ASIFT: A New Framework for Fully Affine Invariant Image Comparison
ASIFT: A New Framework for Fully Affine Invariant Image Comparison
复制标题
DOI：
10.1137/080732730
复制
发表时间：
2009-01-01
影响因子：
2.1
通讯作者：
Yu, Guoshen
中科院分区：
文献类型：
--
作者：
Morel, Jean-Michel;Yu, Guoshen
如果物理对象具有光滑或分段的光滑边界，则其图像是通过摄像机处于不同位置的相机获得的图像，会经历光滑的明显变形。这些变形在图像平面的仿射变换上局部近似。因此，实心对象识别问题通常已导致仿射不变图像本地特征的计算。这种不变的特征可以通过归一化方法获得，但是目前尚无完全贴发的归一化方法。即使比例不变性也仅通过比例不变特征变换（SIFT）方法来严格处理。通过模拟缩放并标准化翻译和旋转，SIFT是仿射变换的六个参数中的四个不变的。本文提出的方法（ASIFT）（ASIFT）模拟了所有图像视图，可以通过改变两个相机轴方向参数，即通过SIFT方法剩下的纬度和经度角度来获得的所有图像视图。然后，它使用SIFT方法本身涵盖了其他四个参数。在数学上将被证明是完全仿射的不变性。在任何预后，根据两个摄像机方向参数模拟所有观点是可行的，没有显着的计算负载。两分辨率方案进一步将ASIFT复杂性降低到筛分的两倍。引入了一个新的概念，即过渡倾斜，测量了从一种视图到另一种视图的失真量。虽然从额叶到倾斜的观点的绝对倾斜度极为罕见，但是当比较两个物体的两个倾斜视图时，较高的过渡倾斜很常见（见图1）。针对每种仿射图像比较方法测量可实现的过渡倾斜。该新方法允许人们可靠地识别经过大量过渡倾斜的特征，最多36岁以上。许多实验证实了这一事实，这些实验表明，ASIFT明显胜过最先进的方法，最大稳定的极端区域（MSER），Harris-Affine和Hessian-frace。
If a physical object has a smooth or piecewise smooth boundary, its images obtained by cameras in varying positions undergo smooth apparent deformations. These deformations are locally well approximated by affine transforms of the image plane. In consequence the solid object recognition problem has often been led back to the computation of affine invariant image local features. Such invariant features could be obtained by normalization methods, but no fully affine normalization method exists for the time being. Even scale invariance is dealt with rigorously only by the scale-invariant feature transform (SIFT) method. By simulating zooms out and normalizing translation and rotation, SIFT is invariant to four out of the six parameters of an affine transform. The method proposed in this paper, affine-SIFT (ASIFT), simulates all image views obtainable by varying the two camera axis orientation parameters, namely, the latitude and the longitude angles, left over by the SIFT method. Then it covers the other four parameters by using the SIFT method itself. The resulting method will be mathematically proved to be fully affine invariant. Against any prognosis, simulating all views depending on the two camera orientation parameters is feasible with no dramatic computational load. A two-resolution scheme further reduces the ASIFT complexity to about twice that of SIFT. A new notion, the transition tilt, measuring the amount of distortion from one view to another, is introduced. While an absolute tilt from a frontal to a slanted view exceeding 6 is rare, much higher transition tilts are common when two slanted views of an object are compared (see Figure 1). The attainable transition tilt is measured for each affine image comparison method. The new method permits one to reliably identify features that have undergone transition tilts of large magnitude, up to 36 and higher. This fact is substantiated by many experiments which show that ASIFT significantly outperforms the state-of-the-art methods SIFT, maximally stable extremal region (MSER), Harris-affine, and Hessian-affine.