Road Extraction Method Research Articles

Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network

With the development of agricultural and rural modernization, the informatization of rural roads has been an inevitable requirement for promoting rural revitalization. To date, however, the vast majority of road extraction methods mainly focus on urban areas and rely on very high-resolution satellite or aerial images, whose costs are not yet affordable for large-scale rural areas. Therefore, a deep learning (DL)-based super-resolution mapping (SRM) method has been considered to relieve this dilemma by using freely available Sentinel-2 imagery. However, few DL-based SRM methods are suitable due to these methods only relying on the spectral features derived from remote sensing images, which is insufficient for the complex rural road extraction task. To solve this problem, this paper proposes a spatial relationship-informed super-resolution mapping network (SRSNet) for extracting roads in rural areas which aims to generate 2.5 m fine-scale rural road maps from 10 m Sentinel-2 images. Based on the common sense that rural roads often lead to rural settlements, the method adopts a feature enhancement module to enhance the capture of road features by incorporating the relative position relation between roads and rural settlements into the model. Experimental results show that the SRSNet can effectively extract road information, with significantly better results for elongated rural roads. The intersection over union (IoU) of the mapping results is 68.9%, which is 4.7% higher than that of the method without fusing settlement features. The extracted roads show more details in the areas with strong spatial relationships between the settlements and roads.

From local context-aware to non-local: A road extraction network via guidance of multi-spectral image

The use of artificial intelligence has led to an increase in road extraction projects from satellite images through deep learning. However, multi-spectral images (MSI) have been largely overlooked in road extraction algorithms due to their lower resolution compared to panchromatic or fused images. Additionally, deep learning faces the challenge of image content reasoning from distant contexts in data rule mining. To address these issues, we propose a new method for road extraction called the MSI-guided Segmentation Network, which utilizes all the data from the GF2 satellite to achieve optimal results. This study highlights the advantages of using MSI with low-resolution for obtaining deeper semantic information in a faster manner, while high-resolution fused images are better suited for extracting precise characteristics. The proposed method includes two sections: (1) a local symmetry feature fusion to enhance the network's local context-awareness for shallow details, and (2) a global asymmetric semantic fusion to improve the network's capability to comprehend the whole scene for deep semantic information. Moreover,to evaluate the robustness and generalization of this method, we have provided a GF2 Full-band China Road Dataset. The codes and datasets will be made public on https://github.com/Dudujia160918/MSNet.

DPSDA-Net: Dual-Path Convolutional Neural Network with Strip Dilated Attention Module for Road Extraction from High-Resolution Remote Sensing Images

Roads extracted from high-resolution remote sensing images are widely used in many fields, such as autonomous driving, road planning, disaster relief, etc. However, road extraction from high-resolution remote sensing images has certain deficiencies in connectivity and completeness due to obstruction by surrounding ground objects, the influence of similar targets, and the slender structure of roads themselves. To address this issue, we propose a novel dual-path convolutional neural network with a strip dilated attention module, named DPSDA-Net, which adopts a U-shaped encoder–decoder structure, combining the powerful advantages of attention mechanism, dilated convolution, and strip convolution. The encoder utilizes ResNet50 as its basic architecture. A strip position attention mechanism is added between each residual block to strengthen the coherent semantic information of a road. A long-distance shortcut connection operation is introduced to preserve the spatial information characteristics of the original image during the downsampling process. At the same time, a pyramid dilated module with a strip convolution and attention mechanism is constructed between the encoder and decoder to enhance the network feature extraction ability and multi-scale extraction of road feature information, expand the model’s receptive field, and pay more attention to the global spatial semantic and connectivity information. To verify the reliability of the proposed model, road extraction was carried out on the Massachusetts dataset and the LRSNY dataset. The experimental results show that, compared with other typical road extraction methods, the proposed model achieved a higher F1 score and IOU. The DPSDA-Net model can comprehensively characterize the structural features of roads, extract roads more accurately, retain road details, and improve the connectivity and integrity of road extraction in remote sensing images.

