Light Field Depth Estimation For Scene With Occlusion

The light field camera is a new imaging system based on the light field imaging technology.It can obtain the 4D light field data from stereoscopic space with one shot.After that,the depth information can be extracted by multiview characteristic of the light field,which is of great importance for visual tasks such as saliency detection,super-resolution reconstruction,and 3D reconstruction.However,the existing depth estimation method rarely considers the presence of occlusion in the scene.The accuracy of the extracted depth information is significantly reduced,when the scene is blocked.To solve this problem,the depth estimation method for light field image of occlusion scene is studied in this paper.The main work of this thesis is listed as follows:(1)The research status of depth estimation,parametric representation and acquisition method of the light field,and imaging principle of the light field camera are summarized.Then introduce the Epipolar Plane Image,multiview image,refocusing of light field and the basic method for obtaining depth information.(2)A depth estimation algorithm based on EPI images is designed and implemented.We First extract the local depth information of the scene by using a spinning parallelogram operator on the horizontal and vertical EPI images,and then calculate the confidence of the depth information using ALM weighted depth information.Finally,we optimize the local depth images by guided filtering and iterative optimization to obtain continuous depth maps.Experimental results show that the method can effectively extract scene depths in the occlusion and edge areas of the image.(3)A new depth estimation method of light field image based on multi-clues fusion is presented to obtain high-precision depth information.Firstly,the adaptive defocus algorithm and the adaptive matching algorithm are used to extract the depth information of the scene.And then the peak ratio is taken as confidence to synthesize the depth images.Finally,the fusion depth map is filtered by a combined filter with structural consistency,and a high precision depth map is obtained.The experimental results show that the depth images obtained by the proposed method are more accurate,less noise,and the extraction depth of the occlusion area and image edge is better.