CASIA OpenIR  > 毕业生  > 博士学位论文
动态图像序列中运动目标行为分析与理解
其他题名Behavior Analysis and Understanding for Moving Objects in Dynamic Image Sequences
王莹
学位类型工学博士
导师谭铁牛
2008-01-27
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
关键词运动特征提取 运动特征表达 行为建模 多人交互行为识别 群行为分析 视觉监控 动态图像序列语义理解 Motion Feature Extraction And Representation Multi-people Interactive Activity Recognition Group Activity Analysis Visual Surveillance Generative Model Based Activity Recognition And An
摘要随着现代社会对安全要求的日益迫切,越来越多的摄像头分布在街头巷尾,如何快速的从海量视频数据中提取有用的信息,并自动分析场景中发生的事件引起计算机视觉研究者们的浓厚兴趣。于是动态图像序列中运动目标行为分析与理解应运而生,这是一种利用图像序列中运动目标的行为特征对其表现的行为进行识别与分析的技术,它可以赋予计算机类似于人一样的观察和理解动态场景的视觉能力。 视频中运动目标行为识别与分析涉及图像处理、模式识别、计算机视觉等多个科研领域,本文主要研究了运动目标特征提取、选择和表达,行为建模与识别,多视角事件分析解等问题,主要贡献包括: 1. 提出了一种基于形状的单人行为识别算法。目标轮廓广泛用作行为识别工作的底层特征,它可以为进一步的行为识别提供充分的空间信息,可是其高维向量为后面的行为建模带来沉重的计算代价。利用R 变换表达行为序列中单帧姿态信息,此变换具有几何不变性,这使得它在跟踪结果不理想,出现阴影,轮廓分离甚至帧丢失的情况下,都可以取得良好的识别效果,具有很强的噪声鲁棒性。而且,R 变换可以有效区分走、跑等相似性很强的行为。实验结果表明该算法不仅获得了令人满意的识别效果,而且拥有相对较低的计算代价。 2. 提出了一种基于参数降维的多人交互行为识别算法。在多人交互行为分析工作中,多个运动目标各自的运动信息以及彼此之间的相互关系导致高维的特征向量,且这些特征向量之间存在很大的相关性,从而引起代表观测与状态之间概率分布的协方差矩阵奇异。为此,我们在行为识别过程中,提出基于主成分分析的推理机制,改进传统隐马尔可夫模型的识别算法,从而取得优于传统HMM的识别性能。 3. 提出一种基于统计形状分析的群行为识别算法。群行为是行为识别研究工作中最具挑战性的,因为场景中不计其数的运动目标,彼此之间的相互遮挡以及低精度的运动图像都造成极大的困难。基于此,我们避开目标的单个跟踪,仅根据运动检测的结果,提取运动目标的地标点,进而采样描绘群行为曲线;并通过统计形状理论归一化镜头变化情况下的各种行为;据此特征,利用自回归滑动平均模型学习各个模型的参数,相较于HMM更多考虑了序列之间的依赖性,识别性能令人鼓舞。 4. 提出基于融合隐马尔可夫模型(FHMM)的多视角行为识别算法。单视角总是不能为行为识别提供足够的特征,容易引起理解上的歧异,我们提出利用FHMM融合两个正交视角下的行为特征,彼此互补的信息很大程度上避免了行为混淆现象。比较不同结构的融合模型发现,FHMM的识别性能优于其他结构的识别性能,即使在帧丢失情况下,依然获得令人满意的识别结果。
其他摘要With the growing requirement for safety, more and more cameras are utilized for visual surveillance. To keep computer aware what happens in the visual field automatically, motion and action understanding has long been the research focus, ranging from computer vision, pattern recognition to cognitive science. In this thesis, we concentrate on activity recognition and analysis in dynamic scenes, with focuses on motion feature extraction and representation, and generative modeling for object activity. Specifically, the following topics are addressed in the thesis: 1.Shape-based activity recognition using R transform: In activity recognition, object silhouette is commonly used to describe the spatial information which provides sufficient posture variance but with high dimensionality. Thus one key issue in activity modeling is to find an efficient feature descriptor with lower dimensionality, while keeping the robustness of the system. Consequently, R transform is adopted as a novel feature descriptor to represent the posture in each frame of an action sequence. Compared with other feature descriptors, R transform has low computational complexity, and is robust to frame loss, disjoint silhouette and holes in shape. Promising performance is achieved with the proposed method. 2.Interactive action analysis based on PCA-HMMs: In the case of multi-people activity recognition, much information is needed to represent low-level features. However, the high dimensionality of feature vectors for HMMs usually leads to covariance matrix singularity. In our solution, an improved inference scheme of HMM is proposed. Our approach distinguishes itself from the standard HMM work in that it uses the parameters with reduced dimensionality by PCA for recognition. Compared with traditional HMM, PCA-HMM gets higher recognition speed, and the performance gets comparatively better with the increase of the number of objects. 3.Group activity analysis based on statistical shape theory: Group activity analysis is challenging because of the large number of objects and occlusion among them. To tackle this problem, a system identification approach is proposed and applied in traffic surveillance. In this scheme, landmark points, instead of the complete trajectory are used to describe the dynamic information. Based on the landmark points, curves are formed and statistical shape theory is used to extract group activity features from the curves. Finally ARMA (Autoregressive and Moving Average) is adopted for feature learning and activity identification. As a robust scheme for activity analysis, the proposed solution is invariant with camera zoom and pan.
馆藏号XWLW1169
其他标识符200318014603029
语种中文
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/6047
专题毕业生_博士学位论文
推荐引用方式
GB/T 7714
王莹. 动态图像序列中运动目标行为分析与理解[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_20031801460302(7598KB) 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
[王莹]的文章
百度学术
百度学术中相似的文章
[王莹]的文章
必应学术
必应学术中相似的文章
[王莹]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。