成果归属机构：

地球科学与资源学院

作者：

Yu, Zhengbo ; Chen, Zhe ; Xiao, Keyan ; Lei, Xiangqi ; Tang, Rui ; He, Qiaoran ; Sun, Zhongchang ; Guo, Huadong

单位：

China Univ Geosci Beijing, Sch Earth Sci & Resources, Beijing, Peoples R China;Chinese Acad Geol Sci, Inst Mineral Resources, MNR Key Lab Metallogeny & Mineral Assessment, Beijing 100037, Peoples R China;Chengdu Univ Technol, Coll Math & Phys, Chengdu 610059, Peoples R China;Univ Padua, Dept Land Environm Agr & Forestry, I-35020 Legnaro, PD, Italy;Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100094, Peoples R China;Chengdu Univ Technol, Coll Earth & Planetary Sci, Chengdu, Peoples R China;Georgia Inst Technol, Coll Comp, Atlanta, GA USA;Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing, Peoples R China

摘要：

Road extraction is crucial for navigation, autonomous driving, and smart city development. With advancements in remote sensing and deep learning, the extraction of road information from remote sensing images has emerged as a prevalent research area. Nevertheless, the complexity of roads and image characteristics pose various challenges. To address this issu e, we propose SegRoadv2, a road extraction algorithm based on SegRoad. SegRoadv2 employs a transformer block with a deformable self-attention (DSA) module and a CNN structure with a new groupable deformable convolution (GroupDCN). Additionally, the novel re-parameterized strip convolutions in the decoder and a pixel connectivity structure improve segmentation connectivity. Tested on the DeepGlobe, Massachusetts, and CHN6-CUG datasets, SegRoadv2 exhibits a novel, state-of-the-art performance, achieving an IoU of 69.88% on DeepGlobe and excellent results on the other datasets. These findings highlight the potential of this algorithm for urban development applications.

基金：

Innovative Research Program of the International Research Center of Big Data for Sustainable Development Goals [CBAS2022IRP04]; Joint HKU-CAS Laboratory for iEarth [313GJHZ2022074MI, E4F3050300]

语种：

英文

DOI：

10.1080/17538947.2025.2480267

来源：

INTERNATIONAL JOURNAL OF DIGITAL EARTH,2025(1):.

出版日期：

2025-12-31

提交日期：

2025-04-18

引用参考：

Yu, Zhengbo; Chen, Zhe; Xiao, Keyan; Lei, Xiangqi; Tang, Rui; He, Qiaoran; Sun, Zhongchang; Guo, Huadong. SegRoadv2: a hybrid deformable self-attention and convolutional network for road extraction with connectivity structure[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2025(1):.