☆ 4.7 Article

Dual-Task Network for Road Extraction From High-Resolution Remote Sensing Images

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Remote Sensing

A comparative study of loss functions for road segmentation in remotely sensed road datasets

Hongzhang Xu et al.

Summary: This study compares the performance differences of 12 commonly used loss functions in road segmentation tasks in remote sensing imagery. It is found that the region-based loss function type generally performs better than the distribution-based one in terms of F1, IoU, and road segmentation maps, while the compound loss function type is comparable to the region-based one. This paper aims to provide suggestions for choosing the loss function that best suits the purposes of road segmentation-related studies.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2023)

添加到收藏夹

Article Geochemistry & Geophysics

NL-LinkNet: Toward Lighter But More Accurate Road Extraction With Nonlocal Operations

Yooseung Wang et al.

Summary: In this letter, an efficient nonlocal LinkNet model is proposed for road extraction, achieving more accurate results compared to state-of-the-art ensemble models in the DeepGlobe Challenge. The NL-LinkNet model outperforms the D-LinkNet model in terms of parameters and training time.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Split Depth-Wise Separable Graph-Convolution Network for Road Extraction in Complex Environments From High-Resolution Remote-Sensing Images

Gaodian Zhou et al.

Summary: The article introduces a method to improve the accuracy of road extraction from high-resolution remote-sensing images using a split depth-wise separable graph convolutional network. The results of the experiment show that this method performs better in extracting covered and tiny roads.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Scribble-Based Weakly Supervised Deep Learning for Road Surface Extraction From Remote Sensing Images

Yao Wei et al.

Summary: The article introduces a scribble-based weakly supervised road surface extraction method named ScRoadExtractor, achieving better performance compared to classic methods through scribble learning and road label propagation algorithm.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Geography, Physical

Large-scale road extraction from high-resolution remote sensing images based on a weakly-supervised structural and orientational consistency constraint network

Mingting Zhou et al.

Summary: In this paper, a weakly-supervised road segmentation network based on structural and orientational consistency (SOC-RoadNet) is proposed to learn road surface from open-source road maps. It eliminates the need for densely labeled road samples and utilizes scribble-labels on road maps for training. The proposed SOC-RoadNet achieves high-quality large-scale road extraction by directly learning road surface features and introducing a structural consistency loss function and an orientation learning module to improve road boundary accuracy and road integrity.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

GMR-Net: Road-Extraction Network Based on Fusion of Local and Global Information

Zixuan Zhang et al.

Summary: This paper proposes a new road extraction network that improves the accuracy and generalization ability of road extraction using multiple methods and mechanisms. The experiments demonstrate that the proposed method performs well in terms of F1 scores on two datasets.

REMOTE SENSING (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Cascaded Multi-Task Road Extraction Network for Road Surface, Centerline, and Edge Extraction

Xiaoyan Lu et al.

Summary: This article proposes a cascaded multitask (CasMT) road extraction framework for simultaneously extracting the road surface, centerline, and edges to improve road connectivity. The framework employs topology-aware learning and hard example mining loss to enhance road completeness. Experimental results show that the proposed framework outperforms the current state-of-the-art method in road extraction.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Remote Sensing

GA-Net: A geometry prior assisted neural network for road extraction

Xin Chen et al.

Summary: This paper proposes a novel road extraction convolutional neural network that enhances road connectivity by incorporating road boundary details and road junction information. Experimental results demonstrate that the model outperforms some state-of-the-art algorithms on different datasets.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2022)

添加到收藏夹

Article Remote Sensing

Road extraction in remote sensing data: A survey

Ziyi Chen et al.

Summary: This paper provides a comprehensive survey and analysis of road extraction methods using 2D and 3D data. The authors classify the literature and present the research findings from the past decade. In addition to methodologies, the paper also reviews the aspects of data and discusses future challenges and trends.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

DA-Net: Dual Branch Transformer and Adaptive Strip Upsampling for Retinal Vessels Segmentation

Changwei Wang et al.

Summary: The morphology of retinal vessels is crucial for the diagnosis of eye-related diseases. However, current segmentation methods have limitations. In order to make use of both local and global information and adapt to the unique distribution of retinal vessels, we propose a new network model called DA-Net.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT II (2022)

添加到收藏夹

Article Geochemistry & Geophysics

DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images

Ying Wang et al.

Summary: This article proposes an enhanced deep neural network model, DDU-Net, for extracting roads from high-resolution remote sensing images. By adding a small decoder and introducing dilated convolution attention module, the model achieves good reliability and accuracy for small-sized road extraction, and can be used as a portable module to enhance road detection performance in other U-Net-like models.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

Doruk Oner et al.

