A point cloud filtering system and filtering method based on RGB-D information

Abstract

The invention relates to the technical field of point cloud filtering, in particular to point cloud filtering system and filtering method based on RGB-D information. The system comprises a calibrationmodule, a mapping module, a conversion module, a first processing module, a repair module, a second processing module and a point cloud obtaining module. The invention can effectively obtain the filtered point cloud and has high efficiency.

Description

technical field [0001] The invention relates to the technical field of point cloud filtering, in particular to a point cloud filtering system and filtering method based on RGB-D information. Background technique [0002] With the development of depth camera technology, cameras capable of simultaneously capturing color images and depth images have been widely used in the acquisition system of 3D point cloud data. However, due to the complex structure and method of the depth image imaging principle itself, as well as the interference of the external environment, the 3D point cloud data obtained by the depth camera will contain a lot of noise. Therefore, in the 3D point cloud acquisition system, filtering processing is the most important An important part. [0003] The current filtering methods can produce certain filtering effects for different noise types. However, for non-isolated outliers, none of the existing filtering methods can obtain better filtering effects. The cu...

AI Technical Summary

Problems solved by technology

However, for non-isolated outliers, none of the existing filtering methods can obtain better filtering effects.

The current filtering methods are all directly applied to 3D data information, so the efficiency is low. For a large amount of point cloud data, it is difficult to achieve the real-time performance required by the engineering field.

Images