基于检测的数据关联多目标跟踪算法研究

发布时间:2019-06-05 15:15
【摘要】:视频序列的多目标跟踪研究是计算机视觉领域的一个重要内容,已经广泛应用于国防、视频监控、智能导航/辅助驾驶、智能机器人、行为分析、视频检索、生物医学等领域。视频多目标跟踪的目的是在视频序列中标定出各个目标的运动轨迹。然而,受成像质量下降、噪声和背景干扰、目标外观和运动模式的变化、被跟踪目标数目的不确定性、复杂多变的遮挡等诸多因素的影响,多目标跟踪算法研究是一个颇具挑战性的课题,还面临大量的理论和技术问题有待解决。近十年来,随着目标检测器性能的不断提升,基于检测的目标跟踪方法引起了广泛的关注,已成为当前主流的多目标跟踪方法。这类方法将检测器输出的检测响应作为输入,通过数据关联技术将属于同一目标的检测响应逐一连接、最终获得各个目标的运动轨迹。关联模型设计是基于检测的数据关联技术的关键,一个好的关联模型应该尽可能的融合那些反映目标轨迹内在属性的观测信息,在噪声和复杂场景下提供可靠的轨迹关联。本文围绕多目标跟踪领域前沿发展动态,着重对关联模型及其在多目标跟踪方法中的应用进行了深入研究。主要工作包括以下四部分:(1)基于霍夫森林学习的多目标跟踪方法多级关联是一种有效的多目标跟踪方法,本文在逐级关联框架下,提出了一种基于霍夫森林分类器的多目标跟踪算法。首先通过保守关联算法生成可靠的短小轨迹片;随后以逐级处理方式从迹片集上提取具有判别性能的外观和运动特征,生成训练样本并构建霍夫森林;在测试阶段,利用森林叶子节点中存储的有效码元信息去估计轨迹片间的连接概率,最终将轨迹关联转化为最大后验概率准则(Maximum-A-Posterior, MAP)下的求解问题。实验证明了基于霍夫森林的轨迹片关联模型的有效性:与一些国外同行的近期算法相比较,该方法取得了与之相当的跟踪效果(2)基于遮挡推理模型的孤立响应点匹配由于运动场景的复杂性、频繁发生的遮挡等,即便是目前最先进的检测器也存虚检、漏检、检测不精确等问题;可靠轨迹片生成阶段所采取的保守关联策略也会遗漏一些检测响应。上述问题都将导致在最后的跟踪结果中,出现不能和任何轨迹相关联的孤立响应点,从而使得目标轨迹间隙增大、平滑性下降。针对此问题,本文提出一种新的遮挡推理模型,以此推断出遮挡目标的被遮挡区域和非遮挡区域;在此基础上设计被遮挡目标的融合特征描述,提出孤立响应点与目标轨迹间的匹配策略,有效解决了孤立响应点的目标归属问题。作为一种填补轨迹间隙的后处理技术,本章方法对于采用轨迹片关联的跟踪算法具有普适性。(3)基于霍夫森林条件随机场的多目标跟踪方法基于条件随机场(conditional random field, CRF)的多目标跟踪近年来已成为一个研究热点。作为CRF模型的核心,CRF模型参数估计和状态推理非常棘手,传统上通常采用近似算法或启发式方法对参数进行估计,而CRF推理过程也易陷入局部最优。本文提出霍夫森林条件随机场模型(Hough Forest Conditional Random Field ,HFRF),该方法通过SW-cuts算法计算MH跳转接受概率以实现状态推理求解,而利用霍夫森林提供CRF推理所需要的概率参数;HFRF将CRF模型参数学习和推理嵌入到同一个框架中,从而规避了传统CRF跟踪方法中的难题。此外,与传统的CRF图模型不同,HFRF对每条边额外定义了一个二元指示隐变量,将传统CRF中的二元组结构关系扩展到三元,可以考虑更多运动目标的时空域关系,利用该三元组结构有助于跟踪算法的优化和性能提升(4)基于数据联合表达的多目标跟踪方法传统的数据关联模型大多依据数据间的差异性建模,例如计算两个特征间的距离;这一操作本质上是降维过程,将导致原始数据可分性的部分丢失。针对此问题,本文在传统CRF图模型下,提出了一种基于数据联合分布建模的多目标跟踪算法。该方法构造二元势函数表征轨迹片间的相关性,构造高阶类别损失函数(正则项)用以约束求解的目标个数,在此基础上得到代价方程,最终通过代价最小化实现CRF模型下的类别标定。其中轨迹片间的势函数建模为两个假设条件下的数据联合分布,通过建立关联数据的相容性、相斥性概率,完成CRF模型的推理过程。该方法另一个特点是利用霍夫森林叶子节点间存储的样本类别的分布特性,以无参的形式实现两个假设条件下数据联合分布概率的估计。在多个数据库上进行的仿真实验证明了本文方法的有效性;该方法所提出的关联数据相容性、相斥性建模思想,为多目标跟踪算法设计提供了一种新的途径
[Abstract]:The multi-objective tracking of video sequences is an important content in the field of computer vision, and has been widely used in the fields of national defense, video surveillance, intelligent navigation/ assistant driving, intelligent robot, behavioral analysis, video retrieval, biomedicine and so on. The purpose of the video multi-target tracking is to calibrate the motion trajectory of each target in the video sequence. However, the study of multi-objective tracking algorithm is a challenging task, which is influenced by the image quality, noise and background interference, the target appearance and the motion pattern, the uncertainty of the number of tracked targets, and the complex and variable occlusion. There is also a large number of theoretical and technical problems to be solved. In the last ten years, with the continuous improvement of the performance of the target detector, the target tracking method based on the detection has attracted wide attention and has become the current multi-target tracking method. In the method, the detection response output by the detector is taken as an input, and the detection responses belonging to the