Title of article
A new Approach to Estimate Motion and Structure of a Moving Rigid Object in a 3D Space with a Single Hand-Held Camera
Author/Authors
Serajeh, Reza Faculty of Electrical Engineering - K.N.Toosi University of Technology - Tehran, Iran , Mousavinia, Amir Faculty of Computer Engineering - K.N.Toosi University of Technology - Tehran, Iran , Safaei, Farzad Faculty of Informatics - University of Wollongong - Wollongong, Australia
Pages
12
From page
245
To page
256
Abstract
Classical SFM (Structure From Motion) algorithms are widely used to estimate the three-dimensional structure of a stationary scene with a moving camera. However, when there are moving objects in the scene, if the equation of the moving object is unknown, the approach fails. This paper first demonstrates that when the frame rate is high enough and the object movement is continuous in time, meaning that acceleration is limited, a simple linear model can be effectively used to estimate the motion. This theory is first mathematically proven in a closed-form expression and then optimized by a nonlinear function applicable for our problem. The algorithm is evaluated both on synthesized and real data from Hopkins dataset.
Keywords
structure from motion , dynamic scene 3D reconstruction , moving rigid object 3D motion estimation
Journal title
Journal of Artificial Intelligence and Data Mining
Serial Year
2022
Record number
2724126
Link To Document