Distinctive Image Features from Scale-Invariant Keypoints-英文文献.pdf

Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe Computer Science Department University of British Columbia Vancouver, B.C., Canada Draft: Submitted for publication. This version: June 6, 2003 Abstract This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different im- ages of an object or scene. The features are invariant to image scale and ro- tation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single fea- ture can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least- squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance. 1 1 Introduction Image matching is a fundamental aspect of many problems in computer vision, including object recognition, solving for 3D structure from multiple images, stereo matching, and motion tracking and segmentation. This paper describes image features that have many properties that make them suitable for matching differing images of