Sawala Prateek, Puri Shalini; International Journal of Advance Research, Ideas and Innovations in Technology
© 2018, www.IJARIIT.com All Rights Reserved Page | 358
ISSN: 2454-132X
Impact factor: 4.295
(Volume 4, Issue 2)
Available online at: www.ijariit.com
Computer Vision in Self Driving Cars
Prateek Sawala
prateeksawala@gmail.com
Poornima College of Engineering, Jaipur,
Rajasthan
Shalini Puri
shalini.puri@poornima.org
Poornima College of Engineering, Jaipur,
Rajasthan
ABSTRACT
In this paper, the examination of the current state of the art in Computer vision with self driving cars has been discussed. The
main points which discussed here are the units of the self driving car, the core components of self-driving cars, Safety problems
of road vehicles are also presented. A Self Driving car is a vehicle that is capable of sensing its environment and able to do the
necessary navigation without the human input. The main idea which has been discussed here is General in-vehicle driver
support system architecture. To detect and track vehicles and other kinds of objects often with different sensors are used. Thus
giving humans the capability of using the self driving vehicle for daily usage will change the current scenario of transportation
and helps to improve the user driving experience.
Keywords: Computer Vision, LIDAR, Deep Neural Network.
1. INTRODUCTION
Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from
digital images or videos. In Computer Vision we try to teach a computer how to see and that seeing can refer to understanding
scenes, reconstructing 3D objects, recognizing objects, avoiding obstacles, helping blind people navigate and a lot of this makes use
of machine learning and it also makes use of geometry and applied math.
Fig 1: Computer Vision object Recognition System
Computer Vision can be seen to be used for various purposes such as - It helps stabilize videos and create virtual worlds. It helps
cameras see faces so they’re not blurry.
There a difference between human vision system and Computer vision system from a Computer perspective an image is just an
array of the number or if its color it would be three arrays of numbers. By themselves, these pixels don’t mean anything the computer
has to interpret what they are as shown in Fig 2.
In Fig 1.Computer vision object recognition System has been described in which an image is given as input and the task is to find
out where are all the object and what are they?