Shape from Focus with Adaptive Focus Measure and High Order Derivatives
Shape from Focus with Adaptive Focus Measure and High Order Derivatives
复制标题
通过自适应焦点测量和高阶导数从焦点形状
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
N. Kiryati
中科院分区：
文献类型：
--
作者：
Yuval Frommer;Rami Ben;N. Kiryati
焦点形状（SFF）方法经常使用单个焦点测量来获得深度图。常见的聚焦度量是固定的和空间不变的。在本文中，我们提出了一个框架，以创建一个自适应的焦点测量的基础上合奏的基础上的焦点运营商。使用所提出的框架，我们推导出一个新的空间变化的焦点测量图像导数的线性组合。这种方法有效地推广了一些现有的措施。一个新的措施出现从建议的框架，包括高阶导数，并提出了一个高度可靠的焦点措施。我们依靠聚焦曲线标准差（CSTD）来确定模型中的线性系数。出现的焦点措施有效地处理纹理变化，强强度的边缘和深度不连续性。使用CSTD，我们进一步提出了一种新的方法，聚集在焦点体积成功的重建的基础上的焦点曲线质心。这种不同的聚合和重建方法产生改进的深度图，尊重纹理图像多样性的形状平滑度和深度不连续性。我们评估我们的新方法的性能，通过广泛的实验与高度逼真的合成图像和真实的图像，包括在野外捕获的两个独特的情况下。在重点措施方面，我们显着优于国家的最先进的，同时提出了上级的结果相比，两个以前公布的替代品。
Shape From Focus (SFF) methods frequently use a single focus measure to obtain a depth map. Common focus measures are fixed and spatially invariant. In this paper we present a framework to create an adaptive focus measure based on ensemble of basis focus operators. Using the proposed framework we derive a new spatially variant focus measure obtained from linear combination of image derivatives. This approach effectively generalizes some of the existing measures. A new measure emerged from the proposed framework includes high order derivatives and presents a highly reliable focus measure. We rely on the focus curve standard deviation (CSTD) to determine the linear coefficients in our model. The emerged focus measure copes effectively with texture variation, strong intensity edges and depth discontinuities. Using CSTD we further suggest a new approach for aggregation in the focus volume succeeded by reconstruction based on the focus curve centroid. This different approach of aggregation and reconstruction yields improved depth maps, respecting shape smoothness and depth discontinuities for diversity of textured images. We assess the performance of our new approach by extensive experiments with highly realistic synthetic images and real images including two unique cases captured in the wild. In terms of focus measure, we significantly outperform the state-of-the-art, while presenting superior results comparing to two previously published alternatives.
影响因子：
3.4
作者：
Thompson, RE;Larson, DR;Webb, WW
通讯作者：
Webb, WW