Dimensionality of illumination in appearance matching
Dimensionality of illumination in appearance matching
复制标题
外观匹配中的光照维度
DOI：
10.1109/robot.1996.506890
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
H. Murase
中科院分区：
文献类型：
--
作者：
S. Nayar;H. Murase
外观匹配最近被证明是用于3D对象识别和姿势估计的强大而有效的方法。每个对象在通过对象姿势和照明方向参数参数的低维子空间中表示为连续的外观歧管。在这里，分析了外观歧管的结构属性，目的是使外观表示有效地在离线计算，存储要求和在线识别时间方面有效。特别是，研究了照明对外观歧管结构的影响。结果表明，对于任意纹理的理想扩散表面，外观歧管是线性和三维的。这样可以从仅使用线性独立光源拍摄的对象的三张图像中构造整个照明歧管。该结果表明，该结果甚至可以通过多个光源和表现出反射间的凹面表面照明。最后，提出了一种简单但有效的算法，该算法仅使用三个多方点来识别在新颖的照明下拍摄的图像。
Appearance matching was recently demonstrated as a robust and efficient approach to 3D object recognition and pose estimation. Each object is represented as a continuous appearance manifold in a low-dimensional subspace parametrized by object pose and illumination direction. Here, the structural properties of appearance manifolds are analyzed with the aim of making appearance representation efficient in off-line computation, storage requirements, and online recognition time. In particular, the effect of illumination on the structure of the appearance manifold is studied. It is shown that for an ideal diffused surface of arbitrary texture, the appearance manifold is linear and three dimensional. This enables the construction of the entire illumination manifold from just three images of the object taken using linearly independent light sources. This result is shown to hold even for illumination by multiple light sources and for concave surfaces that exhibit inter-reflections. Finally, a simple but efficient algorithm is presented that uses just three manifold points for recognizing images taken under novel illuminations.