Road Extraction Research Articles

AU3-GAN: A Method for Extracting Roads from Historical Maps Based on an Attention Generative Adversarial Network

In recent years, the integration of deep learning technology based on convolutional neural networks with historical maps has made it possible to automatically extract roads from these maps, which is highly important for studying the evolution of transportation networks. However, the similarity between roads and other features (such as contours, water systems, and administrative boundaries) poses a significant challenge to the feature extraction capabilities of convolutional neural networks (CNN). Additionally, CNN require a large quantity of labelled data for training, which can be a complex issue for historical maps. To address these limitations, we propose a method for extracting roads from historical maps based on an attention generative adversarial network. This approach leverages the unique architecture and training methodology of the generative adversarial network to augment datasets by generating data that closely resembles real samples. Meanwhile, we introduce an attention mechanism to enhance UNet3 + and achieve accurate historical map road segmentation images. We validate our method using the Third Military Mapping Survey of Austria-Hungary and compare it with a typical U-shaped network. The experimental results show that our proposed method outperforms the direct use of the U-shaped network, achieving at least an 18.26% increase in F1 and a 7.62% increase in the MIoU, demonstrating its strong ability to extract roads from historical maps and provide a valuable reference for road extraction from other types of historical maps.

ROAD EXTRACTION FROM SATELLITE IMAGERY USING DEEP LEARNING VOL - I

Road extraction involves the intricate process of generating road maps automatically through deep learning algorithms. This task, particularly from satellite imagery, presents significant challenges due to various factors like occlusions, shadows, noise, and fluctuating illumination conditions. As a result, achieving complete and accurate road extraction is daunting without relying on manual annotations or imperfect road maps for guidance. One potential strategy to enhance road extraction accuracy is by incorporating partial road maps as supplementary data. These partial maps, sourced from platforms like OpenStreetMap or Google Maps, may not offer complete or pristine representations of roads but can still provide valuable additional information. By integrating these partial maps with satellite images, we can exploit their complementary nature to mitigate uncertainty in the extraction process. It's important to note that while road extraction may be relatively straightforward in some regions, such as rural areas, it becomes significantly more complex in urban or underdeveloped areas. These environments present unique challenges that require sophisticated algorithms and approaches to accurately extract roads from satellite imagery. Key Words: Road Extraction, Satellite Imagery, Google Maps, Open Street Map, Auxiliary information, Disaster management, Occlusions, Illumination, Annotation, Shadow.

Fusion of Multiple Basic Element Features for Airborne LiDAR in-house Surveys

When using airborne LiDAR point clouds for city modelling and road extraction, point cloud classification is a crucial step. There are numerous ways for classifying point clouds, but there are still issues like redundant multi-dimensional feature vector data and poor point cloud classification in intricate situations. A point cloud classification method built on the fusing of multikernel feature vectors is suggested as a solution to these issues. The technique employs random forest to classify point cloud data by merging colour information, and it extracts feature vectors based on point primitives and object primitives, respectively. In this study, a densely populated area was chosen as the study area. Light airborne LIDAR mounted on a delta wing was used to collect point cloud data at a low altitude (170 m) over a dense cross-course. The point cloud data were then combined, corrected, and enhanced with texture data, and the houses were vectorized on the point cloud. The accuracy of the results was then assessed. With a median inaccuracy of 4.8 cm and a point cloud data collection rate of 83.3%, using airborne LIDAR to measure house corners can significantly lighten the labour associated with external house corner measurements.This test extracts the texture information of point cloud data through the efficient processing of high-density point cloud data, providing a reference for the application of texture information of airborne LIDAR data and a clear understanding of its accuracy.

Extraction of Main Urban Roads from High Resolution Satellite Images by Machine Learning

Extraction of Main Urban Roads from High Resolution Satellite Images by Machine Learning

Automatic extraction and 3D modeling of real road scenes using UAV imagery and deep learning semantic segmentation

ABSTRACT The extraction of roads from UAV images is challenged by lighting, noise, occlusions, and similar non-road objects, making high-quality road extraction difficult. To addressing these issues, this study proposes an enhanced U-Net network to automate the extraction and 3D modeling of real road scenes using UAV imagery. Initially, a cascaded atrous spatial pyramid module was integrated into the encoder to capitalize on global context information, thereby refining the fuzzy segmentation outcomes. Subsequently, a module for augmenting road feature extraction was added within the channel, and a spatial attention mechanism was introduced in the decoder to enhance edge clarity. Experimental results demonstrated that this model captures more road information compared to mainstream networks and effectively incorporates topological structure perception for road extraction in complex scenarios, thus improving road connectivity. The model achieved an F1 score and mean Intersection over Union (mIoU) of 85.6% and 81.2%, respectively, on UAV images of road scenes – marking improvements of 3.9% and 3.4% over the traditional U-Net model, thereby exhibiting superior automatic road extraction capabilities. Ultimately, the model facilitated refined modeling and visual analysis of road scenes, achieving high overall accuracy and detailed local restoration of the actual scene.

