已入深夜,您辛苦了!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!祝你早点完成任务,早点休息,好梦!

DDCTNet: A Deformable and Dynamic Cross Transformer Network for Road Extraction from High Resolution Remote Sensing Images

遥感 计算机科学 高分辨率 变压器 图像分辨率 人工智能 计算机视觉 地质学 工程类 电压 电气工程
作者
Lipeng Gao,Yiqing Zhou,Jiangtao Tian,Wenjing Cai
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:1
标识
DOI:10.1109/tgrs.2024.3404044
摘要

Influenced by the concepts of deep learning, extracting roads from high-resolution remote sensing scenes has gained significant attention. However, there are still limitations in both metrics and practical application scenarios. To address these limitations, we proposed a deformable and dynamic cross-transformer network (DDCTNet), introducing three key innovations. Firstly, we employed a deformable and dynamic cross-transformer (DDCT) attention module to enhance the recovery of data and structural information during the feature map upsampling by providing rich semantic information of encoding stage to decoding stage from spatial and channel dimensions, respectively, which improved the quality of upsampling while preserving the inherent characteristics of the road. Secondly, we introduced a cross-scale strip-pooling axial attention (CSSA) between discontinuous encoding stages to alleviate the information loss caused by down-sampling and highlight the linear characteristic of roads by leveraging rich semantic information from previous stage, which not only considers road linear features in complex scenes but also reduces computational complexity. Finally, we designed an auxiliary head (AuxHead) by fusing the outputs from the latter three decoding modules to enhance the model's generalization performance and convergence speed. Extensive experiments were conducted on three benchmark datasets. We also compared our DDCTNet with other classic road extraction models. The results show a noticeable improvement of 1%-5% across various evaluation metrics in three datasets. Additionally, the visualized results demonstrate that the proposed DDCTNet provides more accurate representations of real road scenes including distinguishing regions with high foreground-background similarity, addressing road occlusion, etc.
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
2秒前
哲别发布了新的文献求助10
3秒前
人间烟火发布了新的文献求助10
4秒前
星光熠熠完成签到 ,获得积分20
6秒前
6秒前
传奇3应助Arui采纳,获得10
8秒前
www发布了新的文献求助10
8秒前
害羞耷完成签到 ,获得积分10
9秒前
9秒前
CipherSage应助哲别采纳,获得10
10秒前
情怀应助赫绮琴采纳,获得10
11秒前
人间烟火完成签到,获得积分10
13秒前
19秒前
一直向前发布了新的文献求助10
20秒前
20秒前
21秒前
Arui发布了新的文献求助10
24秒前
24秒前
帅气寒香完成签到 ,获得积分10
25秒前
炙热冰夏发布了新的文献求助10
25秒前
26秒前
方法完成签到,获得积分10
28秒前
28秒前
蓝天白云发布了新的文献求助10
29秒前
Ade完成签到,获得积分10
29秒前
Grandir发布了新的文献求助20
30秒前
方法发布了新的文献求助10
31秒前
32秒前
32秒前
凤梨发布了新的文献求助10
33秒前
jasonjiang完成签到 ,获得积分0
33秒前
迷你的夏菡完成签到 ,获得积分10
34秒前
平常书兰发布了新的文献求助20
34秒前
炙热冰夏完成签到,获得积分10
37秒前
飞舞伤寒发布了新的文献求助10
37秒前
37秒前
小辣里发布了新的文献求助10
38秒前
40秒前
星辰大海应助科研通管家采纳,获得10
41秒前
Ava应助科研通管家采纳,获得10
41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
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
Aktuelle Entwicklungen in der linguistischen Forschung 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 3989918
求助须知:如何正确求助?哪些是违规求助? 3532013
关于积分的说明 11255831
捐赠科研通 3270829
什么是DOI,文献DOI怎么找? 1805053
邀请新用户注册赠送积分活动 882233
科研通“疑难数据库(出版商)”最低求助积分说明 809216