I-Corps: Advanced Driver Assistance Systems for use in Adverse Weather Operations

I-Corps项目更广泛的影响/商业潜力是恶劣天气下安全汽车运输的发展。这个项目是基于先进的计算机视觉算法的发展，在恶劣天气下提供更可靠的驾驶信息。这项技术商业化带来的车辆操作的改进可能会直接降低事故的数量。这项技术将降低保险成本和赔付，因为它将风险降到最低，提高了乘客的安全性。该项目的目标是将拟议的技术添加到当前的高级驾驶辅助系统（ADAS）功能中；也就是说，将新功能与其他汽车应用（如盲点监控、车道保持辅助和前方碰撞警告）结合起来。此外，这项技术可能有助于推进自动驾驶汽车的商业化。由于实施的灵活性，预计未来十年可能会对汽车运输业产生重大影响。I-Corps项目的基础是开发先进的计算机视觉算法，在恶劣天气下提供更可靠的驾驶信息。使用摄像头作为传感器输入，结合专有的计算机视觉算法，可以在积雪覆盖的道路上为高级驾驶员辅助系统（ADAS）提供可驾驶区域。提出的计算机视觉软件是在研究如何在恶劣天气条件下提高自动驾驶汽车性能的基础上开发的。这项研究支持专有图像处理、图像过滤和机器学习技术的发展。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is the development of safe automotive transportation in inclement weather. This project is based on the development of advanced computer vision algorithms that provide more reliable driving information in inclement weather. The improvements in vehicle operation from commercialization of this technology may directly lower the number of accidents. This technology will lower insurance costs and payouts as it minimizes risk and increases the safety of passengers. The goal of this project is to add the proposed technology to the current Advanced Driver Assistance Systems (ADAS) functionality; i.e., include the new abilities alongside other automotive applications such as blind spot monitoring, lane-keep assistance, and forward collision warnings. In addition, this technology may help to advance the commercialization of self-driving vehicles. Due to the flexibility of implementation, it is expected that there may be a significant impact on the automotive transportation community over the next decade.This I-Corps project is based on the development of advanced computer vision algorithms that provide more reliable driving information in inclement weather. Using a camera as the proposed sensor input, combined with proprietary computer vision algorithms, it is possible to provide the Advanced Driver Assistance Systems (ADAS) with a drivable region on snow-covered roads. The proposed computer vision software was developed from research conducted on how to improve autonomous vehicle performance in adverse weather conditions. This research supports the development of proprietary image processing, image filtering, and machine learning techniques.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.