MS-AGAN: Road Extraction via Multi-Scale Information Fusion and Asymmetric Generative Adversarial Networks from High-Resolution Remote Sensing Images under Complex Backgrounds

Extracting roads from remote sensing images is of significant importance for automatic road network updating, urban planning, and construction. However, various factors in complex scenes (e.g., high vegetation coverage occlusions) may lead to fragmentation in the extracted road networks and also affect the robustness of road extraction methods. This study proposes a multi-scale road extraction method with asymmetric generative adversarial learning (MS-AGAN). First, we design an asymmetric GAN with a multi-scale feature encoder to better utilize the context information in high-resolution remote sensing images (HRSIs). Atrous spatial pyramid pooling (ASPP) and feature fusion are integrated into the asymmetric encoder–decoder structure to avoid feature redundancy caused by multi-level cascading operations and enhance the generator network’s ability to extract fine-grained road information at the pixel level. Second, to maintain road connectivity, topologic features are considered in the pixel segmentation process. A linear structural similarity loss (LSSIM) is introduced into the loss function of MS-AGAN, which guides MS-AGAN to generate more accurate segmentation results. Finally, to fairly evaluate the performance of deep models under complex backgrounds, the Bayesian error rate (BER) is introduced into the field of road extraction for the first time. Experiments are conducted via Gaofen-2 (GF-2) high-resolution remote sensing images with high vegetation coverage in the Daxing District of Beijing, China, and the public DeepGlobe dataset. The performance of MS-AGAN is compared with a list of advanced models, including RCFSNet, CoANet, UNet, DeepLabV3+, and DiResNet. The final results show that (1) with respect to road extraction performance, the Recall, F1, and IoU values of MS-AGAN on the Daxing dataset are 2.17%, 0.04%, and 2.63% higher than the baselines. On DeepGlobe, the Recall, F1, and IoU of MS-AGAN improve by 1.12%, 0.42%, and 0.25%, respectively. (2) On road connectivity, the Conn index of MS-AGAN from the Daxing dataset is 46.39%, with an improvement of 0.62% over the baselines, and the Conn index of MS-AGAN on DeepGlobe is 70.08%, holding an improvement of 1.73% over CoANet. The quantitative and qualitative analyses both demonstrate the superiority of MS-AGAN in preserving road connectivity. (3) In particular, the BER of MS-AGAN is 20.86% over the Daxing dataset with a 0.22% decrease compared to the best baselines and 11.77% on DeepGlobe with a 0.85% decrease compared to the best baselines. The proposed MS-AGAN provides an efficient, cost-effective, and reliable method for the dynamic updating of road networks via HRSIs.

Updating forest road networks using single photon LiDAR in northern Forest environments

Abstract Knowledge about the condition and location of forest roads is important for forest management. Coupling accurate forest road information with planning and conservation strategies supports forest resource management. In Canada, spatial data of forestry road networks are available provincially; however, they lack spatial accuracy, and up-to-date information on key attributes such as road width is missing. In this study, we apply a novel approach to update forest road networks and characterize road conditions in Ontario’s Boreal and Great Lakes—St. Lawrence (GLSL) Forest regions. We use airborne laser scanning (ALS), to facilitate the identification of forest roads across densely forested landscapes. We categorized roads into four classes based on driveable width, edge vegetation, as well as surface and edge degradation as derived from high-density Single Photon LiDAR (SPL) data. Using a novel road extraction method, we produced a road probability raster and map road centerlines. We validated road location and attribute information using Global Navigation Satellite System (GNSS) ground truth data in two Ontario forest management units, in the boreal forest and the GLSL. Road segments in some regions have been altered to account for land cover changes, such as flooding or fallen trees. In other situations, the road path may deviate from the planned layout of the road, which is not always followed in the field. Our results highlight inaccuracies in the existing road networks, with 30 per cent of ‘Full access’ roads and 29 per cent of ‘Partial access’ roads being undriveable by standard vehicles and 45 per cent of ‘Status unknown’ roads, which make up 48 per cent of the pre-existing network, being driveable by standard vehicles. Results show that the average positional accuracy of updated road centerlines is 0.4 m, and the average road width error is 2 m. The production of spatially accurate forest road networks and road attribute information is important for characterizing large road networks for which often minimal information is available.

