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
虎啊虎啊发布了新的文献求助10
刚刚
王佳亮关注了科研通微信公众号
1秒前
优雅冷霜完成签到 ,获得积分10
1秒前
Manzia完成签到,获得积分10
2秒前
2秒前
2秒前
jiang发布了新的文献求助10
6秒前
7秒前
10秒前
11秒前
xuxu完成签到,获得积分20
12秒前
下一秒完成签到,获得积分10
12秒前
jiang完成签到,获得积分20
12秒前
soldatJiang发布了新的文献求助10
13秒前
泥嚎完成签到,获得积分10
17秒前
xuxu发布了新的文献求助10
17秒前
伊丽娜完成签到,获得积分20
23秒前
汉堡包应助ylq采纳,获得10
24秒前
26秒前
文城完成签到 ,获得积分10
26秒前
量子星尘发布了新的文献求助30
27秒前
橘笙发布了新的文献求助10
31秒前
31秒前
Akim应助瘦瘦天奇采纳,获得10
32秒前
充电宝应助南冥采纳,获得10
33秒前
SciGPT应助晨曦采纳,获得10
33秒前
34秒前
35秒前
37秒前
38秒前
ylq发布了新的文献求助10
38秒前
diraczh完成签到,获得积分10
39秒前
精神是块骨头完成签到,获得积分10
42秒前
肖肖发布了新的文献求助10
43秒前
MWY关闭了MWY文献求助
43秒前
duhdhd完成签到,获得积分10
44秒前
卓矢完成签到 ,获得积分10
46秒前
49秒前
科目三应助越啊采纳,获得10
50秒前
lixia完成签到 ,获得积分10
50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 3989069
求助须知:如何正确求助?哪些是违规求助? 3531351
关于积分的说明 11253589
捐赠科研通 3269939
什么是DOI,文献DOI怎么找? 1804851
邀请新用户注册赠送积分活动 882074
科研通“疑难数据库(出版商)”最低求助积分说明 809073