基于聚焦法的主动投影三维重建技术

Active Pattern Projection for Shape-From-Focus in Microscopy

基于聚焦法的三维重建技术是一种可以通过单目相机获取物体三维特征的技术,使用聚焦评价算子来计算图像清晰度是其中一个重要环节。针对聚焦评价算子严重依赖被测物体表面纹理这一问题,提出一种在显微镜中主动投影图案的方法,通过光学系统设计实现投影图案与物体纹理共聚焦以增强图像纹理。然而,在实验中发现该方法存在投影图案聚焦面与相机聚焦面不重合、投影图案场曲的问题,针对这些问题提出一种调节相机聚焦面高度并进行深度补偿的方法以矫正误差,并验证了该方法的有效性。对有无主动投影图案的对象进行对比实验,结果表明所提方法能够显著提高光滑表面三维重建精度和完整度,并根据结论给出了该方法的适用场合。

Shape-from-focus(SFF)is a technology that can capture the three-dimensional features of objects through a monocular camera.Using focus measure operators to calculate image clarity is a crucial step in this technique.Addressing the issue of focus evaluation operators heavily relying on the surface texture of the measured object,a method of actively projecting patterns in microscopy is proposed in this paper.Through optical system design,the proposed method achieves co-focusing of the projected pattern and the object texture to enhance image texture.However,it is observed in experiments that this method faces challenges such as the non-coincidence of the focus plane of the projected pattern with the camera’s focus plane and the curvature of the projected pattern field.To solve these problems,this paper proposes a method to adjust the height of the camera’s focus plane and provide depth compensation to correct errors.The effectiveness of this method is validated through experimentation.Comparative experiments on objects with and without active projected patterns demonstrate that the proposed method significantly improves the accuracy and completeness of three-dimensional reconstruction for smooth surfaces.Based on the conclusions drawn,the paper introduces the applicable scenarios of this method.