SIRG: "Being There": User-centric Wireless Image-based Sensor Networks

该传感器方案侧重于解决图像传感器的大规模无线网络的限制，即传感器功率和网络带宽的限制以及人类在吸收和整合大量图像数据的能力方面的限制。理想的系统为用户提供了来自多个成像器的综合视图，提供了一种身临其境的感觉，能够在空间中导航，同时允许网络在无人值守的情况下长时间运行。实现这些目标需要跨层设计，涵盖从应用程序到硬件的所有级别。智能优点：我们建议开发自适应的低功率成像器、分布式图像融合算法和总体传感器管理协议。成像器将能够以自适应的分辨率捕捉场景，无论是在空间上还是在图像位深度方面，并以现有系统所需功率的一小部分进行压缩。为了以更完整的方式将图像数据呈现给用户，我们将开发图像马赛克算法，该算法适用于未校准的相机和非平面场景。最后，我们将开发智能传感器管理技术，使用应用层信息来适当配置传感器和网络本身。广泛的影响：(1)提供身临其境的体验将对从监视到远程呈现的基于距离的观看应用产生深远的影响。(2)PIS致力于培训学生，并将这项研究与他们的教学相结合。(3)这项研究的跨学科性质和可能产生的高度社会影响有望吸引来自代表性不足群体的学生。(4)PIS将开发传感器网络教程，并将其与基于图像的传感器网络演示相结合，以激发社区对这一令人兴奋的研究领域的兴趣。

This Sensor proposal focuses on addressing the limitations of large scale wireless networks ofimaging sensors, namely limitations of sensor power and network bandwidth and human limitationsin the capability to absorb and integrate large amounts of image data. The ideal system providesthe user with an integrated view from the multiple imagers, providing the feeling of being therealong with the capability to navigate the space while allowing the network to run unattended forlong periods of time. Achieving these goals requires a cross-layer design that encompasses all levelsfrom the application to the hardware.Intellectual Merit: We propose developing adaptable low power imagers, distributed imagefusion algorithms, and an overarching sensor management protocol. The imagers will be able tocapture scenes with adaptable resolution, both spatially and in terms of image bit-depth, andperform compression for a fraction of the power required by existing systems. To present theimage data to the user in a more integrated fashion, we will develop image mosaicking algorithmsthat work with uncalibrated cameras and non-planar scenes. Finally, we will develop intelligentsensor management techniques that use application-level information to appropriately configure thesensors and the network itself.Broader Impacts: (1) Providing a being there experience will have a profound impact ondistance-based viewing applications, from surveillance to tele-presence. (2) The PIs are committedto training students and will integrate this research with their teaching. (3) The cross-disciplinarynature of this research and the potential for high societal impact will hopefully attract studentsfrom under-represented groups. (4) The PIs will develop a sensor network tutorial and use thiswith the demonstration image-based sensor network to spark the interest of the community in thisexciting field of study.