CASIA OpenIR  > 毕业生  > 博士学位论文
行为序列分割与聚类方法研究
其他题名Behavior Sequence Segmentation and Clustering
吴晓婕
学位类型工学博士
导师胡占义
2008-05-23
学位授予单位中国科学院研究生院
学位授予地点中国科学院自动化研究所
学位专业模式识别与智能系统
关键词行为分析 行为序列分割 无监督行为聚类 时空显著特征 Map-mrf Behavior Analysis Behavior Sequence Segmentation Unsupervised Behavior Clustering Spatio-temporal Salient Feature Map-mrf
摘要人的行为分析试图从包含人的图像序列中检测、跟踪、识别和解释人的行为。由于它在智能监控、人机交互、虚拟现实和基于内容的视频检索以及医疗诊断等方面有着广泛的应用前景和潜在的经济价值,成为当前计算机视觉研究领域中的一个前沿方向。本文主要开展了以下三个方面的研究:(1)基于局部时空特征的运动表征;(2)行为序列的自动分割;(3)无监督行为聚类。主要工作可以归纳如下: 1.对近年来行为分析高层处理环节的相关文献进行了综述。结合本文研究思路,对近年来文献中的行为分析方法从以下四个角度进行了综述:(1)运动表征方法;(2)行为序列分割方法;(3)基于无/半监督的聚类方法;(4)行为建模与识别方法。 2.研究了基于熵的图像显著点检测算法在行为分析中的应用,主要内容有:(1)提出了一种行为序列分割与聚类方法。该方法将运动的重复性和运动的一致性作为行为分割与聚类的依据,并利用在累计差分图像(ADI)上检测到的显著区域来刻画运动的重复性和一致性;(2)提出了一种基于局部时空显著区域的运动表征方法。将基于熵的图像显著点检测算法用于行为分析运动表征中,该方法提取的时空显著区域具有对图像序列稀疏、对运动区域稠密的特点,在时间、空间复杂度和特征的运动表征能力之间取得了比较好的折中。 3.提出了一种基于Segmental-DTW的行为序列分割与聚类方法。该方法的主要步骤包括:(1)采用等长有重叠的时间窗口对视频序列进行粗分割;(2)将粗分割的视频段两两作比较,通过Segmental-DTW算法分割出两个视频段中最相似的行为片断;(3)将行为片断的相似性转化为邻接图表示,通过图聚类方法对分割出的行为片断进行聚类。该方法采用了从粗到细的分割思想,能够比较准确地分割出视频序列中大量出现的行为的片断,并将相同行为的片断聚为一类。分割结果可直接用于行为建模和识别。 4.提出了一种行为自动分割与识别方法。从分析人运动的连贯性特点出发,指出行为序列的分割不是一个孤立的问题,应该和行为特征的描述、行为识别等问题联系起来考虑。采用了行为-特征共生矩阵构造偶图的方法进行无监督行为聚类,并探究了方法的合理性。提出了基于MAP-MRF的行为序列自动分割与识别方法,利用无监督行为聚类获得的关于行为类描述的先验知识,以及特征原型在低维空间中的距离关系,同时实现了对行为序列的分割与识别。
其他摘要Human behavior analysis attempts to detect, track and identify people, and more generally to interpret human behaviors, from image sequences involving humans. Human motion analysis is currently one of the most active research topics in computer vision. This strong interest is driven by a wide spectrum of promising applications in many areas such as smart surveillance, perceptual interface, virtual reality, content-based video retrieval, and etc. The thesis is mainly focused on the following aspects: (1) Local spatio-temporal feature representation; (2) Human behavior sequence segmentation; (3) Unsupervised behavior clustering. The main contributions are: 1. A review of the state of the art in behavior analysis is carried out, and the methods on behavior analysis are broadly divided into 4 classes: (1) Action representation methods; (2) Behavior segmentation methods; (3) Unsupervised/semi-supervised clustering methods; (4) Behavior modeling and recognition methods. 2. The entropy-based image salient point detection algorithm is used in human action analysis: (1) A novel approach, which uses the action repetition and consistency as the two cues of video contents, is proposed to cluster human actions automatically from video sequences. (2) A novel local spatio-temporal feature representation is introduced. 3. A novel unsupervised algorithm for behavior sequence segmentation is proposed. The algorithm consists of the following steps: (1) The video sequence is coarsely segmented into equal length subsequences with overlapping time window. (2) Segmental-DTW is used to find out matching behavior clips between pairs of video subsequences. (3) The similarity between behavior clips is represented by an adjacency graph, and an efficient graph clustering algorithm is used to generate behavior clusters. The algorithm, based on a coarse-to-fine strategy, is able to satisfactorily segment behavior sequences and cluster typical behavior patterns. The segmentation results could be used for further behavior modeling and recognition. 4. A novel human action sequence segmentation and recognition algorithm is proposed. Taking into account of the continuity of human actions, we argue that the problem of human action sequence segmentation should not be isolated from that of the action representation and recognition. In our work, human action sequences are clustered by constructing a new bipartite graph from the co-occurrence matrix of action sequences-prototype features, and a theoretical analysis is carried out on its applicabilities. Based on MAP-MRF as well as the prior knowledge of action clusters and the distances between prototype features in low-dimensional spaces, an automatic human action sequence segmentation and recognition algorithm is obtained.
馆藏号XWLW1184
其他标识符200518014628049
语种中文
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/6064
专题毕业生_博士学位论文
推荐引用方式
GB/T 7714
吴晓婕. 行为序列分割与聚类方法研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2008.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
CASIA_20051801462804(3931KB) 暂不开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[吴晓婕]的文章
百度学术
百度学术中相似的文章
[吴晓婕]的文章
必应学术
必应学术中相似的文章
[吴晓婕]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。