Distributed Camera Systems and Image Sensor Clouds

想象一下，在一个足球场里，每个人都在用他们的手机捕捉比赛的视频。不同的观众跟随不同的球员，有些人跟着球，其他人可能会打开或关闭他们的相机，许多人在看台上走动。如果我们能够在真实的时间里访问这些视频，我们如何检索有关游戏的信息？一方面，我们将从多个角度了解球场的所有部分，没有任何事件会被记录下来。另一方面，我们不知道摄像机在任何时候都在哪里，它们指向哪个方向，甚至有多少。也会有巨大的冗余（这意味着场景中的一个点被许多摄像机捕获），摄像机之间的视场重叠程度不同，相同的物体在不同图像中以不同尺寸出现的情况，以及许多类似的挑战。 该提案的长期目标是关注传感器云的构建和使用，足球场的插图就是一个例子。我们将考虑这些模块的技术，特别是图像传感器本身，以及网络操作和优化技术。控制和使用大型随机相机网络的一个可能的解决方案是采用“元相机”，即虚拟数据集合，其作用类似于真实的相机，但可以根据简单的基于图像的规则在必要时创建和销毁。 这项工作的较短期目标与上述目标相同（即，传感器技术和系统操作），但是应用于目前正在研究和开发的分布式相机系统。一个具体的应用是光学飞机防撞系统，使用多个相机的分布式控制的基础上的模型的生物集体，如蚂蚁觅食。

Imagine a soccer stadium in which every person in the capacity crowd is using their cell-phone to capture a video of the game. Different spectators follow different players, some follow the ball instead, others may turn their cameras on or off, and many move about the stands. If we were to have access to these videos in real time, how could we retrieve information about the game? On one hand, we would have information about all parts of the pitch from multiple perspectives and no event would go unrecorded. On the other hand, we do not know where the cameras are at any time, in which directions they point, or even how many there are. There would also be huge redundancy (meaning that a point in the scene is captured by many cameras), variable degrees of overlap in fields-of-view between cameras, instances where identical objects appear at different sizes in different images, and a host of similar challenges. The long-term objective of this proposal is concerned with the construction and use of sensor clouds, of which the soccer stadium illustration is an example. We will consider both the technology of these modules, particularly the image sensor itself, and techniques for network operation and optimization. One possible solution to controlling and using large, random camera networks is to employ 'metacameras,' virtual collections of data that act like a real camera but which can be created and destroyed as necessary, according to simple image-based rules. Shorter-term objectives of this work mirror those above (viz., sensor technology and system operation) but with application to distributed camera systems that are under research and development today. A particular application is to an optical aircraft collision avoidance system using multiple cameras with distributed control based on models of biological collectives, such as ant foraging.