Estimating 3D particle motion from high‐speed video for simulation validation

Abstract

PurposeThe purpose of this paper is to present an image based method for estimating the 3D motion of rigid particles from high‐speed video footage (HSV). The computed motion can be used as either a means to generate quantitative feedback for a process or to validate the accuracy of discrete element method (DEM) simulation models.Design/methodology/approachExperiments consist of a diamond impacting an angled plate and video is captured at 4,000 frames per second. Simple image analysis is used to track the particle in each frame and to extract its 2D silhouette boundary. Using an approximate 3D model of the particle generated from a multi‐camera setup, a pose estimation scheme based on silhouette consistency is used in conjunction with a rigid body model to compute the 3D motion.FindingsUnder reasonable conditions, the method can reliably estimate the linear and angular motion of the particle to within 1 per cent of their true values.Practical implicationsAs an example application, we demonstrate how the method can be used to validate DEM simulations of simple impact experiments captured with HSV, providing valuable insight towards further development. In particular, we investigate the effects of shape representation through sphere‐clumping and the applicability of different contact models.Originality/valueThe novelty of our method is its ability to accurately compute the motion associated with a real world interaction, such as an impact, which provides numerical ground truth at an individual particle level. While similar schemes have been attempted with ideal particles (e.g. spheres), the resulting models do not naturally extend to realistic particle shapes. Since our method can track real particles, real‐world processes can be better quantified.