Application of Color Filter Adjustment and K-Means Clustering Method in Lane Detection for Self-Driving Cars

摘要

The lane detection is a crucial key fact for advanced driving assistance systems. Hence, it is an active filed of research in recent years. The challenges to confront is to deal with various scenarios, such as when shadow interference or inconsistency of the road color and texture occur. This study propose to use a combination of color filters and a K-Means clustering filter to reduce the interfering noise. The result of our experiments show significant improvement in the noise robustness in lane detection.