same target are connected one by one by the data association technology, and finally the motion trail of each target is obtained. The design of the association model is the key to the data association technology based on the detection, and a good correlation model should be used to integrate the observation information reflecting the intrinsic attributes of the target track as much as possible, and provide a reliable track association under the noise and the complex scene. This paper focuses on the development of the multi-object tracking field, and focuses on the correlation model and its application in the multi-objective tracking method. The main work includes the following four parts: (1) The multi-objective tracking method based on the Hough forest learning is an effective multi-target tracking method. In this paper, a multi-target tracking algorithm based on the Hough forest classifier is proposed in this paper. the method comprises the following steps of: firstly, generating a reliable short track slice through a conservative correlation algorithm; then, extracting the appearance and the motion characteristic with the discrimination performance from the trace piece set in a step-by-step processing mode, generating a training sample and constructing a Hough forest; and in the testing phase, The connection probability between the track slices is estimated by using the effective symbol information stored in the forest leaf node, and finally the path association is converted into a solution problem under the maximum posterior probability criterion (MAP). The experiment proves the effectiveness of the correlation model of the track slice based on the Hough forest: compared with the recent algorithm of some foreign peers, the method has obtained the corresponding tracking effect (2) matching the complexity of the motion scene due to the isolated response point of the occlusion reasoning model, The frequently occurring occlusion, etc., even the most advanced detector at present, also has the problems of false detection, missed detection, inaccurate detection, etc. The conservative association strategy adopted in the reliable track slice generation phase will also miss some detection responses. The above problems will result in an isolated response point that cannot be associated with any trace in the final tracking result, so that the target track gap is increased and the smoothness decreases. In this paper, a new occlusion reasoning model is proposed, which can be used to infer the occluded area and the non-occlusion area of the occlusion target. Based on this, the fusion feature description of the occlusion target is designed, and the matching strategy between the isolated response point and the target track is proposed. And the problem of the target attribution of the isolated response point is effectively solved. As a post-processing technique to fill the gap of the track, the method of this chapter is of general applicability to the tracking algorithm associated with the track slice. (3) The multi-objective