arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0905.4614cs.AI
收藏

活动识别的逻辑程序设计方法

A Logic Programming Approach to Activity Recognition

NCSR Demokritos(希腊国家科学研究中心“德谟克利特”);Imperial College London(帝国理工学院)

A. Artikis, M. Sergot, G. Paliouras

摘要:

我们一直在开发一个系统,用于识别人类活动的视频内容的符号表示。我们的系统的输入是一组在视频帧上检测到的带有时间戳的短期活动。我们的系统的输出是一组公认的长期活动,这是预定义的短期活动的时间组合。对短期活动的约束,如果满足,导致识别的长期活动,表示使用方言的事件演算。我们通过几个典型的复杂活动的表现来说明方言的表现力。此外,我们提出了一个详细的评估系统,通过实验的基准数据集的监控视频。

英文摘要:

We have been developing a system for recognising human activity given a symbolic representation of video content. The input of our system is a set of time-stamped short-term activities detected on video frames. The output of our system is a set of recognised long-term activities, which are pre-defined temporal combinations of short-term activities. The constraints on the short-term activities that, if satisfied, lead to the recognition of a long-term activity, are expressed using a dialect of the Event Calculus. We illustrate the expressiveness of the dialect by showing the representation of several typical complex activities. Furthermore, we present a detailed evaluation of the system through experimentation on a benchmark dataset of surveillance videos.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