Application of Image Processing Techniques for Autonomous Cars

Abstract

This paper aims to implement different image processing techniques that will help to control an autonomous car. A multistage pre-processing technique is used to detect the lanes, street signs, and obstacles accurately. The images captured from the autonomous car are processed by the proposed system which is used to control the autonomous vehicle. Canny edge detection was applied to the captured image for detecting the edges, Also, Hough transform was used to detect and mark the lanes immediately to the left and right of the car. This work attempts to highlight the importance of autonomous cars which drastically increase road safety and improve the efficiency of driving compared to human drivers. The performance of the proposed system is observed by the implementation of the autonomous car that is able to detect and classify the stop signs and other vehicles.