Distinctive image features from scale-invariant keypoints
Distinctive image features from scale-invariant keypoints
复制标题
DOI：
10.1023/b:visi.0000029664.99615.94
复制
发表时间：
2004-11-01
影响因子：
19.5
通讯作者：
Lowe, DG
中科院分区：
文献类型：
--
作者：
Lowe, DG
本文提出了一种从图像中提取独特的不变特征的方法，这些特征可用于在对象或场景的不同视图之间执行可靠的匹配。的功能是不变的图像的比例和旋转，并提供强大的匹配在相当大的范围内的仿射失真，在3D视点的变化，除了噪声，和照明的变化。这些特征是高度独特的，在这个意义上，单个特征可以以高概率与来自许多图像的大型特征数据库正确匹配。本文还介绍了一种方法，使用这些功能的对象识别。识别过程中，通过匹配单个功能的数据库的功能，从已知的对象使用快速最近邻算法，然后由霍夫变换，以确定集群属于一个单一的对象，最后执行验证，通过最小二乘解决方案的一致的姿态参数。这种识别方法可以鲁棒地识别杂乱和遮挡中的对象，同时实现接近实时的性能。
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature 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.