ロボット化ビューカメラのためのスマート被写界深度最適化
Smart depth of field optimization applied to a robotised view camera
コンピュータ制御のビューカメラを開発し、3D座標取得と幾何モデル構築に基づいて被写界深度内でF値を最小化する制約付き最適化を実現した。
著者: Stéphane Mottelet, Luc de Saint Germain, Olivier Mondin
分類: math.OC, cs.CV, cs.RO
原文アブストラクト
The great flexibility of a view camera allows to take high quality photographs that would not be possible any other way. But making a given object into focus is a long and tedious task, although the underlying laws are well known. This paper presents the result of a project which has lead to the design of a computer controlled view camera and to its companion software. Thanks to the high precision machining of its components, and to the known optical parameters of lenses and sensor, we have been able to consider a reliable mathematical model of the view camera, allowing the acquisition of 3D coordinates to build a geometrical model of the object. Then many problems can be solved, e.g. minimizing the f-number while maintaining the object within the depth of field, which takes the form of a constrained optimization problem. All optimization algorithms have been validated on a virtual view camera before implementation on the prototype
