Moments of superellipsoids and their application to range image registration

Abstract

Abstract-Cartesian moments are frequently used global geometrical features in computer vision for object pose estimation and recognition. In the paper we derive a closed form expression for 3D Cartesian moment of order Ô ·Õ·Ö of a superellipsoid in its canonical coordinate system. We also show how 3D Cartesian moment of a globally deformed superellipsoid in general position and orientation can be computed as a linear combination of 3D Cartesian moments of the corresponding non-deformed superellipsoid in canonical coordinate system. Additionally, moments of objects that are compositions of superellipsoids can be computed as simple sums of moments of individual parts.To demonstrate practical application of the derived results we register pairs of range images based on moments of recovered compositions of superellipsoids. We use a standard technique to find centers of gravity and principal axes in pairs of range images while third-order moments are used to resolve the fourway ambiguity. Experimental results show expected improvement of recovered rigid transformation based on moments of recovered superellipsoids as compared to the registration based on moments of raw range image data. Beside object pose estimation the presented results can be directly used for object recognition with moments and/or moment invariants as object features.

Remarkable simplicity in the prediction of nonspherical particle segregation

“…We conduct discrete element method (DEM) simulations [16][17][18][19][20] of superellipsoid particles in a gravitydriven free-surface flow [12][13][14][21][22][23]. The particle shape is determined by the inside-outside function for superellipsoids [24][25][26]…”

Online Spatial Normalization for Real-Time fMRI

“…However, there are some practical issues in PA. First, if the scan orientation of the source image is not identical to the orientation of the reference image (e.g., a sagittally scanned source image and an axially scanned reference image), the estimate obtained using PA will be incorrect [31] . To eliminate the constraint on scan orientation, higher moments can be introduced into the PA [41] , which would cause extra computational loads. Second, the PA requires whole brain information; if the brain is partially scanned, the estimate by PA could deviate.…”

Part-level object recognition using superquadrics

“…Using that assumption, the configuration can be computed efficiently. Let the partÕs main axis be the axis of minimal inertia [2,22]. Our analysis of such objects showed that the main axes of scene parts are well aligned with true main axes of the object model parts.…”