图 书 馆
这是怎么回事？ 发现动态场景中的时空依赖性What's going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes |
|
| 课程网址: | http://videolectures.net/cvpr2010_kuettel_wgo/ |
| 主讲教师: | Daniel Küttel |
| 开课单位: | 苏黎世联邦理工学院 |
| 开课时间: | 2010-07-19 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the right of way between different lanes or typical traffic light sequences. To extract them, sequences of activities need to be learned. While the first method extracts rules based on a learned topic model, the second model called DDP-HMM jointly learns co-occurring activities and their time dependencies. To this end we employ Dependent Dirichlet Processes to learn an arbitrary number of infinite Hidden Markov Models. In contrast to previous work, we build on state-of-the-art topic models that allow to automatically infer all parameters such as the optimal number of HMMs necessary to explain the rules governing a scene. The models are trained offline by Gibbs Sampling using unlabeled training data. |
| 关 键 词: | 时间依赖性; 复杂动态场景; 隐马尔可夫模型 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-03-13：lxf |
| 阅读次数: | 108 |