KINECT depth map cavity filling method based on local restriction reconstruction

Abstract

The invention discloses a KINECT depth map cavity filling method based on local restriction reconstruction. The KINECT depth map cavity filling method based on the local restriction reconstruction comprises the steps of taking a cavity pixel in a depth map as a center to construct a search window, obtaining all non-cavity pixels in the search window, obtaining corresponding position pixels of the cavity pixel and the non-cavity pixels in a texture map, taking the corresponding position pixels as centers to build blocks, taking a bock where the corresponding position pixel of the cavity pixel is located as a central block, taking blocks where the corresponding position pixels of the non-cavity pixels as neighborhood blocks, constructing a cost function based on a local restriction reconstruction standard and obtaining the neighborhood blocks to be used for expressing the optimal weight vector of the central block, achieving a weighted sum pixel value of all the non-cavity pixels in the search window based on the optimal weight vector of the neighborhood blocks to obtain a target pixel value, and taking the target pixel value as the pixel value of the cavity pixel in the depth map. The KINECT depth map cavity filling method based on the local restriction reconstruction can accurately fill up cavities in an edge area and a smooth area of the depth map.

Description

technical field [0001] The present invention relates to a KINECT depth map hole filling method, in particular to a KINECT depth map hole filling method and system based on local constraint reconstruction. Background technique [0002] Currently, depth information is widely used in depth-based viewpoint rendering, 3D modeling, and pose recognition. Recently, KINECT released by Microsoft provides convenience for real-time acquisition of depth information. KINECT is not only cheap but also can simultaneously collect the depth map and texture map of the scene. However, because the structured light measurement method used by KINECT to collect depth information is susceptible to occlusion, transparent objects or regions with rich textures, the collected depth map has holes at the edge of the object or flat areas, which seriously affect the depth map. Applications. Therefore, accurate filling of the holes in the depth map is crucial. [0003] In recent years, many scholars have ...

AI Technical Summary

Problems solved by technology

However, this algorithm causes the edges of the depth map to swell, and some small holes still exist

Based on the structural and spatial similarity between the depth map and the texture map, some scholars use the iterative diffusion method to restore the lost depth information based on the texture map region segmentation results, but this method is easily limited by the texture map segmentation accuracy

Miao et al. [2] The in-painting algorithm is used to fill the hole. This method fills the hole by dividing the fluctuating edge area, but the hole on the edge of the object is filled with the average value of the depth value in the fluctuating edge area, and the depth value is not accurate.

In order to increase the accuracy of non-hole pixel weight calculation, Camplani et al. [3] Based on the joint bilateral filtering algorithm, the texture map is used to calculate the weight of non-hole pixels for hole filling. Although this method has achieved certain results, it only considers a single surrounding pixel pair center when calculating the weight of non-hole pixels. The contribution of pixels does not consider the overall contribution of all surrounding pixels to the central pixel, resulting in the calculation of weights is not optimal, affecting the accuracy of hole filling

Images