A method and device for denoising deep images

Abstract

The invention is applicable to the technical field of image processing, and provides a depth image noise reduction method and device, and the method comprises the steps: obtaining at least two framesof depth images, and determining one frame of depth image as a current frame of depth image; comparing the current frame of depth image with the adjacent frame of depth image to obtain a difference between two adjacent frames of depth image data, and recording an area corresponding to the difference as a candidate noise point; by taking the candidate noise point as a center, obtaining a connectedregion of the candidate noise point, and forming a candidate noise block by the candidate noise point and the connected region thereof; Filtering the candidate noise blocks to obtain real noise points; processing the depth data of the real noise points in the current frame of depth image to remove the real noise points in the current frame of depth image; noise points and at most two frames of noise point blocks appearing at the same position can be effectively removed, the method can be applied to depth image noise reduction in a multi-frame or dynamic environment, and the method has a wide application prospect.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method and device for denoising a depth image. Background technique [0002] The binocular structured light will match the infrared images acquired by two infrared (IR) lenses to generate parallax, thereby generating depth data. However, due to the complex real environment, in some scenes, due to the influence of some environmental factors (such as interference light sources in the environment, special materials, etc.), the infrared image will be incorrectly matched in some areas, resulting in some error data. When the value should be 0, an abnormal depth value appears, and the depth value of this area is the generated noise. Not only binocular structured light will cause the above situation, but also similar situations will occur when images are collected by time-of-flight (TOF), stereo image and other technologies. [0003] The current technical solutio...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a depth image noise reduction method and device to solve the technical problem in the prior art that the effect of noise reduction in a single frame depth image is not good

Images