1(Engg.) Student, M. S. Ramaiah School of Advanced Studies, Bangalore
2Professor and Centre Manager (CSN), M. S. Ramaiah School of Advanced Studies, Bangalore
3Assistant Professor and Centre Manager (AML), M. S. Ramaiah School of Advanced Studies, Bangalore
Online published on 18 February, 2020.
This paper describes a novel Driver Assistant System based on real-time video to track lanes and road signs with minimal hardware and software requirements. The proposed system was designed to use low cost cameras and processing power of an on-board commodity laptop.
The system model was developed using MATLAB®/Simulink blocksets. This was later converted into an optimized compiled code using the built-in code generation features for the Pentium and AMD processors. The lane tracking algorithm based on Hough Transform was implemented as embedded MATLAB® code. The signboards were detected by Blob Analysis Based Template Matching. Sum of Absolute Differences (SAD) as well as Scale Invariant Feature Transform (SIFT) followed by RANdom SAmple Consensus (RANSAC) based template matching methods. The above were implemented and compared for their performance.
The developed system was tested on different drives varying from a high speed drive on a high way to a low speed drive on the city roads. The system was able to detect the lane markings under various lighting conditions and on many types of roads ranging from unmarked roads to multi-lane national highways. The road sign detection system was able to detect signboards as long as the background was not very cluttered. The implemented system has an overall success rate of over 97% for lane detection and more than 70% for the road sign detection.
Driver Assist System, Lane Detection, Lane Tracking, Signboard Detection, Hough Transform, SIFT, RANSAC, Video Processing, DAS, Simulink
