Visual contextualization and activity monitoring for networked telepresence

Visual contextualization and activity monitoring for networked telepresence
复制标题

网络远程呈现的视觉情境化和活动监控

DOI:
10.1145/1026776.1026785
复制
发表时间:
2004
期刊:
Problems of Economic Transition
影响因子:
--
通讯作者:
M. Trivedi
M. Trivedi
中科院分区:
--
文献类型:
--
作者:
Douglas A. Fidaleo;R. Schumacher;M. Trivedi

文献摘要

被引文献

相似文献

过去、现在和未来事件以及事件周围环境之间复杂的相互关系否定了环境的背景。虽然现在提供了对我们周围环境的当前和即时解释,并能够立即做出决策,但历史数据可以对事件进行事后分析,并预示未来事件,从而影响当前决策所依赖的背景。因此,实现情境感知需要从不同的时间和空间情境中提取、捕获和解释多种模式的信息。这些数据的情境化涉及将信息嵌入到一个熟悉的虚拟环境中,以帮助操作员理解收集到的大量感官数据。本文详细介绍了我们正在开发的原型系统,以促进未来的情境意识研究,并支持、整合和增强我们实验室开发的现有情境重点研究。描述了该系统的核心模块,包括用于传感器集成、处理以及上下文归档和查询的网络传感器挂毯 (NeST) 架构,重点是上下文可视化环境 (CoVE):用于多模态传感器数据视觉融合的 3D 环境。提出了几个构建在这些组件之上的实际应用程序。
The context of an environment is denied by a complex interrelationship between past, present, and future events and of the events' surroundings. While the present provides a current and immediate interpretation of our surroundings and enables immediate decisions, historical data enables post-mortem analysis of an incident as well as a foreshadowing of future events that can in turn afect the context upon which current decisions depend. Achieving context awareness therefore requires extraction, capture, and interpretation of multiple modes of information from different temporal and spatial contexts. Contextualization of this data involves embedding the information into a single familiar virtual environment to assist a human operator in making sense of the volumes of collected sensory data. This paper details a prototype system we are developing to facilitate future context awareness research as well as support, integrate, and augment existing context focused research developed in our laboratory. The core modules of the system are described including the Networked Sensor Tapestry (NeST) architecture for sensor integration, processing, and context archiving and querying with a focus on the Context Visualization Environment (CoVE): a 3D environment for visual fusion of multimodal sensor data. Several real-world applications are presented that are built on top of these components.