Summary: The paper proposes a novel connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, such as roads and irrigation canals, from aerial images. The loss function aims to express the connectivity of roads or canals in terms of disconnections, and prevents unwanted connections between background regions by penalizing unwarranted disconnections.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Res2Net: A New Multi-Scale Backbone Architecture

Shang-Hua Gao et al.

Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Geochemistry & Geophysics

DiResNet: Direction-Aware Residual Network for Road Extraction in VHR Remote Sensing Images

Lei Ding et al.

Summary: The article introduces a direction-aware residual network (DiResNet) that improves the accuracy and connectivity of road binary segmentation through three main contributions. Experiments on two benchmark datasets confirm the effectiveness of the proposed designs, and comparative analysis shows the method's advantages in terms of accuracy and F1-score.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Review Geography, Physical

A Global Context-aware and Batch-independent Network for road extraction from VHR satellite imagery

Qiqi Zhu et al.

Summary: Road extraction in satellite imagery is crucial for governments to plan infrastructure development and mobilize relief efforts worldwide. Recent advancements in deep learning have shown dominance in accurately labeling road pixels from high-resolution satellite images.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery

Jie Mei et al.

Summary: This paper proposes a novel connectivity attention network (CoANet) to efficiently extract road information from satellite imagery by leveraging road shapes and connections in graph networks. By utilizing the strip convolution module (SCM) and connectivity attention module (CoA) to capture long-range information and address occlusions in road regions, superior experimental results are achieved.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Focal Loss for Dense Object Detection

Tsung-Yi Lin et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

添加到收藏夹

Article Geography, Physical

BT-RoadNet: A boundary and topologically-aware neural network for road extraction from high-resolution remote sensing imagery

Mingting Zhou et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2020)

添加到收藏夹

Article Geochemistry & Geophysics

Simultaneous Road Surface and Centerline Extraction From Large-Scale Remote Sensing Images Using CNN-Based Segmentation and Tracing

Yao Wei et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2020)

添加到收藏夹

Article Geochemistry & Geophysics

Topology-Enhanced Urban Road Extraction via a Geographic Feature-Enhanced Network

Xingang Li et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2020)

添加到收藏夹

Article Geochemistry & Geophysics

RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes from High-Resolution Remotely Sensed Images

Yahui Liu et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

添加到收藏夹

Article Environmental Sciences

Road Extraction by Using Atrous Spatial Pyramid Pooling Integrated Encoder-Decoder Network and Structural Similarity Loss

Hao He et al.

REMOTE SENSING (2019)

添加到收藏夹

Article Computer Science, Information Systems

Fusing Taxi Trajectories and RS Images to Build Road Map via DCNN

Yali Li et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Geochemistry & Geophysics

Road Extraction by Deep Residual U-Net

Zhengxin Zhang et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

添加到收藏夹

Proceedings Paper Energy & Fuels

Space Charge Analysis of Polyethylene with Chemical Defects Based on Density Function Theory

Tao Lin et al.

2018 IEEE INTERNATIONAL CONFERENCE ON HIGH VOLTAGE ENGINEERING AND APPLICATION (ICHVE) (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Holistically-Nested Edge Detection

Saining Xie et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2017)

添加到收藏夹

Article Environmental Sciences

Semi Automatic Road Extraction by Fusion of High Resolution Optical and Radar Images

Elahe Khesali et al.

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING (2016)

添加到收藏夹

Article Environmental Sciences

Road Network Extraction from VHR Satellite Images Using Context Aware Object Feature Integration and Tensor Voting

Mehdi Maboudi et al.

REMOTE SENSING (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

An Object-Based Method for Road Network Extraction in VHR Satellite Images

Zelang Miao et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2015)

添加到收藏夹

Article Geography, Physical

Water flow based geometric active deformable model for road network

Leninisha Shanmugam et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2015)

添加到收藏夹

Article Environmental Sciences

Road Detection from Optical Remote Sensing Imagery Using Circular Projection Matching and Tracking Strategy

Gang Fu et al.

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING (2013)

添加到收藏夹

Article Engineering, Electrical & Electronic

Application of a Fast Linear Feature Detector to Road Extraction From Remotely Sensed Imagery

Yuanzheng Shao et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2011)

添加到收藏夹

Article Biochemical Research Methods

Weighted rank aggregation of cluster validation measures: a Monte Carlo cross-entropy approach

Vasyl Pihur et al.

BIOINFORMATICS (2007)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.