Design and development of vehicle collision avoidance system
Zin Maung, Maung Lwin
Date of Issue2017-11-30
School of Electrical and Electronic Engineering
Automotive safety has gained an increasing amount of interest from the general public, governments and the car industry. This is more than justified by traffic accident statistics, as each year around 1.2 million people die due to road traffic accidents. Many automobile manufacturers are harnessing innovative technologies to help alert drivers to avoid collisions and reduce the potential impact speed when a collision cannot be avoided. Most of the current collision warning systems are mainly designed to detect imminent rear-end, lane-changing or lane departure collisions and forward collisions. A main source for human errors is the insensitivity of human vision system to detect the speed and acceleration of approaching vehicles; and therefore, any algorithm for a collision warning system should give consideration to the speed and acceleration of all approaching vehicles to mitigate the insufficiency in the human vision system. Moreover, when designing any collision warning system, false warnings should be minimized to avoid nuisance for drivers that might lead to the loss of the system’s reliability by potential users. This research proposes a collision warning system including automatic parallel parking, lane departure warning and forward collision warning systems that utilizes commercially-available detection cameras to detect approaching vehicles and measure their distances in order to estimate the time-to-collision. We apply some new method combined with fuzzy logic, object detection and tracking method using single camera for constructing system. Simulation results are shown and all the codes is written in MATLAB.
Final Year Project (FYP)
Nanyang Technological University