NSF Award
2014933
The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to demonstrate the viability of a new camera solution for night or day and in adverse weather. Today's automatic driver assist systems are often inadequate for identifying pedestrians at night or in poor conditions. This project will demonstrate a camera solution that will operate day and night, in all weather, and detects and classifies pedestrians, cyclists, animals as well as vehicles (either moving or stationary), thereby unlocking safer vehicle operation and saving lives.<br/><br/>This Small Business Innovation Research (SBIR) Phase I project addresses a shortcoming of contemporary autonomous vehicle sensors by introducing a high-resolution 3D sensor that performs well in any lighting condition and most weather conditions. The research builds upon light field, or plenoptic, technologies proven effective in the visible domain and applies them to the thermal domain with additional innovations. A purpose-built microlens array (MLA) is coupled with a mid-wave infrared (MWIR) camera and new thermal computational photogrammetry algorithms to deliver dense 2D and range information with sufficient detail to quickly classify surrounding objects. In particular, it will be shown that 3D MWIR video is ideally suited to readily detect and classify objects that may move such as pedestrians, vehicles and animals.<br/><br/>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.