MSFANet: Multiscale Fusion Attention Network for Road Segmentation of Multispectral Remote Sensing Data

With the development of deep learning and remote sensing technologies in recent years, many semantic segmentation methods based on convolutional neural networks (CNNs) have been applied to road extraction. However, previous deep learning-based road extraction methods primarily used RGB imagery as an input and did not take advantage of the spectral information contained in hyperspectral imagery. These methods can produce discontinuous outputs caused by objects with similar spectral signatures to roads. In addition, the images obtained from different Earth remote sensing sensors may have different spatial resolutions, enhancing the difficulty of the joint analysis. This work proposes the Multiscale Fusion Attention Network (MSFANet) to overcome these problems. Compared to traditional road extraction frameworks, the proposed MSFANet fuses information from different spectra at multiple scales. In MSFANet, multispectral remote sensing data is used as an additional input to the network, in addition to RGB remote sensing data, to obtain richer spectral information. The Cross-source Feature Fusion Module (CFFM) is used to calibrate and fuse spectral features at different scales, reducing the impact of noise and redundant features from different inputs. The Multiscale Semantic Aggregation Decoder (MSAD) fuses multiscale features and global context information from the upsampling process layer by layer, reducing information loss during the multiscale feature fusion. The proposed MSFANet network was applied to the SpaceNet dataset and self-annotated images from Chongzhou, a representative city in China. Our MSFANet performs better over the baseline HRNet by a large margin of +6.38 IoU and +5.11 F1-score on the SpaceNet dataset, +3.61 IoU and +2.32 F1-score on the self-annotated dataset (Chongzhou dataset). Moreover, the effectiveness of MSFANet was also proven by comparative experiments with other studies.

SemiRoadExNet: A semi-supervised network for road extraction from remote sensing imagery via adversarial learning

Road extraction from remote sensing imagery is a popular and frontier research focus, since road information plays an essential role in application fields, such as urban management, map updating and traffic planning. Deep learning based methods have shown their dominance on road extraction from remote sensing imagery. However, the performance of the existing road extraction methods relies heavily on a large amount of high-quality annotated training data, which is usually hard to obtain in practice. Current semi-supervised road extraction models can effectively reduce the dependency on the labeled data, nevertheless they cannot fully utilize the latent information of low-confidence pixels in pseudo-labels effectively. These pixels are usually a border between road and non-road area and of importance for the prediction accuracy of road extraction models. In order to address these issues, we proposed a novel semi-supervised road extraction network, named SemiRoadExNet. SemiRoadExNet is based on a Generative Adversarial Network (GAN), containing one generator with two discriminators. Firstly, both labeled and unlabeled images are put into the generator network for road extraction, and the outputs of the generator not only include road segmentation results but also the corresponding entropy maps. The entropy maps represent the confidence of prediction (road or non-road) for each pixel. Then, the two discriminators enforce the feature distributions keeping the consistency of road prediction maps and entropy maps between the labeled and unlabeled data. During the adversarial training, the generator is continuously regularized by exploiting the potential information from unlabeled data, thus the generalization capacity of the proposed model can be improved effectively. Compared to several state-of-the-art semi-supervised semantic segmentation methods, the proposed SemiRoadExNet achieves 0.96–5.38% IoU improvements on DeepGlobe Road Extraction, Massachusetts Roads and CHN6-CUG datasets respectively. The source code of d SemiRoadExNet is freely available at https://github.com/hchen118/SemiRoadExNet.

