Integrated Sensing: 3D Description and Recognition of Human Activities Using Distributed Cameras

在这两年的努力中，我们建议解决在解释由一组室内或室外摄像机同时收集的视频流时出现的一些基本研究问题。具体地说，我们对使用分布式摄像机推断一个或多个人类的动作和活动感兴趣。我们建议开发新的方法来检测和跟踪人体，使用身体部位的3D模型，并对人类从事的活动进行准不变识别。我们将利用蒙特卡罗马尔可夫链技术在估计后验概率密度函数的计算方面取得的最新进展来推断人类的描述及其活动。

In this two-year effort, we propose to address some of the basic research issues that arise in the interpretation of video streams, simultaneously collected by a set of indoor or outdoor cameras.Specifically, we are interested in inferring movements and activities of one or more humans usingdistributed cameras. We propose to develop novel methods for detecting and tracking humans using 3D modelsfor body parts, and quasi-invariant recognition of activities humans are engaged in. We will make use of the recent advances made in the computational aspects of estimating posterior probability density functions usingMonte Carlo Markov Chain techniques to infer human descriptions and their activities.