An affine invariant interest point detector
An affine invariant interest point detector
复制标题
DOI：
10.1007/3-540-47969-4_9
复制
发表时间：
2002-01-01
期刊：
影响因子：
--
通讯作者：
Schmid, C
中科院分区：
文献类型：
--
作者：
Mikolajczyk, K;Schmid, C
本文提出了一种用于检测仿射不变兴趣点的新方法。我们的方法可以处理包括大规模变化在内的重大仿射转变。这种转变引入了点位置以及兴趣点附近的尺度和形状的重大变化。我们的方法允许同时解决这些问题。它基于三个关键思想：1）在一个点计算的第二刻矩阵可以用来以仿射不变的方式（偏斜和拉伸）来归一化区域。 2）局部结构的尺度由标准化衍生物的局部极值表明。 3）仿射适应的哈里斯探测器确定了兴趣点的位置。该检测器的多尺度版本用于初始化。然后，迭代算法会修改每个点的位置，比例和邻域，并收敛到仿射不变点。为了进行匹配和识别，图像的特征是一组仿射不变点。与每个点相关的仿射转换允许计算仿射不变的描述符，该描述符也是仿射照明变化的不变。我们的检测器与现有检测器的定量比较显示出大片映射的存在显着改善。宽基线匹配的实验结果表明，在存在较大的透视转换（包括重大尺度变化）的情况下，表现出色。识别结果非常适合拥有5000多个图像的数据库。
This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighbourhood of an interest point. Our approach allows to solve for these problems simultaneously. It is based on three key ideas: 1) The second moment matrix computed in a point can be used to normalize a region in an affine invariant way (skew and stretch). 2) The scale of the local structure is indicated by local extrema of normalized derivatives over scale. 3) An affine-adapted Harris detector determines the location of interest points. A multi-scale version of this detector is used for initialization. An iterative algorithm then modifies location, scale and neighbourhood of each point and converges to affine invariant points. For matching and recognition, the image is characterized by a set of affine invariant points; the affine transformation associated with each point allows the computation of an affine invariant descriptor which is also invariant to affine illumination changes. A quantitative comparison of our detector with existing ones shows a significant improvement in the presence of large affine deformations. Experimental results for wide baseline matching show an excellent performance in the presence of large perspective transformations including significant scale changes. Results for recognition are very good for a database with more than 5000 images.