SI2-SSE: Analyze Visual Data from Worldwide Network Cameras

许多网络摄像机被用于各种用途，如监控交通、评估空气污染、观察野生动物和观察地标。这些相机的数据可以提供有关自然环境和人类活动的丰富信息。为了从摄像机网络中提取有价值的信息，需要复杂的计算机程序从地理分布的摄像机中检索数据并分析数据。该项目通过解决许多不同类型的分析程序的共同问题，创建了一个开源软件基础结构。通过使用这种基础设施，研究人员可以专注于科学发现，而不是编写计算机程序。该方案可以提高效率，从而降低运行分析大量数据的程序的成本。这种基础设施促进了教育，因为学生可以获得网络摄像机的即时视图，并使用视觉信息来了解世界。更好地了解世界可能会鼓励对许多紧迫问题的创新解决方案，例如更好的城市规划和更低的空气污染。该项目可以通过多个已建立的项目来增强多样性，鼓励未被充分代表的少数民族从事科学和工程方面的职业。该项目将结合：(1)从许多异构和分布式摄像机中检索数据的能力，(2)使用云计算管理计算和存储资源，以及(3)通过减少数据移动、平衡多个云实例之间的负载和增强数据级并行性来提高性能。该项目提供了一个应用程序编程接口（API），该接口隐藏了底层复杂的基础结构。该基础设施将以统一的方式处理实时流数据和归档数据，以便可以重用相同的分析程序。该项目有四个主要组成部分：(1)基于web的用户界面，(2)存储网络摄像机详细信息的数据库，(3)分配云实例的资源管理器，以及(4)执行用户编写的程序的计算引擎。面向服务的体系结构将允许研究团体更容易地集成新功能。

Many network cameras have been deployed for a wide range of purposes, such as monitoring traffic, evaluating air pollution, observing wildlife, and watching landmarks. The data from these cameras can provide rich information about the natural environment and human activities. To extract valuable information from this network of cameras, complex computer programs are needed to retrieve data from the geographically distributed cameras and to analyze the data. This project creates a open source software infrastructure by solving many problems common to different types of analysis programs. By using this infrastructure, researchers can focus on scientific discovery, not writing computer programs. This project can improve efficiency and thus reduce the cost for running programs analyzing large amounts of data. This infrastructure promotes education because students can obtain an instantaneous view of the network cameras and use the visual information to understand the world. Better understanding of the world may encourage innovative solutions for many pressing issues, such as better urban planning and lower air pollution. This project can enhance diversity through multiple established programs that encourage underrepresented minorities to pursue careers in science and engineering. This project will combine: (1) the ability to retrieve data from many heterogeneous and distributed cameras, (2) the management of computational and storage resources using cloud computing, and (3) improved performance by reducing data movement, balancing loads among multiple cloud instances, and enhancing data-level parallelism. The project provides an application programming interface (API) that hides the underlying sophisticated infrastructure. This infrastructure will handle both real-time streaming data and archival data in a uniform way, so that the same analysis programs can be reused. This project has four major components: (1) a web-based user interface, (2) a database that stores the details about the network cameras, (3) a resource manager that allocates cloud instances, and (4) a computational engine that execute the programs written by users. The service-oriented architecture will allow new functions to be integrated more easily by the research community.