Differential Evolution with Improved Mutation Strategy

A novel camera calibration technique based on differential evolution particle swarm optimization algorithm, Neurocomputing, http://dx.doi.org/10.1016/j.neucom. 2015.03.119 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting galley proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. AbstractCamera calibration is one of the fundamental issues in computer vision and aims at determining the intrinsic and exterior camera parameters by using image features and the corresponding 3D features. This paper proposes a relationship model for camera calibration in which the geometric parameter and the lens distortion effect of camera are taken into account in order to unify the world coordinate system (WCS), the camera coordinate system (CCS) and the image coordinate system (ICS). Differential evolution is combined with particle swarm optimization algorithm to calibrate the camera parameters effectively. Experimental results show that the proposed algorithm has a good optimization ability to avoid local optimum and can complete the visual identification tasks accurately.

show abstract

“…It can improve the convergence of the algorithm and prevent the particles into premature convergence [25,33,35].…”

Section: Differential Evolution Particle Swarm Optimizationmentioning

confidence: 99%