In view of the imaging mechanism differences between the laser point cloud and image data, as well as existing registration primitives accessibility features, the registration based on features is the mainstream algorithm to refine the transformation of the two data sets. The corner points and edges of buildings are frequently used as characteristics. In order to deal with the weakness of building edge detection and reduce matching- related computation, a new automatic registration method based on airborne LiDAR data and high-resolution aerial image of the road information is proposed. Vector road centerlines are extracted from raw LiDAR data and projected onto related aerial images with the use of coarse exterior orientation parameters (EOPs). The corresponding image road features of each LiDAR vector road are determined with the improved total rectangle matching approach. The endpoints of the conjugate road features obtained from the LiDAR data and aerial images are used as ground control points in space resection adjustment to refine the EOPs. Experimental results show that this method characterized by the road features can not only extract fewer features, but also improve the efficiency of data processing in autoregistration of aerial imagery with airborne LiDAR data.