The number of road accidents in the world is increasing every year due to driver negligence. Unintended lane departure and rear end collisions are some of the main reason behind road accidents in the freeway. This project presents an efficient, robust Lane Departure Warning System (LDWS) and a frontal collision warning system, which work on different illumination conditions. The system uses a monoscopic dashboard camera fitted in the windshield of the car. The algorithm makes a birds-eye view (top-view) of the road using Inverse Perspective Mapping. Hough transform is applied on this IPM to find the candidate points of lanes, and finally RANSAC Bezier spline fitting is done to find out the actual lanes. To detect vehicles, Hough transform is applied on the image to check for horizontal lines made by the vehicle. Multithreding is done to improve the performance of the system and to utilize maximum system resources. © 2017 IEEE.
cited By 0; Conference of 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2017 ; Conference Date: 6 July 2017 Through 7 July 2017; Conference Code:136091
A. V. Vinuchandran and Shanmughasundaram, R., “A real-time lane departure warning and vehicle detection system using monoscopic camera”, in 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2017, 2018, vol. 2018-January, pp. 1565-1569.