3D interest point detection using local surface characteristics with application in action recognition

Abstract

In this paper we address the problem of detecting 3D interest points (IPs) using local surface characteristics. We contribute to this field by introducing a novel approach for detection of 3D IPs directly on a surface mesh without any requirements of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an example of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion descriptors, Histogram of Optical 3D Flow (HOF3D), are extracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the publicly available i3DPost dataset show promising results.