亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

MVGCN: Multi-View Graph Convolutional Neural Network for Surface Defect Identification Using Three-Dimensional Point Cloud

点云 鉴定(生物学) 计算机科学 卷积神经网络 人工智能 曲面(拓扑) 机身 逆向工程 不变(物理) 转化(遗传学) 点(几何) 算法 计算机视觉 模式识别(心理学) 工程类 几何学 数学 结构工程 基因 生物 植物 生物化学 化学 数学物理 程序设计语言
作者
Yinan Wang,Wenbo Sun,Jionghua Jin,Zhenyu Kong,Xiaowei Yue
出处
期刊:Journal of Manufacturing Science and Engineering-transactions of The Asme [ASM International]
卷期号:145 (3) 被引量:19
标识
DOI:10.1115/1.4056005
摘要

Abstract Surface defect identification is a crucial task in many manufacturing systems, including automotive, aircraft, steel rolling, and precast concrete. Although image-based surface defect identification methods have been proposed, these methods usually have two limitations: images may lose partial information, such as depths of surface defects, and their precision is vulnerable to many factors, such as the inspection angle, light, color, noise, etc. Given that a three-dimensional (3D) point cloud can precisely represent the multidimensional structure of surface defects, we aim to detect and classify surface defects using a 3D point cloud. This has two major challenges: (i) the defects are often sparsely distributed over the surface, which makes their features prone to be hidden by the normal surface and (ii) different permutations and transformations of 3D point cloud may represent the same surface, so the proposed model needs to be permutation and transformation invariant. In this paper, a two-step surface defect identification approach is developed to investigate the defects’ patterns in 3D point cloud data. The proposed approach consists of an unsupervised method for defect detection and a multi-view deep learning model for defect classification, which can keep track of the features from both defective and non-defective regions. We prove that the proposed approach is invariant to different permutations and transformations. Two case studies are conducted for defect identification on the surfaces of synthetic aircraft fuselage and the real precast concrete specimen, respectively. The results show that our approach receives the best defect detection and classification accuracy compared with other benchmark methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
开心的瘦子完成签到,获得积分20
1秒前
JOSIELO完成签到 ,获得积分10
1秒前
2秒前
6秒前
程小柒完成签到 ,获得积分10
11秒前
13秒前
19秒前
Ghiocel完成签到,获得积分10
30秒前
36秒前
佟语雪完成签到,获得积分10
36秒前
轻松的惜芹应助喂喂采纳,获得10
40秒前
淳于如雪发布了新的文献求助10
43秒前
LLL完成签到 ,获得积分10
47秒前
yar应助淳于如雪采纳,获得10
48秒前
Koking关注了科研通微信公众号
53秒前
54秒前
淳于如雪完成签到,获得积分20
56秒前
lv发布了新的文献求助10
57秒前
我是老大应助吴嘉俊采纳,获得10
1分钟前
1分钟前
在水一方应助阿九采纳,获得10
1分钟前
1分钟前
ZT完成签到,获得积分10
1分钟前
搜集达人应助zhouleiwang采纳,获得10
1分钟前
吴嘉俊发布了新的文献求助10
1分钟前
仙人掌王朝完成签到,获得积分10
1分钟前
1分钟前
Hello应助zhouleiwang采纳,获得10
1分钟前
阿九完成签到,获得积分10
1分钟前
lllxxx完成签到 ,获得积分10
1分钟前
lv发布了新的文献求助10
1分钟前
冉亦完成签到,获得积分10
1分钟前
WGS完成签到,获得积分10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
华仔应助科研通管家采纳,获得20
1分钟前
吉吉吉完成签到 ,获得积分10
1分钟前
1分钟前
阿九发布了新的文献求助10
1分钟前
大胆的小懒猪完成签到 ,获得积分10
1分钟前
111完成签到 ,获得积分10
1分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3990012
求助须知:如何正确求助?哪些是违规求助? 3532049
关于积分的说明 11256153
捐赠科研通 3270925
什么是DOI,文献DOI怎么找? 1805123
邀请新用户注册赠送积分活动 882270
科研通“疑难数据库(出版商)”最低求助积分说明 809216