I-Corps: On-line image analysis and dynamic mission planning for unmanned aerial vehicles

这个i-Corps项目探索了新的图像分析和特征检测算法以及动态路径规划算法的商业适用性。这一i-Corps项目的更广泛的影响/商业潜力包括创建一种利用无人驾驶航空系统监测农业和自然景观的软件产品并将其商业化。这种先进技术商业化的好处预计将包括提高主要粮食作物的盈利能力和生产率，增加粮食安全，并使国家的农业和自然资源能够长期可持续发展。拟议的客户互动努力还将提高美国农业和自然资源管理部门利益相关者的技术能力，因为它们将涉及具有科学和技术专业知识的提议团队与目标客户细分市场中具有必要实地经验的利益相关者之间的密集互动。这个I-Corps项目的图像分析和特征检测算法以及动态路径规划算法已经开发，用于使用移动处理器快速和计算高效地检测视觉光谱图像中的异常区域。动态路径规划算法能够基于对来自无人机传感器的输入数据的分析，自动修改无人机飞行计划。这些算法结合在一起，能够自主捕获高价值信息，并立即从无人机任务中提供可操作的见解。与现有的基于无人机的监控商业产品相比，这项技术将是一个重大改进。现有的无人机监控产品涉及高劳动力和设备成本，需要云连接才能进行数据分析，而且难以使用和理解。相比之下，这里将研究的全新工作流程范例和创新技术进步将使人们能够使用消费级无人机和视觉光谱相机，快速提供有关远程环境中潜在问题的可行见解。

This I-Corps project explores the commercial applicability of novel image analysis and feature detection algorithms and dynamic path planning algorithms. The broader impact/commercial potential of this I-Corps project include creation and commercialization of a software product for monitoring agricultural and natural landscapes using unmanned aerial systems. The benefits of commercialization of this advanced technology are expected to include improvement in the profitability and productivity of major food crops, increase in food security, and enable long-term sustainability of the nation's agronomic and natural resources. The proposed customer-interaction efforts will also lead to increased technical capacity among stakeholders in US agriculture and natural resource management sectors as they will involve intensive interaction between the proposing team with scientific and technical expertise, and the stakeholders in the target customer segments who have the necessary on-the-ground experience.This I-Corps project's image analysis and feature detection algorithms and dynamic path planning algorithms have been developed for rapid and computationally efficient detection of anomalous areas in visual spectrum images using mobile processors. The dynamic path planning algorithms enable automatic mid-flight modification of drone flight plans based on analysis of incoming data from drone-based sensors. Together these algorithms enable autonomous capture of high-value information and immediate delivery of actionable insights from drone missions. This technology will be a significant improvement on existing commercial offerings for drone-based monitoring, which involve high labor and equipment costs, require cloud-connectivity for data analysis, and are difficult to use and understand. By contrast, the fundamentally new workflow paradigms and innovative technical advances that will be examined here will enable rapid delivery of actionable insights about potential problems in remote environments using consumer level drones and visual spectrum cameras.