Performance analysis of rule-based classification and deep learning method for automatic road extraction

The need for accurate and up-to-date spatial data by decision-makers in public and private administrations is increasing gradually. In recent decades, in the management of disasters and smart cities, fast and accurate extraction of roads, especially in emergencies, is quite important in terms of transportation, logistics planning, and route determination. In this study, automatic road extraction analyses were carried out using the Unmanned Aerial Vehicle (UAV) data set, belonging to the Yildiz Technical University Davutpasa Campus road route. For this purpose, this paper presents a comparison between performance analysis of rule-based classification and U-Net deep learning method for solving automatic road extraction problems. Objects belonging to the road and road network were obtained with the rule-based classification method with overall accuracy of 95%, and with the deep learning method with an overall accuracy of 86%. On the other hand, the performance metrics including accuracy, recall, precision, and F1 score were utilized to evaluate the performance analysis of the two methods. These values were obtained from confusion matrices for 4 target classes consisting of road and road elements namely road, road line, sidewalk, and bicycle road. Finally, integration of classified image objects with ontology was realized. Ontology was developed by defining four target class results obtained as a result of the rule-based classification method, conceptual class definition and properties, rules, and axioms.

RoadFormer: Road Extraction Using a Swin Transformer Combined with a Spatial and Channel Separable Convolution

The accurate detection and extraction of roads using remote sensing technology are crucial to the development of the transportation industry and intelligent perception tasks. Recently, in view of the advantages of CNNs in feature extraction, its related road extraction methods have been proposed successively. However, due to the limitation of kernel size, they perform less effectively at capturing long-range information and global context, which are crucial for road targets distributed over long distances and highly structured. To deal with this problem, a novel model named RoadFormer with a Swin Transformer as the backbone is developed in this paper. Firstly, to extract long-range information effectively, a Swin Transformer multi-scale encoder is adopted in our model. Secondly, to enhance the feature representation capability of the model, we design an innovative bottleneck module, in which the spatial and channel separable convolution is employed to obtain fine-grained and globe features, and then a dilated block is connected after the spatial convolution module to capture more integrated road structures. Finally, a lightweight decoder consisting of transposed convolution and skip connection generates the final extraction results. Extensive experimental results confirm the advantages of RoadFormer on the Deepglobe and Massachusetts datasets. The comparative results of visualization and quantification demonstrate that our model outperforms comparable methods.

A Context-Aware Road Extraction Method for Remote Sensing Imagery Based on Transformer Network

A Context-Aware Road Extraction Method for Remote Sensing Imagery Based on Transformer Network

Satellite road extraction method based on RFDNet neural network

<abstract><p>The road network system is the core foundation of a city. Extracting road information from remote sensing images has become an important research direction in the current traffic information industry. The efficient residual factorized convolutional neural network (ERFNet) is a residual convolutional neural network with good application value in the field of biological information, but it has a weak effect on urban road network extraction. To solve this problem, we developed a road network extraction method for remote sensing images by using an improved ERFNet network. First, the design of the network structure is based on an ERFNet; we added the DoubleConv module and increased the number of dilated convolution operations to build the road network extraction model. Second, in the training process, the strategy of dynamically setting the learning rate is adopted and combined with batch normalization and dropout methods to avoid overfitting and enhance the generalization ability of the model. Finally, the morphological filtering method is used to eliminate the image noise, and the ultimate extraction result of the road network is obtained. The experimental results show that the method proposed in this paper has an average F1 score of 93.37% for five test images, which is superior to the ERFNet (91.31%) and U-net (87.34%). The average value of IoU is 77.35%, which is also better than ERFNet (71.08%) and U-net (65.64%).</p></abstract>

A Lightweight High-Resolution RS Image Road Extraction Method Combining Multi-Scale and Attention Mechanism

A Lightweight High-Resolution RS Image Road Extraction Method Combining Multi-Scale and Attention Mechanism

