SBIR Phase I: Computational Pipeline and Architecture for Personalized Displays

SBIR 第一阶段：个性化显示的计算管道和架构

• 批准号: 1548976
• 负责人: Paul Dietz
• 金额: $ 15万
• 依托单位: Misapplied Sciences, Inc.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-01-01 至 2016-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1548976&HistoricalAwards=false
• 关键词: SBIR; Phase; Computational; Pipeline; Architecture

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is in improving the performance of the back-end of a display system that delivers personalized information in public spaces. Currently, the primary method for an individual to receive customized information in public spaces is through personal devices. The heavy use of personal devices in public often leads to heads-down, isolating, and even hazardous situations. The delivery of personalized information through infrastructure can significantly improve these issues. However, the bandwidth requirements in doing so have been prohibitively high using standard computational architectures. This project aims to improve the performance of such a system, allowing practical applications that will broadly enhance safety, accessibility, transportation, and other areas.This Small Business Innovation Research (SBIR) Phase I project focuses on creating a scalable computational pipeline and architecture that will allow a display system to direct personalized visual information in real-time to large numbers of people. Technically, this involves computing, transmitting, and displaying image data for large crowds in parallel. The architecture takes advantage of the inherent redundancies in this application to provide a cost-effective solution. The goal of the project is to create a computational back-end capable of driving, in real-time, a system equivalent to thousands of displays.

该小型企业创新研究 (SBIR) 第一阶段项目的更广泛影响/商业潜力在于提高在公共空间提供个性化信息的显示系统后端的性能。 目前，个人在公共场所接收定制信息的主要方法是通过个人设备。 在公共场合大量使用个人设备常常会导致低头、孤立甚至危险的情况。 通过基础设施提供个性化信息可以显着改善这些问题。 然而，使用标准计算架构时，这样做的带宽要求非常高。 该项目旨在提高此类系统的性能，从而实现广泛增强安全性、可达性、交通和其他领域的实际应用。该小型企业创新研究（SBIR）第一阶段项目的重点是创建可扩展的计算管道和架构，使显示系统能够将个性化视觉信息实时引导给大量人员。 从技术上讲，这涉及并行计算、传输和显示大量人群的图像数据。 该架构利用该应用中固有的冗余来提供经济高效的解决方案。该项目的目标是创建一个能够实时驱动相当于数千个显示器的系统的计算后端。