A Novel PCA Perspective Mapping for Robust Lane Detection in Urban Streets

Lane detection has been an active research subject in recent years which has a wide range of applications in intelligent transportation systems. Various approaches have been proposed to solve this problem but most of them suffer from lack of robustness towards noise, illumination and occlusion. In this paper, we propose a novel lane detection method which consists of three major parts:(1) lane detection, (2) perspective mapping and (3) lane selection. In order to solve the perspective issue in the acquisition of input image, we introduce a novel method based on Principal Component Analysis (PCA). More over, we employ a rotated rectangle model which leads to more accurate lane detection. The proposed method is evaluated through five different scenarios namely, occlusion, illumination change, crowded scene, noncrowded scene and noisy image. Experimental results proved that our method is accurate and robust to aforementioned scenarios. A comparison between a respectable lane detection method and ours demonstrates that the proposed method has better accuracy and robustness.