Statistics show that around 1.3 million people are becoming victims of road accidents every year around the world; out of which, major causes are due to less visibility of the edges of the road during night times. This can be reduced by the implementation of any system that improves or gives a clear view of the edges of the road by any means of technology. The present system solves this problem partially by detecting the lanes in the road only during daytime. Driving vehicles during nighttime does not give much clarity on the road which sometimes causes the driver to run across the edges of the road or cause some catastrophic events. The road is not always visible at night, so driving in such conditions is not easy. This research suggests a lane detection system that uses computer vision techniques to help improve the safety of driving at night, specifically using the HSV and Temporal filtering technique for separating the lane color from the rest of the scene while the Adaptive Threshold, Canny edge detection algorithm for identifying edges within the lane. Moreover, the Hough Lines helps in identifying straight lines that correspond to lane markers, and the DBSCAN clustering technique groups these lines into continuous segments. In this research, the effectiveness of the proposed system is evaluated using real-world nighttime driving footage, showing its ability to accurately detect lane markings under difficult low-light conditions. By providing real-time feedback to the driver, this system has the potential to improve the safety of nighttime driving and prevent accidents caused by veering off the road.