跟踪中只用了单一特征,未来考虑融合多特征来提升算法鲁棒性和准确度。     

在线多目标视频跟踪算法综述

视频多目标跟踪是计算机视觉领域重要的研究课题之一,不论是在军用还是民用都有广泛应用。目前对单目标的跟踪算法研究已经相当成熟,但对于多目标跟踪的研究还处于发展阶段。重点研究了多目标跟踪过程中的四个重要阶段：特征提取、检测器、数据关联、跟踪器。特征提取阶段详细介绍了目前主流的特征提取方法以及各个方法之间的优缺点;检测器阶段首先详细介绍了目标外观模型在具体应用场景中的跟踪效果,接着对基于检测跟踪的多目标跟踪算法和基于深度学习的多跟踪算法进行了分析;跟踪器阶段分别介绍了目标运动模型的建立和利用不同跟踪器混合的多目标跟踪算法;数据关联阶段分别介绍了基于能量最小化的多目标跟踪以及常用的数据关联算法。接着,介绍了目前主流的数据集以及评测方法;最后对多目标跟踪未来的发展进行了思考和展望。     

目标跟踪综述

随着深度学习与人工智能技术的不断发展,视频目标跟踪已经成为了计算机视觉的重要研究内容,在公安布控、人机交互、交通管制、军事等各个领域起到越来越重要的作用。尽管现在国内外学者提出了多种目标跟踪算法,也搭建了较为完善的目标跟踪系统,但是算法的鲁棒性依然是一个比较大的挑战。本文对运动目标跟踪系统结构进行了简要介绍,并从特征提取及融合、外观模型、目标搜索等方面详细阐述了目前主流运动目标跟踪算法。然后对目标跟踪算法在深度学习大环境下的新发展进行了分析,从基于深度学习的目标跟踪及目标检测算法角度分析了深度学习在提高目标检测算法鲁棒性方面的有效性,最后概述了深度学习在视频目标检测算法中的具体应用并对其未来发展进行了展望。     

基于形状上下文和粒子滤波的多目标跟踪

目标跟踪是计算机视觉领域里研究的热点和难点。提出一种基于形状上下文和粒子滤波的多目标跟踪算法,通过在跟踪过程中融入目标检测信息来处理目标进入与离开场景问题和目标重叠与分离问题。首先,采用自适应增强检测算法对视频区域中的目标进行检测;然后,利用形状上下文特征来建立被跟踪目标的外观模型;最后,利用粒子滤波方法进行粒子的选择和目标的跟踪。实验证明,提出的算法能够有效处理目标进入与离开场景的问题和目标重合与分离的问题,在单一背景和复杂背景下都能进行较为准确的跟踪,还能一定程度上处理部分遮挡问题。     

基于视觉注意机制的目标跟踪方法

提出一种基于视觉注意机制的运动目标跟踪方法。该方法借鉴人类的视觉注意机制的研究成果,建立视觉注意机制的计算模型,计算视频中各部分内容的视觉显著性。结合视觉显著性计算结果,提取视频图像中的显著性目标。利用颜色分布模型作为目标的特征表示模型,与视频中各显著目标进行特征匹配,实现目标的跟踪。在多个视频序列中进行实验,并给出相应的实验结果及分析。实验结果表明,提出的目标检测与跟踪算法是正确有效的。     

基于视频分析的智能监控系统

智能监控是当前计算机视觉研究的热点领域之一。针对室内监控的具体特点,实现了一种基于视频分析的智能检测跟踪监控系统。利用基于统计模型的目标检测算法提取运动目标;然后结合Meanshift算法对目标进行粗跟踪;最后针对Meanshift算法无法实时改变跟踪窗大小的缺陷,提出边界力调整算法以自适应更新跟踪窗窗宽。并以DM642数字图像处理DSP为核心,设计并搭建了智能视频监控平台。实验表明,该系统可以实时有效地检测、跟踪室内运动目标。     

