Non-line-of-sight Imaging for Advanced Automotive Sensing

用于先进汽车传感的非视距成像

• 批准号: 540138-2019
• 负责人: Leonelli, Richard
• 金额: $ 1.82万
• 依托单位: Université de Montréal
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=680957
• 关键词: Non; line; sight; Imaging; Advanced

The capacity of imaging systems must continue to expand to keep pace with rapidly emerging technologies. Imaging objects obscured by occluders poses a significant challenge for many applications. A camera that could "see around corners" could help improve navigation and mapping capabilities of autonomous vehicles, allowing vehicles to detect what lies beyond the next bend or another car. Sensing technology offering such non-line-of-sight (NLOS) capabilities could help make self-driving cars safer and unlock unprecedented potential for other machine vision systems.Through this new collaboration between the Université de Montréal and Algolux Inc., we would like to gain insights into the feasibility of a system that allows for high-resolution NLOS imaging. The goal of the collaboration is to demonstrate a prototype system that validates our concepts and achieves an order of magnitude higher resolution for NLOS imaging than today's methods.

成像系统的能力必须继续扩大，以跟上迅速出现的技术。对被遮挡物遮挡的物体进行成像对于许多应用来说是一个重大挑战。一个可以“看到周围角落”的摄像头可以帮助提高自动驾驶汽车的导航和地图绘制能力，使汽车能够检测到下一个弯曲或另一辆汽车之外的东西。提供这种非视距（NLOS）功能的传感技术可以帮助使自动驾驶汽车更安全，并为其他机器视觉系统释放前所未有的潜力。通过蒙特利尔大学和Algolux Inc.之间的这项新合作，我们希望深入了解允许高分辨率NLOS成像的系统的可行性。合作的目标是展示一个原型系统，验证我们的概念，并实现一个数量级更高的分辨率NLOS成像比今天的方法。