基于三维点云深度学习的飞机表面多圆孔基元提取方法

Method for Extracting Multiple Circle Primitives Extraction of Aircraft Surface Based on 3D Point Cloud Deep Learning

在飞机部件自动制孔系统中,快速、精确检测飞机表面圆孔对飞机装配质量具有重要作用,但从大规模三维测量点云数据中自动化、精确、快速检测所有圆孔特征依旧是一个难点。鉴于此,提出一种基于三维点云深度学习的飞机表面多圆孔基元提取方法。使用三维点云深度学习网络预测三维测量点云中初始圆孔边界点,并基于初始圆孔边界点,学习圆孔法向。同时,设计基于学习的加权最小二乘(Weighted least square,WLS)方法拟合圆孔参数,并将圆孔边界点检测误差、圆孔参数估计误差、圆孔法向学习误差作为多任务联合损失进行网络训练。通过在不同噪声、不同分辨率的模拟点云数据和实测点云数据上进行测试,并与现有先进边界提取、圆孔拟合方法进行对比。试验结果表明,所提出的方法在边界点识别准确度、圆孔参数计算准确度等方面获得了优越的综合性能。

In the aircraft automatic hole manufacturing system,rapidly and accurately detecting the circle holes on the surface of the aircraft is important for the assembly quality of the aircraft.However,it is still difficult to detect them accurately and quickly from the measured point clouds.A method for extracting multiple circle primitives based on 3D point cloud deep learning is proposed.Specifically,a 3D point cloud network is presented to predict the initial circle boundary points,based on which,the circles’ normals are computed.Learning-based weighted least squares(WLS) is then designed to estimate the circle parameters.Finally,the circle boundary point classification,circle parameter estimation and circle normal computation are co-trained with a multi-task loss to enhance the quality of circle extraction.Comparisons on the simulated point clouds and real-scanned point clouds of different noise intensities and resolutions exhibit clear improvements in terms of noise-robustness and extraction accuracy.