A Road Extraction Method of a High-Resolution Remote Sensing Image Based on Multi-Feature Fusion and the Attention Mechanism

A Road Extraction Method of a High-Resolution Remote Sensing Image Based on Multi-Feature Fusion and the Attention Mechanism

Research on Road Extraction Method Based on Sustainable Development Goals Satellite-1 Nighttime Light Data

Road information plays a fundamental role in many applications. However, at present, it is difficult to extract road information from the traditional nighttime light images in view of their low spatial and spectral resolutions. To fill the gap in high-resolution nighttime light (NTL) data, the Sustainable Development Goals Satellite-1(SDGSAT-1) developed by the Chinese Academy of Sciences (CAS) was successfully launched on 5 November 2021. With 40 m spatial resolution, NTL data acquired by the Glimmer Imager Usual (GIU) sensor on the SDGSAT-1 provide a new data source for road extraction. To evaluate the ability of SDGSAT-1 NTL data to extract road information, we proposed a new road extraction method named Band Operation and Marker-based Watershed Segmentation Algorithm (BO-MWSA). Comparing with support vector machine (SVM) and optimum threshold (OT) algorithms, the results showed that: (1) the F1 scores of the roads in the test area extracted by SVM, OT, and BO-MWSA were all over 70%, indicating that SDGSAT-1/GIU data could be used as a data source for road extraction. (2) The F1 score of road extraction by BO-MWSA is 84.65%, which is 11.02% and 9.43% higher than those of SVM and OT, respectively. In addition, the F1 scores of BO-MWSA road extraction in Beijing and Wuhan are both more than 84%, indicating that BO-MWSA is an effective method for road extraction using NTL imagery. (3) In road extraction experiments for Lhasa, Beijing, and Wuhan, the results showed that the greater the traffic flow was, the lower the accuracy of the extracted roads became. Therefore, BO-MWSA is an effective method for road extraction using SDGSAT-1 NTL data.

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

Road extraction from high-resolution remote-sensing images has high application values in various fields. However, such work is susceptible to the influence of the surrounding environment due to the diverse slenderness and complex connectivity of roads, leading to false judgment and omission during extraction. To solve this problem, a road-extraction network, the global attention multi-path dilated convolution gated refinement Network (GMR-Net), is proposed. The GMR-Net is facilitated by both local and global information. A residual module with an attention mechanism is first designed to obtain global and other aggregate information for each location’s features. Then, a multi-path dilated convolution (MDC) approach is used to extract road features at different scales, i.e., to achieve multi-scale road feature extraction. Finally, gated refinement units (GR) are proposed to filter out ambiguous features for the gradual refinement of details. Multiple road-extraction methods are compared in this study using the Deep-Globe and Massachusetts datasets. Experiments on these two datasets demonstrate that the proposed method achieves F1-scores of 87.38 and 85.70%, respectively, outperforming other approaches on segmentation accuracy and generalization ability.

Application of Road Extraction from High-Resolution Remote Sensing Images in Tourism Navigation and GIS

In order to quickly and accurately obtain and process road information and its damage information, to obtain better tourism navigation experience and accurate geographic information, this paper proposes a road extraction method based on high-resolution remote sensing images. Based on the known road width information and the analysis of the gray-scale characteristics of the road surface, the method takes the road center line and straight line in the image as the center line and then deduces the road edge line information, so as to extract the edge information. Then, through the image de redundancy information processing, the final obtained road width parameters are compared to verify the accuracy and reliability of the method. The experiment shows that the road information can be extracted accurately, and the extraction accuracy and efficiency have been significantly improved, reaching more than 90%, and can directly reflect the road edge line, median line, and width information. Conclusion. The road extraction method based on high-resolution remote sensing images can effectively and accurately extract road information, obtain better tourism navigation experience, and accurate geographic information.

