Defocus depth estimation and full focus image acquisition method of dynamic scene

Abstract

The invention provides a defocus depth estimation and full focus image acquisition method of a dynamic scene. The method comprises the following steps of: acquiring first depth maps and globally inconsistent fuzzy kernels of a plurality of defocused images, and employing an image deblurring algorithm based on defocus depth estimation to carry out feedback iterative optimization to obtain a full focus image and a second depth map of each moment; after carrying out color segmentation on the full focus image of each moment, and carrying out plane fitting on the depth map, and carrying out refinement of space to obtain a third depth map, and carrying out optimization again to obtain an optimized full focus image; after carrying out optical flow estimation on the full focus image, carrying out smoothing on the third depth map, refining the third depth map in the time to obtain a depth estimation result with a consistent time. According to the method, a more precise dynamic scene depth estimation result and a full clear image can be obtained, and realization is easy.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for estimating the defocus depth of a dynamic scene and acquiring an all-focus image. Background technique [0002] How to restore the depth information of the scene from the 2D image sequence collected from the 3D scene is an important research content in the field of computer vision. The depth cues collected are usually used to infer the depth of the scene, such as depth estimation based on multi-view, depth estimation based on shadow, depth estimation of defocus, depth estimation of focus, etc. In addition, there are some methods by projecting active light way to estimate the depth of the scene. [0003] Defocus depth estimation has attracted people's attention since it was proposed by Pentland, and there are mainly methods based on a single defocused image and based on multiple defocused images. The defocused depth estimation algorithm based on a single def...

AI Technical Summary

Problems solved by technology

The defocused depth estimation algorithm based on a single defocused image usually cannot obtain satisfactory depth estimation results due to the underdetermination of the problem

Depth estimation algorithms based on multiple defocused images mainly include local methods and global methods. Local methods such as some spatial or frequency domain methods using local windows usually produce edge or window effects, while some global methods Algorithmic complexity is usually higher

The traditional defocus depth estimation algorithm usually eliminates the estimation of scene irradiance (full focus image) and only estimates the depth of the scene during the solution process

In addition, the main reason for the relatively little research on defocus depth estimation in dynamic scenes is that it is difficult to collect multiple defocused images focused at different depths in a dynamic scene at a certain moment

Images