tracking method based on the conditional random field (CRF) has become a hot topic in recent years based on the multi-objective tracking method of the Hough forest condition with the airport. As the core of the CRF model, the parameter estimation and state-based reasoning of the CRF model is very difficult, and the parameters are estimated conventionally by using a heuristic algorithm or a heuristic method, and the CRF reasoning process is also easy to fall into a local optimal. In this paper, Hough Forest Conditional Random Field (HFRF) is proposed in this paper. The probability of MH jump acceptance is calculated by the SW-ctrl algorithm to realize the state-based reasoning, and the probability parameters required for CRF inference are provided by the Hough forest. HFRF has embedded CRF model parameter learning and reasoning in the same framework, thus avoiding the difficulty in the traditional CRF tracking method. In addition, unlike the traditional CRF map model, HFRF additionally defines a binary indicator hidden variable for each side, extends the binary group structure relationship in the traditional CRF to the ternary, and can consider the time-space relationship of the more moving target, the triple structure facilitates the optimization of the tracking algorithm and the performance improvement (4), and the traditional data association model of the multi-target tracking method based on the joint expression of the data is mostly modeled according to the difference between the data, for example, the distance between the two features is calculated; This operation is essentially a dimension reduction process that will result in a partial loss of the original data. In this paper, a multi-objective tracking algorithm based on data joint distribution modeling is presented in the traditional CRF model. The method constructs a binary potential function to characterize the correlation between the track slices, and constructs a high-order class loss function (regular term) to constrain the number of targets to be solved, and on the basis of which, a cost equation is obtained, and finally the class calibration under the CRF model is realized through the cost minimization. In which the potential function between the track pieces is modeled as the data joint distribution under two hypothetical conditions, and the reasoning process of the CRF model is completed by establishing the compatibility of the related data, the repulsion probability and the completion of the CRF model. The method is characterized in that the distribution characteristics of the sample categories stored among the tree leaf nodes of the Hough forest are utilized, and the estimation of the joint distribution probability of the data under the two assumptions is realized in the form of a non-reference. The simulation experiments carried out on a plurality of databases prove the effectiveness of the method in this paper. The proposed method is a new way to design the multi-object tracking algorithm.
【学位授予单位】:华中科技大学
【学位级别】:博士
【学位授予年份】:2016
【分类号】:TP391.41

