期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2020
卷号：68
期号：4
页码：129-131
DOI：10.14445/22312803/IJCTT-V68I4P121
出版社：Seventh Sense Research Group
摘要：The world has moved further from the time when Benz first introduced the first production car to the whole world which at that time was not less than a miracle. As time passed, the cars have evolved but one thing remained the same, the need for a driver to drive the car around. Be it a luxury car, a wonderful speed car or a day to day commuter it could not be driven without a driver. Even in today’s world a car is just a marvel of modern mechanics sitting in your garage being useless without a driver and off course, be it any country you need a valid Driving License if you want to be eligible to drive a car according to the law and can’t be used in times of emergency if a trained and learned driver is not available. Selfdriving vehicles are cars or trucks in which human drivers are not required to take control to safely operate the vehicle. Also known as autonomous or “driverless” cars, they combine sensors and software to control, navigate, and drive the vehicle. Our goal is to make “Centaur” to be able to work on the principle of convolutional neural network which is in turn a class of deep neural network, also it uses Computer Vision which helps in object classification and lane detection, correction and lane change. It also uses a variety of sensors to collect data and improves drivability, all of which are powered by batteries. This paper deals with how it can be done and proposes a system for the same.
关键词：Convolutional Neural Network; Object Classifiers; Computer Vision; Sensors; Data Collection.
