CASIA OpenIR  > 毕业生  > 博士学位论文
复杂场景下目标跟踪技术的研究
Alternative TitleObject Tracking under Complex Scenes
郭文
Subtype工学博士
Thesis Advisor徐常胜
2012-05-31
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword目标跟踪 鱼群优化算法 粒子滤波 半监督学习 最大置信度提升 视觉关注度 Object Tracking Fish Swarm Optimization Particle Filter Semi-supervised Learning Max-confidence Boosting Visual Attention
Abstract视觉目标跟踪是计算机视觉领域中的研究热点之一。在视频监控、人机交互、智能交通、视频检索等领域具有广阔的应用前景。虽然经过人们在目标跟踪领域几十年的研究,目标跟踪技术已经有了长足的发展,但是实现复杂场景中对任意目标进行稳定、准确的跟踪仍然有很多理论与技术问题亟需解决,特别是跟踪过程中的遮挡、背景干扰、目标的复杂运动和目标形状与表观变化等。本文从解决上述问题的角度对复杂场景下目标跟踪的关键技术进行了研究,分别在表观模型、贝叶斯跟踪、判别式的跟踪等方面取得一些创新的研究 成果。论文的主要贡献归纳如下: 1、为了提高均值漂移算法颜色直方图表观适应复杂场景下跟踪的能力,我们提出了一种基于视觉关注加权的均值漂移目标跟踪方法,将基于运动信息的动态关注度和基于KL变换处理的静态关注度结合起来提高跟踪区域直方图对目标的表达能力,同时为了提高算法对部分遮挡的鲁棒性,采用了交互式的贝叶斯滤波技术,提高了跟踪的性能。 2、我们提出了一种黎曼度量的鱼群优化贝叶斯目标跟踪方法。分析了基于协方差表观的贝叶斯跟踪方法存在的问题,提出采用人工鱼群算法优化粒子滤波的粒子,使得粒子更多的处于高似然度区域,提高了粒子的采样质量,缓解粒子的退化与贫化问题。目标的相似度计算采用了协方差算子黎曼度量,这种表观模型的表达提高了算法对目标跟踪中目标表观的变化以及复杂背景环境的影响。在处理部分遮挡的问题中,采用了分块的结构,这提高了算法对部分遮挡的鲁棒性,这几部分合理的融合在一起形成完整的黎曼度量下的鱼群优化贝叶斯目标跟踪方法。 3、我们提出了一种最大置信度提升算法目标跟踪方法,最大置信度提升算法把传统的自适应提升算法从确定性标签推广到了非确定性标签,是一种推广的半监督学习方法,不但将新加入的样本看作是无标签的样本来处理,而且利用了非确定性标签数据,从而保证了跟踪过程中特征更新的正确性,提高了目标与背景的分类精度,有效的避免了判别式跟踪方法由于分类误差而带来的累积误差。在理论上,我们深入的分析了最大置信度提升算法,并通过理论证明了传统的自适应提升算法是最大置信度提升算法的一种特例,这也扩展了自适应提升算法的应用范围。 4、针对集成跟踪方法由于分类器误差积累带来的错误更新导致跟踪漂移问题,我们提出了一种辅助子空间更新的自适应随机森林集成跟踪法。随机森林嵌入到集成跟踪框架,并采用了自组织的多视角融合的方式来得到更准确的置信度图,提高了分类器的分类精度,而子空间学习的更新方法则可以辅助分类器的更新,减少分类器错误的特征更新,维持分类器具有较高的判别性能。
Other AbstractObject tracking is one of the hottest research topics in the field of computer vision. It has broad application prospects in video surveillance, human-computer interface, intelligent transportation, and video retrieval, etc. Although, with the efforts on theresearch of object tracking for several decades, the technology of object tracking has made great progress, it is still difficult to track an arbitrary object in complex environments. There are still many challenges and difficulties on the tracking under complex scenes, for example, occlusion, clutter background, complex motion and object appearance and shape changes, etc. In this dissertation, we focus on the key techniques of object tracking to solve the problems above. We have proposed some robust tracking methods from the view of object appearance, Bayesian tracking and discriminative tracking. The main contributions of the thesis include the following issues: 1、We propose a visual attention based mean shift tracking method. We combine the KL static attention with motion attention to obtain the object visual attention region. Since object representation using color histogram cannot be adapted to complex scenes, the weight of object representation based on visual attention is calculated for kernel density estimation mean shift tracker. To handle the occlusion, we propose an interactive Bayesian filter to combine the mean shift tracking method, which improve the performance of tracking. 2、We propose a robust fish swarm optimized Bayesian tracking method with Riemannian manifold metric. To solve the problems of covariance Bayesian tracking,we embed the fish swarm algorithm into particle filter, which enables most particles move into the region with high likelihood to avoid both degeneracy and impoverishment problems of particles. The calculation of similarity of object uses Riemannian manifold metric. The object representation is encoded in the proposed methods to handle difficult background and appearance changes. The fragment-based representation effectively utilizes the spatial distribution of object for partial occlusion tracking. All parts are integrated to form a complete framework of fish swarm optimized Bayesian tracking methods with Riemannian manifold metric. 3、We propose a max-confidence boosting learning framework based on object tracking method. The max-confidence boosting replaces the determinate labels with indeterministic labels as well as handing unlabel data, and it can be seen...
shelfnumWXLW1812
Other Identifier200918014628024
Language中文
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/6468
Collection毕业生_博士学位论文
Recommended Citation
GB/T 7714
郭文. 复杂场景下目标跟踪技术的研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2012.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20091801462802(14027KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[郭文]'s Articles
Baidu academic
Similar articles in Baidu academic
[郭文]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郭文]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.