Lane Boundaries Detection Algorithm based on Retinex with Line Segments Angles Computation

In unmanned vehicle systems, lane detection is important for road security improvement. This paper has developed an efficient lane detection system to deal with different types of lighting conditions. Line detection based on Hough Transform with Line Segments' Angles Computation is developed. Moreover, Retinex algorithm is employed to normalize input images for all types of illumination. Our proposed method can reduce computation time and detect left and right boundaries correctly through experiments.