In order to reduce the effects caused by complex environments and ambient light conditions, a fast, robust and effective obstacles detection method of vehicles based on image analysis of multi-feature is proposed. Firstly, regions of interest (ROI) which contain lanes, vehicles and few parts of interference background are extracted in the input image by detecting gradient feature in rows. Secondly, color segmentation is tackled in YCrCb image to reduce illumination effect. Then, lanes are detected in segmented image by Line Segment Detector (LSD) to obtain the accurate detected regions of obstacles. At last, Obstacles are detected based on an adaptive threshold. The experiment proves that the proposed method can detect obstacles with small calculating amount, high accuracy and robustness. It is suitable in practical engineering.