| 摘要 |
A method for processing stereo rectified images, each stereo rectified image being associated with a camera position, the method including selecting a first pair of stereo rectified images; determining a first point cloud of features from the pair of stereo rectified images; determining the locations of the features of the first point cloud with respect to a reference feature in the first point cloud; selecting a second pair of stereo rectified images so that one stereo rectified image of the second pair is common to the first pair, and scaling a second point cloud of features associated with the second pair of stereo rectified images to the first point cloud of features. |
