A novel video-based application for road markings detection and recognition

Advanced Driving Assistant System (ADAS) was widely learned nowadays. As crucial parts of ADAS, video-based application like lane markings detection and other objects detection, have become more popular than before. However, most methods implemented in such areas cannot perfectly balance the performance of accuracy versus efficiency, and the mainstream methods (e.g. Machine Learning) suffer several limitations which can hardly break the wall between partial automation and fully automation. This paper proposed a real-time lane marking detection framework for ADAS, which included 4-extreme points set descriptor and a rule-based cascade classifier. Several experiments were conducted in highway and urban roads in Ottawa. The detection rate of the markings by the proposed algorithm reached an average accuracy rate of 96.77% while F
₁
Score (harmonic mean of precision and recall) also attained a rate of 90.57%. In summary, the proposed method exhibited a state-of-the-art performance and represents a significant advancement of understanding.