Underwater Non-Rigid 3D Shape Reconstruction via Structure from Motion for Fish Ethology Research

In this paper, we try to develop a general framework of 3D shape reconstruction strategy with extremely rare point cloud extracted for fish ethology research. Particle filter is first taken to focus on fish trajectory tracking from monocular video sequence. The Speeded Up Robust Features (SURF) technique will be adopted to match the same tracking fish across the overlapping view fields with more stable and accurate features. Non-rigid 3D shape reconstruction will be finally developed with the help of expectation maximization (EM) model and linear dynamical system (LDS). It is shown from our simulation experiment that the developed scheme of this paper achieves consistent performance improvements over non-rigid 3D shape reconstruction for fish ethology research.