Global road extraction using a pseudo-label guided framework: from benchmark dataset to cross-region semi-supervised learning

ABSTRACT Recent advancements in satellite remote sensing technology and computer vision have enabled rapid extraction of road networks from massive, Very High-Resolution (VHR) satellite imagery. However, current road extraction methods face the following limitations: 1) Insufficient availability of accurate and diverse training datasets for global-scale road extraction; 2) Costly and time-consuming manual labeling of millions of road samples; and 3) Limited generalization ability of deep learning models across diverse global contexts, resulting in better performance for regions well-represented in the training dataset, but worse performance when faced with domain gaps. To address these challenges, a semi-supervised framework was developed in this study, which includes a global-scale benchmark dataset – termed GlobalRoadSet (GRSet) – and a pseudo-label guided semi-supervised road extraction network – termed GlobalRoadNetSF (GRNetSF). The GRSet dataset was constructed using high-resolution satellite imagery and open-source crowdsourced OpenStreetMap (OSM) data. It comprises 47,210 samples collected from 121 capital cities across six populated continents. The GRNetSF trains the network by generating pseudo-labels for unlabeled images, combined with a few labeled samples from the target region. To enhance the quality of the pseudo-labels, strong data augmentation perturbation and auxiliary feature perturbation techniques are employed to ensure model prediction consistency. The proposed GRNetSF_GRSet framework was implemented in over 30 cities worldwide, where most of the Intersection-over-Union (IoU) values increased by more than 10%. This outcome confirms its strong generalization ability.

A Review of Deep Learning-Based Methods for Road Extraction from High-Resolution Remote Sensing Images

A Review of Deep Learning-Based Methods for Road Extraction from High-Resolution Remote Sensing Images

Effect of dataset distribution on automatic road extraction in very high-resolution orthophoto using DeepLab V3+

Road extraction is one of the stages in the map-making process, which has been done manually, takes a long time, and costs a lot. Deep Learning is used to speed up the road extraction process by performing binary semantic segmentation on the image. We propose DeepLab V3+ to produce road extraction from very high-resolution orthophoto for Indonesia study area, which poses many challenges, such as road obstruction by trees, clouds, building shadows, dense traffic, and similarities to rivers and rice fields. We compared the distribution of datasets to obtain the optimal performance of the DeepLab V3+ model in relation to the dataset. The results showed that dataset ratio of 75:10:15 resulted in mean Intersection Over Union (mIoU) of 0.92 and Dice Loss of 0.042. Visually, the results of road extraction are more accurate when compared to the results obtained from different distributions of the dataset.

ST-MDAMNet: Swin transformer combines multi-dimensional attention mechanism for semantic segmentation of high-resolution earth surface images

In the derection of remote sensing (RS) image analysis, semantic segmentation, as an important technology, is of key significance for the identification and analysis of land surface cover types. In recent years, applying deep learning models to tasks such as road extraction, water distribution extraction, building classification and building segmentation from RS images has become an important research hotspot. Due to its limited receptive field, traditional convolutional neural networks (CNN) cannot effectively capture global context information. Transformer uses the multi-head self-attention mechanism to capture a wide range of information and can solve this problem well. Therefore, we proposed ST-MDAMNet based on Swin Transformer and combined with the multi-dimensional attention mechanism. First, a feature enhancement module (FAM) is introduced after each stage of the Swin Transformer encoder to effectively enhance the model’s proficiency in identifying essential information. Secondly, a feature fusion module (FFM) is proposed to effectively fuse the multi-scale information of the encoder part. It further improves the expression ability of different dimensional features and effectively improves the detection effect of small targets. Ultimately, the fused features are input into the multi-dimensional attention module (MDAM) to carefully optimize the features, which greatly increases the effect of semantic segmentation of RS images. We demonstrate the effectiveness of each module through ablation experiments. Comparative experiments are completed on two publicly large-scale datasets, and the proposed method shows excellent results compared with state-of-the-art methods.

