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
Xinxxx完成签到,获得积分10
刚刚
感性的初兰完成签到,获得积分10
刚刚
yydragen应助房天川采纳,获得30
1秒前
1秒前
zzz完成签到,获得积分10
2秒前
2秒前
2秒前
rational完成签到,获得积分10
3秒前
好好学习完成签到,获得积分10
3秒前
cherry完成签到,获得积分10
3秒前
加德士完成签到,获得积分10
3秒前
4秒前
xiang完成签到 ,获得积分10
4秒前
夜捕白日梦完成签到,获得积分10
4秒前
科研废柴完成签到,获得积分10
5秒前
啦啦啦完成签到,获得积分10
5秒前
热心的冷松完成签到,获得积分10
5秒前
研友_ZG4ml8发布了新的文献求助10
5秒前
lili完成签到 ,获得积分10
6秒前
STAN完成签到,获得积分20
6秒前
忧郁豆芽完成签到,获得积分20
6秒前
天边发布了新的文献求助10
6秒前
书芹发布了新的文献求助10
8秒前
jason完成签到,获得积分10
8秒前
纷纷完成签到 ,获得积分10
8秒前
8秒前
9秒前
自由的中蓝完成签到 ,获得积分10
9秒前
竞燃查无此人完成签到,获得积分0
9秒前
9秒前
9秒前
danny完成签到,获得积分20
9秒前
SGLY完成签到,获得积分10
9秒前
熊猫盖浇饭完成签到,获得积分10
10秒前
10秒前
忧郁豆芽发布了新的文献求助20
10秒前
小李完成签到,获得积分10
11秒前
嘉星糖完成签到,获得积分10
11秒前
yanziwu94完成签到,获得积分10
11秒前
vc小星完成签到,获得积分10
11秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 1000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3976858
求助须知:如何正确求助?哪些是违规求助? 3521046
关于积分的说明 11205737
捐赠科研通 3257901
什么是DOI,文献DOI怎么找? 1798911
邀请新用户注册赠送积分活动 877997
科研通“疑难数据库(出版商)”最低求助积分说明 806723