Filling method and device for missing pixels of depth image

Abstract

The invention provides a filling method and device for missing pixels of a depth image. The method comprises the steps of determining a to-be-filled pixel region, a strip-shaped region and an effective pixel region according to the data effectiveness of the depth image, wherein the to-be-filled pixel region comprises a missing pixel part and/or a pixel invalid part caused by noise; obtaining a mapping value from an effective pixel to a boundary distance in the strip-shaped region to form a priority queue; when the number of the pixels in the priority queue is greater than zero, obtaining the pixels of the priority queue, and adding the pixels to the effective pixel region; acquiring four neighborhood pixels of the pixel, dividing the region where the four neighborhood pixels are located, when the number of the pixels in the priority queue is equal to zero, obtaining a depth image which is completely filled, achieving the quick and effective filling of the depth image, setting a regionneeding to be filtered as an invalid pixel region while the missing pixels are filled, and achieving the filling of the invalid pixels in the filtering region.

Description

technical field [0001] The present application relates to the field of visual images, in particular to a method and device for filling missing pixels in a depth image. Background technique [0002] In the field of visual images, the depth image can reflect the depth information of the captured object. By processing the acquired depth image, the height measurement, volume measurement and related detection operations of the object can be realized. At present, due to the limited viewing angle of the laser light source or the camera, the laser cannot scan some areas of the object, or the camera cannot observe part of the light stripe information of the laser, so the depth values ​​of some pixels in the image cannot be calculated, which eventually leads to the existence of Due to the lack of pixels, and due to the influence of the acquisition equipment and the acquisition environment, noise data will inevitably be introduced into the acquired depth image, which will affect the pr...

AI Technical Summary

Problems solved by technology

[0005] The present application provides a method and device for filling missing pixels in a depth image to solve the technical problem of not fully utilizing the depth information of effective pixels in the neighborhood of missing pixels in the filling method

Images