深度学习的目标跟踪算法综述

目标跟踪是利用一个视频或图像序列的上下文信息,对目标的外观和运动信息进行建模,从而对目标运动状态进行预测并标定目标位置的一种技术,是计算机视觉的一个重要基础问题,具有重要的理论研究意义和应用价值,在智能视频监控系统、智能人机交互、智能交通和视觉导航系统等方面具有广泛应用。大数据时代的到来及深度学习方法的出现,为目标跟踪的研究提供了新的契机。本文首先阐述了目标跟踪的基本研究框架,从观测模型的角度对现有目标跟踪的历史进行回顾,指出深度学习为获得更为鲁棒的观测模型提供了可能;进而从深度判别模型、深度生成式模型等方面介绍了适用于目标跟踪的深度学习方法;从网络结构、功能划分和网络训练等几个角度对目前的深度目标跟踪方法进行分类并深入地阐述和分析了当前的深度目标跟踪方法;然后,补充介绍了其他一些深度目标跟踪方法,包括基于分类与回归融合的深度目标跟踪方法、基于强化学习的深度目标跟踪方法、基于集成学习的深度目标跟踪方法和基于元学习的深度目标跟踪方法等;之后,介绍了目前主要的适用于深度目标跟踪的数据库及其评测方法;接下来从移动端跟踪系统,基于检测与跟踪的系统等方面深入分析与总结了目标跟踪中的最新具体应用情况,最后对深度学习方法在目标跟踪中存在的训练数据不足、实时跟踪和长程跟踪等问题进行分析,并对未来的发展方向进行了展望。     

Backtracking: Retrospective multi-target tracking

We introduce a multi-target tracking algorithm that operates on prerecorded video as typically found in post-incident surveillance camera investigation. Apart from being robust to visual challenges such as occlusion and variation in camera view, our algorithm is also robust to temporal challenges, in particular unknown variation in frame rate. The complication with variation in frame rate is that it invalidates motion estimation. As such, tracking algorithms based on motion models will show decreased performance. On the other hand, appearance based detection in individual frames suffers from a plethora of false detections. Our tracking algorithm, albeit relying on appearance based detection, deals robustly with the caveats of both approaches. The solution rests on the fact that for prerecorded video we can make fully informed choices; not only based on preceding, but also based on following frames. We start off from an appearance based object detection algorithm able to detect in each frame all target objects. From this we build a graph structure. The detections form the graph’s nodes and the vertices are formed by connecting each detection in a frame to all detections in the following frame. Thus, each path through the graph shows some particular selection of successive detections. Tracking is then reformulated as a heuristic search for optimal paths, where optimal means to find all detections belonging to a single object and excluding any other detection. We show that this approach, without an explicit motion model, is robust to both the visual and temporal challenges.     

基于Mean Shift算法的目标跟踪综述

介绍Mean Shift算法及其研究进展,在众多计算机视觉研究和实际应用,尤其是视频跟踪研究中,基于Mean Shift算法的视频跟踪被大量应用。就目前所应用的跟踪算法,Mean Shift算法使跟踪中存在的很多问题得到了解决,例如运动目标的突然加速,背景的干扰,目标和目标以及目标和背景之间的遮挡,背景或者目标外部的变化等。对目前基于Mean Shift算法本身及其改进方法的理论和应用进行分类和比较,详述其各自方法内容和优缺点。     

基于视觉的目标检测与跟踪综述

基于视觉的目标检测与跟踪是图像处理、计算机视觉、模式识别等众多学科的交叉研究课题,在视频监控、虚拟现实、人机交互、自主导航等领域,具有重要的理论研究意义和实际应用价值.本文对目标检测与跟踪的发展历史、研究现状以及典型方法给出了较为全面的梳理和总结.首先,根据所处理的数据对象的不同,将目标检测分为基于背景建模和基于前景建模的方法,并分别对背景建模与特征表达方法进行了归纳总结.其次,根据跟踪过程有无目标检测的参与,将跟踪方法分为生成式与判别式,对基于统计的表观建模方法进行了归纳总结.然后,对典型算法的优缺点进行了梳理与分析,并给出了其在标准数据集上的性能对比.最后,总结了该领域待解决的难点问题,对其未来的发展趋势进行了展望.     

Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking

Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based algorithms cannot effectively represent spatial correlations between pixel values. Current tensor subspace-based algorithms construct an offline representation of image ensembles, and current online tensor subspace learning algorithms cannot be applied to background modeling and object tracking. In this paper, we propose an online tensor subspace learning algorithm which models appearance changes by incrementally learning a tensor subspace representation through adaptively updating the sample mean and an eigenbasis for each unfolding matrix of the tensor. The proposed incremental tensor subspace learning algorithm is applied to foreground segmentation and object tracking for grayscale and color image sequences. The new background models capture the intrinsic spatiotemporal characteristics of scenes. The new tracking algorithm captures the appearance characteristics of an object during tracking and uses a particle filter to estimate the optimal object state. Experimental evaluations against state-of-the-art algorithms demonstrate the promise and effectiveness of the proposed incremental tensor subspace learning algorithm, and its applications to foreground segmentation and object tracking.     

Efficient multi-feature PSO for fast gray level object-tracking

Robust and real-time moving object tracking is a tricky job in computer vision systems. The development of an efficient yet robust object tracker faces several obstacles, namely: dynamic appearance of deformable or articulated targets, dynamic backgrounds, variation in image intensity, and camera (ego) motion. In this paper, a novel tracking algorithm based on particle swarm optimization (PSO) method is proposed. PSO is a population-based stochastic optimization algorithm modeled after the simulation of the social behavior of bird flocks and animal hordes. In this algorithm, a multi-feature model is proposed for object detection to enhance the tracking accuracy and efficiency. The object's model is based on the gray level intensity. This model combines the effects of different object cases including zooming, scaling, rotating, etc. into a single cost function. The proposed algorithm is independent of object type and shape and can be used for many object tracking applications. Over 30 video sequences and having over 20,000 frames are used to test the developed PSO-based object tracking algorithm and compare it to classical object tracking algorithms as well as previously published PSO-based tracking algorithms. Our results demonstrate the efficiency and robustness of our developed algorithm relative to all other tested algorithms.     

Adaptive visual tracking using the prioritized Q-learning algorithm: MDP-based parameter learning approach

This paper introduces an adaptive visual tracking method that combines the adaptive appearance model and the optimization capability of the Markov decision process. Most tracking algorithms are limited due to variations in object appearance from changes in illumination, viewing angle, object scale, and object shape. This paper is motivated by the fact that tracking performance degradation is caused not only by changes in object appearance but also by the inflexible controls of tracker parameters. To the best of our knowledge, optimization of tracker parameters has not been thoroughly investigated, even though it critically influences tracking performance. The challenge is to equip an adaptive tracking algorithm with an optimization capability for a more flexible and robust appearance model. In this paper, the Markov decision process, which has been applied successfully in many dynamic systems, is employed to optimize an adaptive appearance model-based tracking algorithm. The adaptive visual tracking is formulated as a Markov decision process based dynamic parameter optimization problem with uncertain and incomplete information. The high computation requirements of the Markov decision process formulation are solved by the proposed prioritized Q-learning approach. We carried out extensive experiments using realistic video sets, and achieved very encouraging and competitive results.     

Dynamic tracking re-adjustment: a method for automatic tracking recovery in complex visual environments

Detection and analysis of events from video sequences is probably one of the most important research issues in computer vision and pattern analysis society. Before, however, applying methods and tools for analyzing actions, behavior or events, we need to implement robust and reliable tracking algorithms able to automatically monitor the movements of many objects in the scene regardless of the complexity of the background, existence of occlusions and illumination changes. Despite the recent research efforts in the field of object tracking, the main limitation of most of the existing algorithms is that they are not enriched with automatic recovery strategies able to re-initialize tracking whenever its performance severely deteriorates. This is addressed in this paper by proposing an automatic tracking recovery tool which improves the performance of any tracking algorithm whenever the results are not acceptable. For the recovery, non-linear object modeling tools are used which probabilistically label image regions to object classes. The models are also time varying. The first property is implemented in our case using concepts from functional analysis which allow parametrization of any arbitrary non-linear function (with some restrictions on its continuity) as a finite series of known functional components but of unknown coefficients. The second property is addressed by proposing an innovative algorithm that optimally estimates the non-linear model at an upcoming time instance based on the current non-linear models that have been already approximated. The architecture is enhanced by a decision mechanism which permits verification of the time instances in which tracking recovery should take place. Experimental results on a set of different video sequences that present complex visual phenomena (full and partial occlusions, illumination variations, complex background, etc) are depicted to demonstrate the efficiency of the proposed scheme in proving tracking in very difficult visual content conditions. Additionally, criteria are proposed to objectively evaluate the tracking performance and compare it with other strategies.