Semi-Automatic Method of Extracting Road Networks from High-Resolution Remote-Sensing Images

Article Geochemistry & Geophysics

SC-RoadDeepNet: A New Shape and Connectivity-Preserving Road Extraction Deep Learning-Based Network From Remote Sensing Data

Abolfazl Abdollahi et al.

Summary: The study introduces a deep learning architecture called SC-RoadDeepNet that improves road extraction by addressing discontinuity issues and preserving road shape and connectivity.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Semantic Segmentation and Edge Detection-Approach to Road Detection in Very High Resolution Satellite Images

Hamza Ghandorh et al.

Summary: Road detection technology plays a crucial role in various applications, and recent developments in high-resolution satellite images have utilized semantic segmentation for road detection. This paper proposes a novel approach that combines semantic segmentation and edge detection to generate sharp segmentation masks for accurate road edge detection. The experiments demonstrate the effectiveness of this method in accurately detecting road edges even in complex backgrounds.

REMOTE SENSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SDUNet: Road extraction via spatial enhanced and densely connected UNet

Mengxing Yang et al.

Summary: This paper proposes a novel network for road extraction called SDUNet, which aggregates multi-level features and global prior information of road networks to enhance feature learning about the road surface. It also introduces a structure preserving model to explore continuous clues in the spatial level. Experimental results demonstrate that the proposed method achieves state-of-the-art performance for road extraction, surpassing previous approaches.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Remote Sensing

Road marking extraction in UAV imagery using attentive capsule feature pyramid network

Haiyan Guan et al.

Summary: This article introduces an attentive capsule feature pyramid network (ACapsFPN) for accurately extracting road markings from high-resolution UAV images. The ACapsFPN integrates capsule representations and attention mechanisms into the feature pyramid network to improve extraction accuracy. The network is capable of extracting multi-level and multi-scale capsule features and emphasizes informative features through attention modules, providing high-quality and semantically-strong abstractions. Evaluations show the effectiveness and superiority of the ACapsFPN in extracting road markings under complex conditions.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2022)

添加到收藏夹

Article Multidisciplinary Sciences

RDD2020: An annotated image dataset for automatic road damage detection using deep learning

Deeksha Arya et al.

Summary: The RDD2020 dataset includes road images from India, Japan, and the Czech Republic, totaling 26,336, capturing 4 types of road damage, aiming to develop deep learning methods to automatically detect and classify road damage, which can be used for developing low-cost methods for monitoring road pavement conditions.

DATA IN BRIEF (2021)

添加到收藏夹

Article Remote Sensing

Exploring multiple crowdsourced data to learn deep convolutional neural networks for road extraction*

Panle Li et al.

Summary: In this study, a multi-map integration model (MMIM) is developed using multiple crowdsourced data, including OpenStreetMap (OSM), Zmap, and GPS, to improve the performance of DCNNs in road extraction tasks. The proposed method shows great performance in experiments, with smoother and more complete road extraction results.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2021)

添加到收藏夹

Article Environmental Sciences

Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes

Ziyang Wang et al.

Summary: This paper proposes a method for segmenting pole-like objects under geometric structural constraints and combines classification results at different scales to effectively extract pole-like objects from point clouds in road scenes, achieving high-precision classification and identification.

REMOTE SENSING (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

A review of deep learning methods for semantic segmentation of remote sensing imagery

Xiaohui Yuan et al.

Summary: This paper reviews the application of deep learning methods for semantic segmentation of remote sensing imagery and identifies challenges in handling non-traditional data as well as small datasets. Researchers are still facing difficulties in developing and evaluating new deep learning methods for remote sensing analysis.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Semi-Automatic Extraction of Rural Roads under the Constraint of Combined Geometric and Texture Features

Hai Tan et al.

Summary: This paper proposes a semi-automatic rural road extraction method constrained by a combination of geometric and texture features. By improving the accuracy of the initial road centre point, predicting tracking direction, and solving the problem of similarity between road and neighbourhood texture, the proposed method not only guarantees road extraction accuracy but also improves the degree of automation to a certain extent.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (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 Economics

Economic benefits of road widening: Discrepancy between outturn and forecast

David Metz

Summary: The cost-benefit analysis of road investments relies on models that predict travel time savings. A study on the M25 London orbital motorway found that traffic volumes increased significantly after widening but speed of travel did not. The forecast model underestimated traffic volumes and overestimated speeds, questioning the usefulness of traditional transport models and the value of increasing road capacity in certain scenarios.

TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE (2021)

添加到收藏夹

Article Environmental Sciences

An adaptive atmospheric correction algorithm for the effective adjacency effect correction of submeter-scale spatial resolution optical satellite images: Application to a WorldView-3 panchromatic image

Tao Wang et al.

Summary: The paper introduces an adaptive atmospheric correction algorithm based on Equivalent Average Background Reflectance (EABR), which can better represent the adjacency effect in SM satellite images. By adjusting the contribution factor of background pixels to the adjacency effect, the algorithm significantly improves image quality.

REMOTE SENSING OF ENVIRONMENT (2021)

添加到收藏夹

Article Computer Science, Information Systems

Automatic Road Extraction from Historical Maps Using Deep Learning Techniques: A Regional Case Study of Turkey in a German World War II Map

Burak Ekim et al.

Summary: Historical maps are scanned from various sources and automatic geographical feature extraction is conducted using deep learning to derive valuable spatial information. By digitizing and labeling different road types, the study achieved remarkable results with an overall accuracy of 98.73%.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

添加到收藏夹

Article Computer Science, Information Systems

Road Characteristics Detection Based on Joint Convolutional Neural Networks with Adaptive Squares

Chiao-Ling Kuo et al.

Summary: A novel simple deep-learning-based approach utilizing joint convolutional neural networks with adaptive squares and combination rules is proposed to detect road characteristics from roadmap tiles, improving detection accuracy. Experimental results demonstrate outstanding performance in reality, converting human-readable road characteristics information to machine-readable, benefiting many applications.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

添加到收藏夹

Article Geography

Challenging infrastructural orthodoxies: Political and economic geographies of a Himalayan road

Phurwa Gurung

Summary: The author challenges the orthodox narrative by arguing that road construction in Nepal's Karnali region does not solve food insecurity but actually increases vulnerability. They highlight unintended effects of roads, such as becoming key sites of electoral politics and vectors of new economic and labor geographies in the Himalayan borderlands. The paper contributes to the interdisciplinary literature on the relationship between road infrastructure and food security, emphasizing the contingent nature of infrastructural development.

GEOFORUM (2021)

添加到收藏夹

Article Remote Sensing

Trajectory analysis at intersections for traffic rule identification

Chenxi Wang et al.

Summary: This paper focuses on studying movement patterns at intersections with various regulation types using GPS trajectories. The research shows that different movement patterns are observed at intersections depending on the regulation type.

GEO-SPATIAL INFORMATION SCIENCE (2021)

添加到收藏夹

Article Remote Sensing

Feature detection and description for image matching: from hand-crafted design to deep learning

Lin Chen et al.

Summary: In feature based image matching, distinctive features in images are detected and represented by feature descriptors. Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate points. The evolution from hand-crafted feature descriptors, e.g. SIFT, to machine learning and deep learning based descriptors is discussed in detail, along with the advantages and challenges of different approaches.

GEO-SPATIAL INFORMATION SCIENCE (2021)

添加到收藏夹

Article Geochemistry & Geophysics