Depth map estimation based on linear regression using image focus

Abstract

This article presents a method for depth estimation using image focus based on the linear regression model. Two datasets are selected for each pixel based on the maximum value which is calculated using Laplacian operator. Then linear regression model is used to find lines that approximate these datasets. The best fit lines are found using least squares method. After approximating the two lines, their intersection point is calculated, and weights are assigned to calculate the new value for the depth map. The proposed method is compared with four depth estimation algorithms. Six different objects are selected for testing the proposed method. V

Partial light field tomographic reconstruction from a fixed-camera focal stack

“…An optical focus measure to obtain a depth map from a focal stack is proposed in [15], where a band-pass filter to detect sharpness is designed based on bipolar incoherent image processing. The focus measure proposed in [16] is obtained by taking the SML focus measure [13] as an initial estimate and improving it by fitting a linear regression model. Some other focus measures based on feature detection [17] and the complex wavelet transform [18] have also been proposed for depth estimation.…”