The goal of this project is a new cost-effective architecture for machine vision, which will be evaluated for intelligent highway applications. Components of three smart image sensors are being developed and integrated into a heterogeneous vision system. The smart sensors use analog, digital, and mixed signal techniques to perform 3 dimensional measurement for adaptive cruise control, lane detection, and time-to-collision measurements. All of these tasks are intended for machine vision systems within intelligent vehicles, and will be tested in intelligent vehicle applications within the later stages of the award. MIT is performing basic research on the first versions of all of these cameras, while later development, integration, and testing will be carried out by industrial partners.
