Video image 3D noise reduction method and apparatus thereof

Abstract

The invention provides a video image 3D noise reduction method and an apparatus thereof. The method comprises the following steps of collecting current first image data from a video image; carrying out 2D noise reduction based on an airspace on the first image data and acquiring current second image data; according to the current second image data, acquiring a binary image, wherein the binary image includes a background area and a foreground area; acquiring a filtering intensity coefficient of each pixel point in the current second image data on time-domain filtering; and according to a 3D noise reduction result of a previous frame of image data of the current first image data and the filtering intensity coefficient, carrying out 3D noise reduction processing on the current second image data. In an existing 3D noise reduction technology, relatively-accurate motion information is difficult to acquire; and FIR filtering is performed in a time domain so that storage cost of equipment is increased. By using the method and the apparatus of the invention, the above problems are solved. A noise reduction effect of the video image is increased so that 3D noise reduction can be widely applied.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a method and device for 3D noise reduction of video images. Background technique [0002] Videos and images have attracted the attention of users due to their strong visualization. However, the quality of video images directly affects the use of users, and the noise reduction function of video images undoubtedly plays a key role in it. Good image noise reduction technology Some moving objects can be clearly identified in low-light scenes. In the field of video image noise reduction technology, 3D noise reduction technology has become a research hotspot. Generally speaking, if only the noise reduction method based on the space domain or only the time domain is used for video image noise reduction, it is easy to have smooth image transitions, loss of details, and jumping noise between frames, and the combination of time domain and space domain The 3D noise reduction method ca...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the technical problem to be solved by the present invention is to overcome the 3D noise reduction in the prior art. It is relatively difficult to obtain relatively accurate motion information in low-illuminance scenes, which easily leads to erroneous analysis of background and foreground pixels. , there are defects such as background noise not falling down and foreground moving objects appearing serious smearing. At the same time, FIR filtering in the time domain needs to store multiple frames of historical image data, which increases the storage overhead of the device, which is not conducive to the 3D noise reduction method. Real-time performance of video image system

Thereby providing a video image 3D noise reduction method and device

Images