【相似文献】

相关期刊论文 前10条

1 金忠;一种多目标跟踪算法[J];南京理工大学学报(自然科学版);1985年S1期

2 龚萍;张辉;毛征;张庆龙;孔文超;;融合局部熵二维熵的空中目标跟踪算法研究[J];国外电子测量技术;2014年01期

3 马奔,史忠科,皮燕妮;成像目标跟踪算法分析[J];西安电子科技大学学报;2005年03期

4 孙中森;孙俊喜;宋建中;乔双;;一种抗遮挡的运动目标跟踪算法[J];光学精密工程;2007年02期

5 陈爱华;孟勃;朱明;王艳华;;多模式融合的目标跟踪算法[J];光学精密工程;2009年01期

6 牛长锋;刘玉树;;融合多特征的粒子滤波目标跟踪算法[J];华中科技大学学报(自然科学版);2010年01期

7 蔡荣太;吴元昊;王明佳;吴庆祥;;视频目标跟踪算法综述[J];电视技术;2010年12期

8 佟国峰;蒋昭炎;谷久宏;庞晓磊;;基于随机蕨丛的长期目标跟踪算法[J];东北大学学报(自然科学版);2013年01期

9 曹晓丽;李明;邢玉娟;谭萍;;几种自动目标跟踪算法的比较研究[J];硅谷;2013年02期

10 王鲁平,李飚,胡敏露;一种基于多传感器数据融合的目标跟踪算法[J];红外与激光工程;2004年02期

相关会议论文 前10条

1 徐炳吉;;一种多站联合目标跟踪算法[A];数学及其应用文集——中南模糊数学和系统分会第三届年会论文集(上卷)[C];1995年

2 杜方芳;刘士荣;邱雪娜;;一种改进的粒子滤波目标跟踪算法[A];PCC2009—第20届中国过程控制会议论文集[C];2009年

3 付晓薇;方康玲;李曦;;一种基于特征的多目标跟踪算法[A];2003年中国智能自动化会议论文集(下册)[C];2003年

4 许伟村;赵清杰;;一种基于粒子滤波的多目标跟踪算法[A];2011年中国智能自动化学术会议论文集(第一分册)[C];2011年

5 李军;张华;单梁;;一种基于Mean shift和粒子滤波的综合目标跟踪算法[A];2009年中国智能自动化会议论文集(第七分册)[南京理工大学学报(增刊)][C];2009年

6 肖敬若;胡伏原;郑江滨;张艳宁;;一种有效的多目标跟踪算法[A];第十二届全国信号处理学术年会(CCSP-2005)论文集[C];2005年

7 郑黎义;陈兴无;王磊;李正东;;红外/雷达双传感器融合目标跟踪算法[A];中国工程物理研究院科技年报(2005)[C];2005年

8 张震宇;王立松;;基于粒子滤波的传感器目标跟踪算法[A];2008年中国高校通信类院系学术研讨会论文集(上册)[C];2009年

9 王亚楠;陈杰;甘明刚;;基于差分进化的改进粒子滤波目标跟踪算法[A];中国自动化学会控制理论专业委员会C卷[C];2011年

10 张涛;费树岷;胡刚;;基于多特征信息自适应融合的视频目标跟踪算法[A];第二十九届中国控制会议论文集[C];2010年

相关博士学位论文 前10条

1 胡子军;基于随机有限集的雷达多目标跟踪算法研究[D];西安电子科技大学;2015年

2 张雷;复杂场景下实时目标跟踪算法及实现技术研究[D];中国科学院研究生院(长春光学精密机械与物理研究所);2016年

3 王晶晶;复杂拥挤环境下协同视频监控中目标跟踪算法研究[D];中国科学技术大学;2016年

4 田浩;基于核函数的目标跟踪算法研究[D];长安大学;2016年

5 秦永;基于随机有限集的目标跟踪算法研究[D];华中科技大学;2016年

6 项俊;基于检测的数据关联多目标跟踪算法研究[D];华中科技大学;2016年

7 卢建国;基于粒子滤波的视频目标跟踪算法研究[D];北京邮电大学;2011年

8 冯巍;分布式多视角目标跟踪算法研究[D];复旦大学;2011年

9 王书朋;视频目标跟踪算法研究[D];西安电子科技大学;2009年

10 刘晴;基于区域特征的目标跟踪算法研究[D];北京理工大学;2014年

相关硕士学位论文 前10条

1 张健;形变目标跟踪算法的研究与实现[D];辽宁大学;2015年

2 张巧丽;基于LabVIEW的运动目标跟踪算法研究与实现[D];陕西科技大学;2015年

3 钟宝康;基于压缩感知的预测目标跟踪算法研究[D];江西理工大学;2015年

4 薛桐;基于CamShift的运动目标跟踪算法研究[D];沈阳理工大学;2015年

5 王增宇;基于稀疏表达的目标跟踪算法研究[D];沈阳理工大学;2015年

6 王静;结构化的表观模型及两阶段目标跟踪算法研究[D];沈阳理工大学;2015年

7 葛凯蓉;自然场景下目标跟踪算法的研究[D];山东大学;2015年

8 向伟;基于检测的目标跟踪算法研究[D];上海交通大学;2015年

9 单顺勇;结合多示例学习和模板匹配的目标跟踪算法研究[D];江西理工大学;2015年

10 张碧武;基于单目视觉的目标跟踪算法的研究与实现[D];电子科技大学;2015年



本文编号:2493621

资料下载
论文发表

本文链接:https://www.wllwen.com/shoufeilunwen/xxkjbs/2493621.html


Copyright(c)文论论文网All Rights Reserved | 网站地图 |

版权申明:资料由用户5571d***提供,本站仅收录摘要或目录,作者需要删除请E-mail邮箱bigeng88@qq.com