A Multimodal Feature Fusion Network for Building Extraction With Very High-Resolution Remote Sensing Image and LiDAR Data

激光雷达 遥感 特征提取 计算机科学 人工智能 特征(语言学) 卷积神经网络 传感器融合 计算机视觉 分割 模式识别(心理学) 数据挖掘 地质学 语言学 哲学
作者
Hui Luo,Xibo Feng,Bo Du,Yuxiang Zhang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-19 被引量:5
标识
DOI:10.1109/tgrs.2024.3389110
摘要

Building extraction from remote sensing images is extremely important for urban planning, land-cover change analysis, disaster monitoring and so on. With the growing diversity in building features, shape, and texture, coupled with frequent occurrences of shadowing and occlusion, the use of high-resolution remote sensing image (HRI) alone has limitations in building extraction. Therefore, feature fusion using multisource data has gradually become one of the most popular. However, the unique characteristics and noise issues make it difficult to achieve effective fusion and utilization. So it is very challenging to realize the full fusion of multisource data to achieve complementary advantages. In this paper, we propose an end-to-end multimodal feature fusion building extraction network based on segformer, which utilizes the fusion of HRI and LiDAR data to realize the building extraction. Firstly, we utilize the segformer encoder to break through the limitations of the traditional convolutional neural network with restricted receptive field so as to achieve effective feature extraction of complex building. In addition, we propose a cross-modal feature fusion (CMFF) method utilizing the self-attention mechanism to ensure the fusion of multisource data. In the decoder part, we propose a multi-scale up-sampling decoder (MSUD) strategy to achieve full fusion of multi-level features. As demonstrated by experiments on three datasets, our model shows better performance than several multisource building extraction and semantic segmentation models. The IoU for buildings on the three datasets reach 91.80%, 93.03%, and 84.59%. Subsequent ablation experiments further validate the effectiveness of each strategy.
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
1秒前
lichunlei完成签到,获得积分10
1秒前
shinn发布了新的文献求助30
2秒前
2秒前
卡卡西应助王者归来采纳,获得30
4秒前
义气小白菜完成签到 ,获得积分10
4秒前
5秒前
小羊完成签到,获得积分10
5秒前
123456发布了新的文献求助10
5秒前
羊咩咩完成签到 ,获得积分10
6秒前
婉婉完成签到,获得积分10
7秒前
zb发布了新的文献求助10
7秒前
Carrot发布了新的文献求助10
8秒前
风趣青槐完成签到,获得积分10
8秒前
刘洪均完成签到,获得积分10
8秒前
9秒前
冷艳芯发布了新的文献求助10
11秒前
我爱科研完成签到,获得积分10
13秒前
14秒前
碰碰完成签到,获得积分10
14秒前
14秒前
大个应助Aaron采纳,获得10
14秒前
Carrot完成签到,获得积分10
15秒前
英俊的铭应助宫冷雁采纳,获得10
15秒前
汉堡包应助zzy采纳,获得30
17秒前
17秒前
路灯下的小伙完成签到,获得积分10
17秒前
ning发布了新的文献求助10
17秒前
欢呼吐司发布了新的文献求助20
20秒前
十一发布了新的文献求助10
20秒前
大模型应助shinn采纳,获得50
20秒前
21秒前
23秒前
onlyan发布了新的文献求助10
24秒前
25秒前
26秒前
26秒前
28秒前
28秒前
ning完成签到,获得积分10
28秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
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
Effective Learning and Mental Wellbeing 300
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 3975250
求助须知:如何正确求助?哪些是违规求助? 3519625
关于积分的说明 11199055
捐赠科研通 3255962
什么是DOI,文献DOI怎么找? 1798001
邀请新用户注册赠送积分活动 877358
科研通“疑难数据库(出版商)”最低求助积分说明 806298