Sampling-attention deep learning network with transfer learning for large-scale urban point cloud semantic segmentation

计算机科学 增采样 学习迁移 分割 点云 深度学习 人工智能 采样(信号处理) 协议(科学) 云计算 特征(语言学) 机器学习 数据挖掘 计算机视觉 图像(数学) 操作系统 滤波器(信号处理) 哲学 病理 医学 语言学 替代医学
作者
Yunxiang Zhou,Ankang Ji,Limao Zhang,Xiaolong Xue
出处
期刊:Engineering Applications of Artificial Intelligence [Elsevier BV]
卷期号:117: 105554-105554 被引量:19
标识
DOI:10.1016/j.engappai.2022.105554
摘要

Targeting the development of smart cities to facilitate the significant analysis of large-scale urban for construction and update. This research develops a new method named transfer learning-based sampling-attention network (TSANet) to act on 3D urban point clouds for semantic segmentation. The main contributions of this research are a segmentation model and a transfer learning protocol, where the segmentation model adopts the point downsampling–upsampling structure for time efficiency, the embedding method and an attention mechanism for point cloud feature processing, and the transfer learning protocol is employed to reduce the data requirements and labeling efforts by using prior knowledge for practical application. In addition, a focal loss is designed to assist the model for feature extraction and learning with handling data imbalance. To demonstrate the efficiency and effectiveness of the developed method, a realistic point cloud dataset of Cambridge and Birmingham cities is utilized as a case study. The results demonstrate that (1) the developed method has promising performance with overall accuracy (OA) of 0.9133 and Mean Intersection over Union (MIoU) of 0.5588; (2) the proposed transfer learning protocol contributes to the core model performance by fully combining accuracy and time efficiency, offering a 74.91% improvement in time efficiency; (3) the developed TSANet outperforms other state-of-the-art models, such as PointNet++ and DGCNN, by comparing the accuracy and time efficiency. Overall, the method developed in this research is capable of great potential as a practical application tool by presenting accurate, effective, and efficient results for semantic segmentation of large-scale 3D urban point clouds.
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
清爽尔安发布了新的文献求助10
1秒前
2秒前
丫丫发布了新的文献求助10
3秒前
huangyikun发布了新的文献求助10
3秒前
叔铭完成签到,获得积分10
4秒前
大个应助ZONG采纳,获得10
6秒前
6秒前
Ma完成签到,获得积分10
7秒前
孙燕应助猪猪hero采纳,获得10
7秒前
会发光的小灰灰完成签到,获得积分10
7秒前
板凳儿cc发布了新的文献求助10
7秒前
黑色天使发布了新的文献求助10
8秒前
8秒前
激情的代曼完成签到,获得积分10
8秒前
9秒前
12秒前
缓慢手机完成签到,获得积分10
12秒前
丫丫完成签到,获得积分10
12秒前
13秒前
时尚俊驰发布了新的文献求助10
13秒前
耍酷的冷雪完成签到,获得积分10
14秒前
wanci应助baonali采纳,获得10
16秒前
ZONG发布了新的文献求助10
17秒前
wuy发布了新的文献求助10
17秒前
123完成签到,获得积分10
18秒前
19秒前
saisyo发布了新的文献求助10
20秒前
隐形曼青应助炸胡娃娃采纳,获得30
21秒前
坦率白萱应助wwl采纳,获得10
21秒前
NexusExplorer应助小晓采纳,获得10
21秒前
22秒前
22秒前
123发布了新的文献求助10
23秒前
搞怪的紫易完成签到,获得积分10
23秒前
WYQ完成签到,获得积分10
23秒前
幸福大白发布了新的文献求助10
25秒前
玩命的凝天完成签到,获得积分10
25秒前
量子星尘发布了新的文献求助10
25秒前
zxq1996完成签到 ,获得积分10
25秒前
所所应助时尚俊驰采纳,获得10
26秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
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 3989444
求助须知:如何正确求助?哪些是违规求助? 3531531
关于积分的说明 11254250
捐赠科研通 3270191
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174