Kinect depth image inpainting method based on improved trilateral filtering

Abstract

The invention belongs to the technical field of depth image inpainting, and particularly relates to a Kinect depth image inpainting method based on improved trilateral filtering for kinect depth images. The method comprises the steps that depth images and color images are synchronously acquired by utilizing Kinect; the color images and the depth images are aligned; edge information of the depth images is extracted; edge information of the color images is extracted; non-boundary texture information in the color images is removed; pixel points of which the depth values are incorrect are found in the depth images by using a region growing method and the incorrect depth values of the points are removed; and filling inpainting is performed on the hole areas of the depth images by using the improved trilateral filtering method based on aberration and structural similarity coefficient. The method has great hole filling effect for the kinect depth images so that the edge information of the depth images can be greatly maintained.

Description

technical field [0001] The invention belongs to the technical field of depth image repair, and in particular relates to a Kinect depth image repair method based on improved trilateration filtering for kinect depth images. Background technique [0002] Depth image is a new image mode, which has broad application prospects in computer vision, automatic navigation and other fields. [0003] As a relatively cheap depth image and color image acquisition device, Kinect acquires depth images through special structured light technology, and obtains depth images with high resolution, which has attracted the general attention of scientific research and development workers and the industry. However, due to the limitations of Kinect's structural characteristics and ranging principle, the obtained depth image has some defects: such as the hollow area caused by the inability to accurately measure the depth value, and the edge mismatch between the depth image and the color image. These pr...

AI Technical Summary

Problems solved by technology

However, due to the limitations of Kinect's structural characteristics and ranging principle, the obtained depth image has some defects: such as the hollow area caused by the inability to accurately measure the depth value, and the edge mismatch between the depth image and the color image, etc.

[0004] At present, there are mainly two methods for Kinect depth image restoration: one method is to repair the depth image directly without texture image, and its restoration effect is poor; The information of the texture image, this type of method has a good effect on maintaining the edge of the depth map

Images