Abstract
M.Ing. (Electrical and Electronic Engineering)
Adaptive Cruise Control (ACC) is proposed to assist drivers tedious manual acceleration
or braking of the vehicle, as well as with maintaining a safe headway time gap. This thesis
proposes, simulates, and implements a vision-based ACC system which uses a single
camera to obtain the clearance distance between the preceding vehicle and the ACC
vehicle. A three-step vehicle detection framework is used to obtain the position of the
lead vehicle in the image. The vehicle coordinates are used in conjunction with the lane
width at that point to estimate the longitudinal clearance range. A Kalman filter filters
this range signal and tracks the vehicle’s longitudinal position. Since image processing
algorithms are computationally intensive, this document addresses how adaptive image
cropping improves the update frequency of the vision-based range sensor. A basic model
of a vehicle is then derived for which a Proportional-Integral (PI) controller with gain
scheduling is used for ACC. A simulation of the system determines whether the ACC
algorithm will work on an actual vehicle.