Multi-scale surface flatness evaluation method based on the idea of two-dimensional convolution

被引:0
|
作者
Xu, Wenbiao [1 ]
Lan, Xuejing [2 ]
Li, Zhifeng [3 ]
机构
[1] Guangdong Inst Metrol, Guangdong Prov Key Lab Modern Geometr & Mech Metr, Guangzhou, Peoples R China
[2] Guangzhou Univ, Sch Mech & Elect Engn, Guangzhou, Peoples R China
[3] Guangdong Inst Metrol, Guangzhou, Peoples R China
关键词
flatness evaluation; multi-scale; point clouds; convolution; CONSTRUCTION;
D O I
10.1109/YAC51587.2020.9337705
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes a multi-scale surface flatness evaluation method, where the surface flatness of objects is measured by using laser point clouds. This method is based on the idea of two-dimensional convolution, and the natural neighbor interpolation (NNI) is used to construct convolution kernels and establish an evaluation function. By changing the size of the convolution kernel, it is easier to reflect the situation of plane flatness at different scales. At the same time, according to the convolution results, non-flat regions and their sizes can be quickly extracted. Finally, the effectiveness of the evaluation method is verified by simulations and experiments.
引用
收藏
页码:38 / 43
页数:6
相关论文
共 50 条
  • [41] Typhoon Classification Model Based on Multi-Scale Convolution Feature Fusion
    Lu Peng
    Zou Peiqi
    Zou Guoliang
    LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (16)
  • [42] Monocular Depth Estimation Based on Multi-Scale Graph Convolution Networks
    Fu, Junwei
    Liang, Jun
    Wang, Ziyang
    IEEE ACCESS, 2020, 8 : 997 - 1009
  • [43] Steganalysis for HEVC video based on multi-scale residual convolution network
    Zhang M.
    Li Z.
    Liu J.
    Zhang Z.
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (11): : 2226 - 2233
  • [44] Multi-scale sparse convolution and point convolution adaptive fusion point cloud semantic segmentation method
    Bi, Yuxuan
    Liu, Peng
    Zhang, Tianyi
    Shi, Jialin
    Wang, Caixia
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [45] MGCNet: A Multi-scale Grouped Convolution-Based Seal Detection Method for Painting and Calligraphy Works
    Liu, Yuzheng
    Li, Min
    Zhao, Xueqing
    WEB INFORMATION SYSTEMS AND APPLICATIONS, WISA 2024, 2024, 14883 : 586 - 594
  • [46] Small Object Detection Method Based on Adaptive Spatial Parallel Convolution and Fast Multi-Scale Fusion
    Qi, Guanqiu
    Zhang, Yuanchuan
    Wang, Kunpeng
    Mazur, Neal
    Liu, Yang
    Malaviya, Devanshi
    REMOTE SENSING, 2022, 14 (02)
  • [47] Image Detection Method for Tank and Armored Targets Based on Hierarchical Multi-scale Convolution Feature Extraction
    Sun H.-Z.
    Chang T.-Q.
    Wang Q.-D.
    Kong D.-P.
    Dai W.-J.
    Chang, Tian-Qing (changtianqing@263.net), 1681, China Ordnance Industry Corporation (38): : 1681 - 1691
  • [48] Non-intrusive load monitoring method based on multi-scale convolution and Informer hybrid model
    Han L.
    Gao F.
    Zhao Z.
    Guo S.
    Li X.
    Zhang D.
    Wu X.
    Dianli Zidonghua Shebei/Electric Power Automation Equipment, 2024, 44 (03): : 134 - 141
  • [49] Remote Sensing Scene Classification Method Based on Multi-Scale Graph Convolution Context Feature Aggregation
    Chen, Baolan
    Li, Huawang
    Wang, Yinxiao
    LASER & OPTOELECTRONICS PROGRESS, 2025, 62 (04)
  • [50] Retinal Vessel Segmentation Method Based on Position-Aware Circular Convolution with Multi-Scale Input
    Jiang, Zhongchuan
    Wu, Yun
    Computer Engineering and Applications, 2023, 59 (21) : 242 - 250