Road extraction in remote sensing data: A survey

• This review covers a wider perspective in terms of both 2D remote sensing images and 3D point clouds. • This review provides a detail survey on 2D and 3D remote sensing datasets used for road extraction. • This review presents a detail analysis of challenges and future trends of road extraction from remote sensing data. Automated extraction of roads from remotely sensed data come forth various usages ranging from digital twins for smart cities, intelligent transportation, urban planning, autonomous driving, to emergency management. Many studies have focused on promoting the progress of methods for automated road extraction from aerial and satellite optical images, synthetic aperture radar (SAR) images, and LiDAR point clouds. In the past 10 years, no a more comprehensive survey on this topic could be found in literature. This paper attempts to provide a comprehensive survey on road extraction methods that use 2D earth observing images and 3D LiDAR point clouds. In this review, we first present a tree-structure that separate the literature into 2D and 3D. Then, further methodologies level classification is demonstrated both in 2D and 3D. In 2D and 3D, we introduce and analyze the literature published in the last ten years. Except for the methodologies, we also review the aspects of data commonly used. Finally, this paper explores the existing challenges and future trends.

A Low-Grade Road Extraction Method Using SDG-DenseNet Based on the Fusion of Optical and SAR Images at Decision Level

Low-grade roads have complex features such as geometry, reflection spectrum, and spatial topology in remotely sensing optical images due to the different materials of those roads and also because they are easily obscured by vegetation or buildings, which leads to the low accuracy of low-grade road extraction from remote sensing images. To address this problem, this paper proposes a novel deep learning network referred to as SDG-DenseNet as well as a fusion method of optical and Synthetic Aperture Radar (SAR) data on decision level to extract low-grade roads. On one hand, in order to enlarge the receptive field and ensemble multi-scale features in commonly used deep learning networks, we develop SDG-DenseNet in terms of three modules: stem block, D-Dense block, and GIRM module, in which the Stem block applies two consecutive small-sized convolution kernels instead of the large-sized convolution kernel, the D-Dense block applies three consecutive dilated convolutions after the initial Dense block, and Global Information Recovery Module (GIRM) combines the ideas of dilated convolution and attention mechanism. On the other hand, considering the penetrating capacity and oblique observation of SAR, which can obtain information from those low-grade roads obscured by vegetation or buildings in optical images, we integrate the extracted road result from SAR images into that from optical images at decision level to enhance the extraction accuracy. The experimental result shows that the proposed SDG-DenseNet attains higher IoU and F1 scores than other network models applied to low-grade road extraction from optical images. Furthermore, it verifies that the decision-level fusion of road binary maps from SAR and optical images can further significantly improve the F1, COR, and COM scores.

Weakly supervised road network extraction for remote sensing image based scribble annotation and adversarial learning

Performing accurate road extraction from remote sensing images has great practical importance. Nevertheless, the accuracy of segmentation can be seriously affected by complex and variable objective factors. Complex topological structures lead to discontinuity of extracted roads. State-of-the-art road extraction methods rely heavily on intensive annotation with high acquisition costs. In this work, we propose a scribble-based weakly supervised remote sensing road extraction network (WR2E), which can extract roads from remote sensing images based on scribble annotations. A road trimap generation algorithm is introduced to allow the propagation of semantic information for scribble annotations. The WR2E network contains two key modules, i.e., the road positioning module (RPM) and the oriented attention module (OAM). The road positioning module is designed to locate the initial position of the road from a global perspective, and the oriented attention module guides the propagation of high-level semantic information based on image affinity features. The proposed modal achieved the highest structural measure of 89.1%, the highest adaptive E measure of 92.0%, the highest weighted F measure of 88.6%, the highest mean absolute error of 3.6%, the highest IoU of 86.9%, and the highest F1-score of 93.7%, indicating the WR2E can accurately and effectively implement remote sensing image road extraction.

Survey of Road Extraction Methods in Remote Sensing Images Based on Deep Learning

Survey of Road Extraction Methods in Remote Sensing Images Based on Deep Learning