An image-based parking guiding system is proposed to help drivers to park their cars into parking space. The proposed system only relies on an embedded hardware and a wide-angle camera to capture images for analysis. The proposed system needs no steering sensor; it is a money-saved technique; moreover, it is suitable for used cars and after-market usage. The input image is first transformed into a top-view image by a transformation matrix of homography. Then corner feature points on two continuous images are extracted to match each other. The feature-point pairs are further pruned by a least-square error metrics. The remained feature-point pairs are then used to estimate the vehicle motion parameters, where a coordinate transformation model is used to model and simulate the Ackermann steering geometry to describe the vehicle motion. At last, the vehicle trajectory is generated based on the vehicle motion parameters and the parking guiding lines are drawn according to the vehicle trajectory.