DPIF-Net: a dual path network for rural road extraction based on the fusion of global and local information

DPIF-Net: a dual path network for rural road extraction based on the fusion of global and local information

Mountainous road vector data update method based on matching point pair grouping

ABSTRACT The vector information of mountainous roads is great significance, including regional economics, emergency response, disaster management, among others. Nevertheless, there are irregular deformations in existing vector data, coupled with incomplete extraction results for mountainous roadways. These issues pose challenges in establishing a matching model between road extraction results and existing vector data, significantly reducing the efficiency of automated updates for the current vector data. Targeting roads as a distinct artificial feature and leveraging their topological connectivity, we propose a vector data updating method based on matching point pair grouping. Firstly, we employ the SDUNet model to extract mountainous road and utilize the Superglue model to match road binary images with vector binary images, resulting in sets of initial matching point pairs. Subsequently, we propose a road line extraction model that groups matching point pairs, eliminates misaligned pairs based on road topological connectivity, and establishes a mapping relationship between road lines and vector lines. Ultimately, through road line optimization and vector line optimization methods, we accomplish the automatic updating of vector data for mountainous roadways. Through a comprehensive analysis of over 2600 vector data, our method demonstrates substantial advantages in terms of both F1 and IoU compared to alternative methods.

Unstructured Road Extraction in UAV Images based on Lightweight Model

There is no unified planning standard for unstructured roads, and the morphological structures of these roads are complex and varied. It is important to maintain a balance between accuracy and speed for unstructured road extraction models. Unstructured road extraction algorithms based on deep learning have problems such as high model complexity, high computational cost, and the inability to adapt to current edge computing devices. Therefore, it is best to use lightweight network models. Considering the need for lightweight models and the characteristics of unstructured roads with different pattern shapes, such as blocks and strips, a TMB (Triple Multi-Block) feature extraction module is proposed, and the overall structure of the TMBNet network is described. The TMB module was compared with SS-nbt, Non-bottleneck-1D, and other modules via experiments. The feasibility and effectiveness of the TMB module design were proven through experiments and visualizations. The comparison experiment, using multiple convolution kernel categories, proved that the TMB module can improve the segmentation accuracy of the network. The comparison with different semantic segmentation networks demonstrates that the TMBNet network has advantages in terms of unstructured road extraction.

A road semantic segmentation system for remote sensing images based on deep learning

With the rapid development of deep learning of computer science nowadays in China, many fields in academic research have experienced the powerful and efficient advantages of deep learning and have begun to integrate it with their own research. To be specific, in the field of remote sensing, the challenge of road extraction from the original images can be effectively solved by using deep learning technology. Getting a high precision in road extraction can not only help scientists to update their road map in time but also speed up the process of digitization of roads in big cities. However, until now, compared to manual road extraction, the accuracy is not high enough to meet the needs of high-precision road extraction for the deep learning model because the model cannot extract the roads exactly in complex situations such as villages. However, this study trained a new road extraction model based on UNet model by using only datasets from large cities and can get a pretty high precision in extraction for roads in big cities. Undoubtedly, this can lead to over-fitting, but its unique high accuracy ensures that the model's ability to extract roads can be well utilized under the situations of large cities, helping researchers to update road maps more conveniently and quickly in large cities.

A Deep Neural Network for Road Extraction with the Capability to Remove Foreign Objects with Similar Spectra

Abstract. Existing road extraction methods based on deep learning often struggle with distinguishing ground objects that share similar spectral information, such as roads and buildings. Consequently, this study proposes a dual encoder-decoder deep neural network to address road extraction in complex backgrounds. In the feature extraction stage, the first encoder-decoder designed for extracting road features. The second encoder-decoder utilized for extracting building features. During the feature fusion stage, road features and building features are integrated using a subtraction method. The resultant road features, constrained by building features, enhance the preservation of accurate road feature information. Within the feature fusion stage, road feature maps and building feature maps designated for fusion are input into the convolutional block attention module. This step aims to amplify the features of different channels and extract key information from diverse spatial positions. Subsequently, feature fusion is executed using the element-by-element subtraction method. The outcome is road features constrained by building features, thus preserving more precise road feature information. Experimental results demonstrate that the model successfully learns both road and building features concurrently. It effectively distinguishes between easily confused roads and buildings with similar spectral information, ultimately enhancing the accuracy of road extraction.

