A Denoising Method for Depth Image

Abstract

The invention discloses a depth image denoising method which can reduce edge blur of images, is applicable to non-zero-mean Gaussian denoising and greatly improves depth image quality. The depth image denoising method includes the steps that 1, joint bilateral filtering is carried out on the depth images, the action scope of a bilateral filter is constrained, and accordingly filtered images are obtained; 2, a dictionary is trained through a K-SVD method, the filtered images of the first step are denoised through sparse representation on the basis of the dictionary, and reconstructed images are obtained.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for denoising a depth image, and is particularly suitable for denoising a human body depth image collected by a Kinect and a time-of-flight camera (ToF camera). Background technique [0002] Compared with traditional grayscale images and color images, depth images have three-dimensional feature information of objects, so they are more and more used in computer vision, computer graphics and other fields. In November 2010, the Kinect produced by Microsoft has become one of the commonly used depth image acquisition devices because of its real-time, low-cost and other characteristics. However, due to environmental light conditions, occlusion and other factors, the depth data collected by Kinect usually has low resolution and contains many noises and singular pixels. [0003] For image noise removal, researchers have proposed a large number of effective ...

AI Technical Summary

Problems solved by technology

The usual image denoising algorithm inevitably brings the smoothness and fuzzy problem of the edge, which brings difficulties to the further application of the depth image.

Images