Mining and Indexing Spatio-Temporal Patterns in Video Databases of Human Motion

本研究项目的目的是开发和测试视频数据库中人体运动轨迹的索引、检索和数据挖掘方法。计算机视觉技术正在被设计用于从视频中自动提取人体运动时间序列数据。数据挖掘算法正在开发中，可用于在提取的运动时间序列数据中发现聚类和其他模式。一个很有前途的方向是用隐马尔可夫模型（hmm）的有限混合来模拟观察到的运动时间序列序列。HMM表示的使用在建模方面具有一定的优势；然而，这对设计高效的聚类、索引和检索算法提出了重要的挑战。因此，必须制定更有效的、基于采样和基于嵌入的方法。在一个原型视频检索系统中，使用描述人体运动的真实视频数据集对所得想法进行评估。合成序列（例如，通过计算机图形生成）用于需要地面真值信息的定量性能实验。这项研究工作的成果可以使许多对社会有价值的应用成为可能：国土安全；基于视频的职业安全人体生物力学分析，以及舞蹈和运动训练；新闻、娱乐、体育视频档案管理与分析；视频数据库管理，用于对残疾人、体弱者或老年人的运动模式进行非侵入式监控，以检测衰退、危险，并在需要时提醒护理人员。可以在该项目的网站（http://www.cs.bu.edu/groups/ivc/MotionMining/）上访问结果。

The aim of this research project is to develop and test methods for indexing, retrieval, and data mining of human motion trajectories in video databases. Computer vision techniques are being devised for automatic extraction of human motion time series data from video. Data mining algorithms are being developed that can be used to discover clusters and other patterns in the extracted motion time-series data. One promising direction being explored is to model the observed motion time series sequences with a finite mixture of Hidden Markov Models (HMMs). Use of the HMM representation presents certain advantages with regard to modeling; however, it presents important challenges for the design of efficient clustering, indexing, and retrieval algorithms. Thus more efficient, sampling-based and embedding-based methods must be formulated. The resulting ideas are evaluated in a prototype video retrieval system, with real-world video datasets that depict human body motion. Synthetic sequences (e.g., generated via computer graphics) are used in quantitative performance experiments where ground truth information is required. The products of this research effort can enable numerous applications that are valuable to society: homeland security; video-based analysis of human biomechanics for occupational safety, as well as dance and sports training; archive management and analysis for news, entertainment, and sports video; and video database management for non-intrusive monitoring of the motion patterns of handicapped, infirm, or elderly people to detect decline, danger, and to alert caregivers when needed. Results can be accessed at the project's Web site (http://www.cs.bu.edu/groups/ivc/MotionMining/).