An automatic defect classification and segmentation method on three-dimensional point clouds for sewer pipes

点云 分割 人工智能 过度拟合 计算机科学 棱锥(几何) 模式识别(心理学) 特征(语言学) 过程(计算) 点(几何) 人工神经网络 数学 几何学 语言学 哲学 操作系统
作者
Niannian Wang,Duo Ma,Xueming Du,Bin Li,Danyang Di,Gaozhao Pang,Yihang Duan
出处
期刊:Tunnelling and Underground Space Technology [Elsevier BV]
卷期号:143: 105480-105480 被引量:17
标识
DOI:10.1016/j.tust.2023.105480
摘要

With the development of deep learning (DL), sewer pipe inspection on two-dimensional (2D) images has achieved remarkable accuracy. However, extracting defect measurements from these 2D images is challenging due to the curved nature of pipes and the lack of depth information. Point clouds can restore the three-dimensional (3D) information of objects. To effectively identify defects in disordered and sparse point clouds, a 3D sewer pipe classification and segmentation method was proposed. In the encoder, the original point clouds are sampled and grouped and the local features in the clusters are extracted by two symmetric functions (1 × 1 convolution and the maximization function) to process the points with permutation invariance. In the decoder, the multi-scaling abstract features are upsampled using feature pyramid network (FPN) to predict the category of each point. Especially, the network structure and training strategy of the inspection method is optimized to improve the inspection accuracy. Furthermore, two data augmentation methods, namely random scaling and point jitter, are used to increase the data volume. An ablation experiment shows that the optimization of network structure can effectively improve the performance of the inspection model and the novel training strategies can stabilize the training process and prevent overfitting. Comparison among the state-of-the-art networks demonstrates that the proposed segmentation model attains the highest mIoU of 94.15 %, which is improved by 11.46 % with the optimization of network structure and training strategy. For the classification task, the F1 score and accuracy of the established model are 6.79 % and 5.46 % higher than PointNet++, respectively. These results signify the high-accuracy defect inspection capability of our proposed method on 3D point clouds of sewer pipelines.
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
博慧完成签到 ,获得积分10
刚刚
小刘医生完成签到,获得积分10
2秒前
安安完成签到,获得积分10
2秒前
啊啊啊啊完成签到,获得积分10
2秒前
英俊的铭应助飞飞鱼采纳,获得10
4秒前
科目三应助zzz采纳,获得10
4秒前
小小西瓜萝卜青菜完成签到,获得积分10
4秒前
思源应助虚幻采枫采纳,获得10
5秒前
5秒前
不安的可乐完成签到,获得积分10
5秒前
6秒前
nano完成签到 ,获得积分10
6秒前
da完成签到,获得积分10
6秒前
科研通AI2S应助啊啊啊啊采纳,获得10
7秒前
cyndi发布了新的文献求助20
7秒前
8秒前
852应助小小西瓜萝卜青菜采纳,获得10
10秒前
sci完成签到,获得积分10
11秒前
醉熏的鑫发布了新的文献求助10
12秒前
Nizarn发布了新的文献求助10
12秒前
13秒前
13秒前
乐呵呵完成签到,获得积分10
13秒前
13秒前
忧心的惜天完成签到 ,获得积分10
13秒前
77完成签到,获得积分10
14秒前
yz发布了新的文献求助10
14秒前
周周南完成签到 ,获得积分10
17秒前
17秒前
zz完成签到,获得积分10
17秒前
自由老头应助cyndi采纳,获得20
18秒前
努力做实验完成签到 ,获得积分10
19秒前
wf发布了新的文献求助10
19秒前
研友_ngkEgn完成签到,获得积分10
19秒前
代丽娟完成签到,获得积分10
19秒前
21秒前
快来下载文献完成签到,获得积分10
21秒前
苹果山芙完成签到,获得积分10
22秒前
煎饼狗子发布了新的文献求助10
22秒前
r41r32完成签到 ,获得积分10
23秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds第二卷 1200
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038657
求助须知:如何正确求助?哪些是违规求助? 3576306
关于积分的说明 11375198
捐赠科研通 3306108
什么是DOI,文献DOI怎么找? 1819379
邀请新用户注册赠送积分活动 892698
科研通“疑难数据库(出版商)”最低求助积分说明 815066