Research of multimodal transport potential of major cities in China based on the satellite remote sensing

Abstract. By two or more modes of transportation to connect with each other and complete the transport process, multimodal transport could significantly improve transport efficiency, reduce costs, while promote energy conservation and emission reduction, compared with the traditional single mode of transport. Therefore, the multimodal transport development reflects the level of national or regional economic development to some extent. In this study, multimodal transport potential index was built to evaluate the possibility of multimodal transport. Remote sensing images from satellites were used to extract roads, railway stations and airports. A method was proposed to derive the road-rail transport potential index and road-air transport potential index, and then for the analysis of multimodal transport potential in 36 cities. Results show that there is a big gap among 36 cities on the development potential of road-rail and road-air transport. Compared with the road-rail transport potential index, the distribution of road-air transport potential index is more consistent among and within the seven regions. Index values of megacity and super cities are much higher than type I and II big cities. Moreover, in the 36 cities, there is a positive correlation between the multimodal transport potential index and GDP. The research results could be used to quantitatively evaluate the development of transport infrastructure, consequently provide more solid and reliable basic information for the planning, design and scheme adjustment of multimodal transport, thus comprehensively improve the efficiency and quality of multimodal transport, serve the territorial spatial planning.

MDSC-Net: multi-directional spatial connectivity for road extraction in remote sensing images

MDSC-Net: multi-directional spatial connectivity for road extraction in remote sensing images

DEDU-Net: Dual-Encoder-Decoder-U-Net for road extraction from high-resolution remote sensing images

ABSTRACT The development of the modern urban economy is closely tied to road construction, with roads being one of the most crucial components in urban development. The use of high-resolution remote sensing images to monitor the road conditions in cities and surrounding towns has become a highly emphasized research focus in recent years. However, due to the complexity of the environment, this task still faces significant challenges. For instance, urban road structures are intricate, which involve multiple lanes, intersections, building obstructions, etc. Rural roads may consist of narrow paths or irregular dirt roads. In addressing these issues, this paper proposes a road extraction algorithm based on a Dual-Encoder-Decoder U- Net (DEDU-Net). The algorithm leverages a dual encoder-decoder network to extract multi-scale information from the image. It then employs a dual decoder network to restore the feature map to the original image, achieving precise road extraction. Additionally, a new module, the Global Fusion Module (GFM), is introduced. This module achieves global context information fusion by weighting features. In the experimental section, two publicly available datasets were used for testing: the CHN6-CUG dataset and the Gansu Mountain Road dataset. For example, for the Gansu Mountain Road and CHN6-CUG mixed dataset, the model achieved an Overall Accuracy (OA) of 94.947% and a mean Intersection over Union (mIoU) of 70.971%. The results indicate that compared to traditional methods, this proposed method exhibits higher accuracy and robustness. It can adapt to both urban and rural roads, delivering outstanding performance even in complex scenarios.

A New Road Extraction Method from Satellite Images Using Genetic Programming

A New Road Extraction Method from Satellite Images Using Genetic Programming

A new optimization approach based on neural architecture search to enhance deep U-Net for efficient road segmentation

Neural Architecture Search (NAS) has significantly improved the accuracy of image classification and segmentation. However, these methods concentrate on finding segmentation structures for natural or medical applications. In this study, we introduce a NAS approach based on gradient optimization to identify ideal cell designs for road segmentation. To the best of our knowledge, this work represents the first application of gradient-based NAS to road extraction. Taking insight from the U-Net model and its successful variations in different image segmentation tasks, we propose NAS-enhanced U-Net, illustrated by an equal number of cells in both encoder and decoder levels. While cross-entropy combined with dice loss is commonly used in many segmentation tasks, road extraction brings up a unique challenge due to class imbalance. To address this, we introduce a combination of loss function. This function merges cross-entropy with weighted Dice loss, focusing on elevating the importance of the road class by assigning it a weight (⍵), while background Dice values are disregarded. The results indicate that the optimal weight for the proposed model equals 2. Additionally, our work challenges the assumption that increased model parameters or depth inherently leads to improved performance. Therefore, we establish search spaces 2,3,4,5,6,7 and 8 to automatically choose the optimal depth for model. We present promising segmentation results for our proposed method, achieved without any pretraining on the Massachusetts road dataset. Furthermore, these results are compared with those of 14 models categorized into four groups: U-Net, Segnet, FCN8, and Nas-U-Net.

Extracting roads from satellite images via enhancing road feature investigation in learning

AbstractIt is a hot topic to extract road maps from satellite images. However, it is still very challenging with existing methods to achieve high‐quality results, because the regions covered by satellite images are very large and the roads are slender, complex and only take up a small part of a satellite image, making it difficult to distinguish roads from the background in satellite images. In this article, we address this challenge by presenting two modules to more effectively learn road features, and so improving road extraction. The first module exploits the differences between the patches containing roads and the patches containing no road to exclude the background regions as many as possible, by which the small part containing roads can be more specifically investigated for improvement. The second module enhances feature alignment in decoding feature maps by using strip convolution in combination with the attention mechanism. These two modules can be easily integrated into the networks of existing learning methods for improvement. Experimental results show that our modules can help existing methods to achieve high‐quality results, superior to the state‐of‐the‐art methods.