Study Of Guided Filtering-based Light Field Image Fusion And Depth Estimation

With the continuous development of light field theory and the maturity of light field imaging technology,the light field image processing has received widespread attention from many scholars at home and abroad in recent years.Compared with the traditional camera,the light field camera records the position and angle information of light ray,so digital refocusing technology can be used to realize the conversion of a single light field image to multiple highly matched refocused images,which has significant advantages in the all-in-focus image fusion and depth estimation.In this regard,the all-in-focus image and depth image acquisition technology based on micro-lens light field camera is studied in this paper.The specific research work and innovations are as follows:1.A light field all-in-focus image fusion algorithm based on edge-enhanced guided filtering is proposed.Through multi-scale decomposition of the digital refocused images and guided filtering optimization of the feature layer decision map,the final all-in-focus image is obtained.Compared with the traditional fusion algorithm,the edge information loss caused by the 4D light field calibration error is compensated in the presented method.In the step of multi-scale decomposition of the refocused image,the edge layer extraction is added to accomplish the high-frequency information enhancement.Then the multi-scale evaluation model is established to optimize the edge layer's guided filtering parameters to obtain a better light field all-in-focus image.The experimental results show that the perceptual sharpness of the all-in-focus image can be improved by 18.4% on average without significantly reducing the similarity between the all-in-focus image and the original image.2.A light field depth map optimization algorithm based on guided filtering is proposed.In view of the blur edge information and low precision of the depth map obtained by the traditional light field depth estimation algorithms,the optimization of depth map is completed based on the edge-preserving smoothing filtering property of the guide filter.In the guided filtering process,the center sub-aperture image is used as the guidance image of the depth map,and the edge correlation between the texture of the light field image and the depth information is used to realize the edge reconstruction of the depth map.Experiments verify the effectiveness of the proposed algorithm.After guided filtering of the depth map from combing defocus and correspondence algorithm,the edge details of the optimized depth map are more reasonable,and the mean square error of quantitative evaluation is reduced by 0.96% on average.