The invention discloses an intelligent vehicle map landmark positioning method integrating monocular vision and differential GNSS. The method comprises five steps including sensor synchronization, data preprocessing, landmark detection and landmark feature point extraction, landmark tracking and positioning, and landmark descriptor calculation. A sensor obtains space coordinates of a vehicle and acamera corresponding to an image synchronously; the image landmark is detected and landmark feature points are extracted by means of data processing; the image feature points are tracked by using anoptical flow method; and the feature points are extracted from the same landmark for tracking, and the position of the landmark is calculated by averaging. And after the landmark is successfully positioned, features are extracted from the finally detected landmark to describe the landmark in a unique way, and the position, type and feature description of the landmark are stored in a database.