Multi-Resolution Spin-Images

Abstract

Johnson and Hebert's spin-images have been applied to the registration of range images and object recognition with much success because they are rotation, scale, and pose invariant. In this paper we address two issues concerning spin-images, namely: (1) comparing uncompressed spinimages across large datasets is costly, and (2) a method to select the appropriate bin size and image width for spinimages is not clearly defined.Our solution to these issues is a multi-resolution method that generates a pyramid of spin-images by successively decreasing the spin-image size by powers of two. To efficiently correlate surface points, we compare spin-images in a low-to-high resolution manner. Once multi-resolution spin-images are generated for a given object, we have found that the different resolutions can also be used to compare objects that have differing or non-uniform point densities. To select the appropriate bin sizes for comparing such objects, we use the ratio of the average edge lengths of the objects. We also show preliminary results of using the pyramid to converge on the appropriate image width by traversing the pyramid in a low-to-high resolution manner looking for the highest resolution at which the fewest number of highly correlated points are found to match a given feature point.

An efficient registration algorithm based on spin image for LiDAR 3D point cloud models

“…1) the computational burden is decreased greatly compared to that of classical spin image based registration method and the multiple resolution method in reference [17]. This can be obtained through experiment 1.…”

“…This can be obtained through experiment 1. 2) the robustness and the accuracy can also be improved compared to that of classical spin image based registration method and the multiple resolution method in reference [17]. This can be obtained through the number of the good correspondences in experiment 1 and the quantitative evaluation in experiment 2.…”

“…In each experiment, two groups of point cloud data are obtained with different conditions: In experiment I, the data are obtained from different viewpoints but with the similar sensor-scene distance, i.e., with the similar data scale; in experiment II, the data are obtained from different distance but with the similar viewpoint; while in experiment III, the data are obtained from different distance/scale and different viewpoint. Furthermore, in order to show the performance improvement of the proposed algorithm, in each experiment, three different registration algorithms, including Algorithm I (called TSPR) as shown in section II, Multi-Resolution Spin-Image algorithm (MRSP) as shown in reference [17], which is a good extension of Algorithm I with reduced computational burden, and the new proposed algorithm, are used and the results are compared. Experimental results are shown in Fig.…”

“…For example, in reference [16], PCA method is used to reduce the dimension of the spin-image feature, so that the total computation requirement can be cut down. In reference [17], Dinh and Kropac propose to use multiple resolution method to reduce the computational burden of spin image based registration algorithm. While in reference [18], SIFT operator is used to reduce the key-point that needs to be considered, and thus the computational burden of the registration can be decreased greatly.…”

Novel 3-D Object Recognition Methodology Employing a Curvature-Based Histogram

“…Spin image [29,30,31] is another object matching technique, which uses 2-D image characterization of a point belonging to a surface. The 2-D image shape descriptor has two coordinates of alpha and beta, which are calculated for a vertex in the surface mesh.…”