Nanjing University of Aeronautics and Astronautics

Zikuan Li

Jun Wang

Zhongde Shan

Yuan Zhang

Chao Li

Qian Xie

Anyi Huang

Tianchi Zhong

Kun Xiao

Kaijun Zhang

Hu Li

The present disclosure discloses a method for multi-view point cloud registration for a whole aircraft based on a spherical harmonic feature (SHF). Gaussian sphere projection is mainly performed on a local point cloud. An SHF of each point is obtained by using a spherical harmonic transform technology. A constraint correspondence between feature points is found based on an SHF of each point in the point cloud. Multi-view point cloud data registration is performed according to an optimization graph method under a constraint of the SHF. A key of multi-view point cloud registration is to search for feature constraint relationships between different observation stations and perform non-linear solution based on these relationships, so as to obtain a pose parameter of a point cloud in each viewing angle.

Method for multi-view point cloud registration for whole aircraft based on spherical harmonic feature (SHF)

A semantic segmentation method for aircraft point cloud based on voxelization and three views, including: filtering a collected point cloud followed by centralization to obtain a centralized point cloud; inputting the centralized point cloud into a T-Net rotation matrix network; rotating the centralized point cloud to a front side followed by voxelization to obtain a voxelized point cloud; subjecting the voxelized point cloud to voxel filling to obtain a voxel-filled point cloud; calculating thickness maps of three views of the voxel-filled point cloud, followed by sequentially stitching and inputting to the point cloud semantic segmentation network to train the point cloud semantic segmentation network; inputting the collected point cloud into the trained point cloud semantic segmentation network; and predicting a result semantic segmentation of a 3D point cloud of the aircraft.

Semantic segmentation method for aircraft point cloud based on voxelization and three views

This application discloses a semantic learning-based down-sampling method of point cloud data of an aircraft, including: (S) constructing a multi-input encoder based on feature learning according to point cloud semantic learning principle; inputting the point cloud data of the aircraft and feature point data into the multi-input encoder for feature fusion followed by decoding using a decoder the multi-input feature fused data to obtain to-be-measured data; (S) constructing and training a point cloud feature weight calculation network based on semantic learning to acquire a feature weight of each point in the to-be-measured data; and (S) performing spatial weighted sampling on the feature weight of each point in the to-be-measured data followed by down-sampling based on Gaussian distribution-based spatial sampling principle.

Semantic learning-based down-sampling method of point cloud data of aircraft

A method for visualizing a large-scale point cloud based on normal, including: (S) according to a spatial structure of a point cloud data, constructing a balanced octree structure of a node point cloud; (S) according to the balanced octree structure and normal information of a point cloud, constructing an octree structure with the normal information; and constructing a normal level-of-detail (LOD) visualization node through downsampling; and (S) determining a node scheduling strategy according to a relationship between a viewpoint, a viewing frustum and a normal of a render node; and respectively calling a reading thread and a rendering thread to simultaneously perform reading and rendering according to the node scheduling strategy.

Method for visualizing large-scale point cloud based on normal

Growing community of inventors

Nanjing, China

Zikuan Li