ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images

Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.

Automatic road extraction framework based on codec network

Road extraction based on deep learning is one of hot spots of semantic segmentation in the past decade.In this work,we proposed a framework based on codec network for automatic road extraction from remote sensing images.Firstly,a pre-trained ResNet34 was migrated to U-Net and its encoding structure was replaced to deepen the number of network layers,which reduces the error rate of road segmentation and the loss of details.Secondly,dilated convolution was used to connect the encoder and the decoder of network to expand the receptive field and retain more low-dimensional information of the image.Afterwards,the channel attention mechanism was used to select the information of the feature image obtained by up-sampling of the encoder,the weights of target features were optimized to enhance the features of target region and suppress the features of background and noise regions,and thus the feature extraction effect of the remote sensing image with complex background was optimized.Finally,an adaptive sigmoid loss function was proposed,which optimizes the imbalance between the road and the background,and makes the model reach the optimal solution.Experimental results show that compared with several semantic segmentation networks,the proposed method can greatly reduce the error rate of road segmentation and effectively improve the accuracy of road extraction from remote sensing images.

Intelligent extraction of road cracks based on vehicle laser point cloud and panoramic sequence images

In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strategy for extracting road cracks.This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images.The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously.A convolutional neural network is utilized to extract cracks from the panoramic sequence image.The extracted sequence image is then aligned with the laser point cloud,enabling the assignment of RGB information to the vehicle-mounted three dimensional(3D)point cloud and location information to the two dimensional(2D)panoramic image.Additionally,a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud.The three-dimensional data pertaining to the cracks can be acquired.The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks.The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks.This approach exhibits superior accuracy when compared to conventional methods.Moreover,it facilitates rapid and accurate identification and localization of road cracks,thereby playing a crucial role in ensuring road maintenance and traffic safety.Consequently,this technique finds extensive application in the domains of intelligent transportation and urbanization development.The technology exhibits significant promise for use in the domains of intelligent transportation and city development.

A Semi-automatic Method Based on Statistic for Mandarin Semantic Structures Extraction in Specific Domains

This paper proposed a new method of semi-automatic extraction for semantic structures from unlabelled corpora in specific domains. The approach is statistical in nature. The extracted structures can be used for shallow parsing and semantic labeling. By iteratively extracting new words and clustering words, we get an inital semantic lexicon that groups words of the same semantic meaning together as a class. After that, a bootstrapping algorithm is adopted to extract semantic structures. Then the semantic structures are used to extract new

Automatic Road Extraction Using Particle Filters from High Resolution Images

Road extraction plays an important role in many applications such as car navigation, but the manual extraction of roads is a laborious, tedious task. To speed the extraction of roads, an approach based on particle filtering to extract automatically roads from high resolution imagery is proposed. Particle filtering provides a statistical framework for propagating sample-based approximations of posterior distributions and has almost no restriction on the ingredients of the model. We integrate the similarity of grey value and the edge point distribution of roads into particle filtering to deal with complex scenes. To handle road appearance changes the tracking algorithm is allowed to update the road model during temporally stable image observations. A fully automatic initialization strategy is used. Experimental results show that the proposed approach is a promising and fully automatic method for extracting roads from images, even in the presence of occlusions.

Automatic Extraction of Urban Road Centerlines from High-Resolution Satellite Imagery Using Automatic Thresholding and Morphological Operation Method

The commercial high-resolution imaging satellite with 1 m spatial resolution IKONOS is an important data source of information for urban planning and geographical information system (GIS) applications. In this paper, a morphological method is proposed. The proposed method combines the automatic thresholding and morphological operation techniques to extract the road centerline of the urban environment. This method intends to solve urban road centerline problems, vehicle, vegetation, building etc. Based on this morphological method, an object extractor is designed to extract road networks from highly remote sensing images. Some filters are applied in this experiment such as line reconstruction and region filling techniques to connect the disconnected road segments and remove the small redundant. Finally, the thinning algorithm is used to extract the road centerline. Experiments have been conducted on a high-resolution IKONOS and QuickBird images showing the efficiency of the proposed method.

A Road Extraction Method for Remote Sensing Image Based on Encoder-Decoder Network

According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are rich in local details and simple in semantic features,an Encoder-Decoder network with shallow layers and high resolution is designed to improve the ability to represent detail information.Secondly,as the road area is a small proportion in remote sensing images,the cross-entropy loss function is improved,which solves the imbalance between positive and negative samples in the training process.Experiments on large road extraction datasets show that the proposed method gets the recall rate 83.9%,precision 82.5%and F1-score 82.9%,which can extract the road targets in remote sensing images completely and accurately.The Encoder-Decoder network designed in this paper performs well in the road extraction task and needs less artificial participation,so it has a good application prospect.

An automatic method for road centerline extraction from post-earthquake aerial images

Road vector database plays an important role in post-earthquake relief, rescue and reconstruction.However, due to data privacy policy, it is difficult for general users to obtain high-precision and complete vector data of road network. The OpenStreetMap(OSM) project provides an open-source, global free road dataset, but there are inevitable geo-localization/projection errors, which will lead to large errors in hazard survey analysis. In this paper, we proposed a road centerline correction method using postearthquake aerial images. Under the constraint of the vector road map(OpenStreetMap), we rectified the centerline by the context feature and spectral gradient feature of post-event images automatically.The experiment implemented on 0.5 m/pixel post-event aerial images of Haiti, 2010, showed that the completeness and extraction quality of proposed method were over 90% and 80% without any manual intervention.

A Road Extraction Method Based on Region Growing and Mathematical Morphology from Remote Sensing Images

Road traffic is the important driving factor for economic and social development. With the rapid increase of vehicle population, road traffic problems such as traffic jam and traffic accident have become the bottleneck which restricts economic development. In recent years, natural disasters frequently occur in China. Therefore, it is essential to extract road information to compute the degree of road damage for traffic emergency management. A road extraction method based on region growing and mathematical morphology from remote sensing images is proposed in this paper. According to the road features, the remote sensing image is preprocessed to separate road regions from non-road regions preliminarily. After image thresholding, region growing algorithm is used to extract connected regions. Then we sort connected regions by area to exclude the small regions which are probably non-road objects. Finally, the mathematical morphology algorithm is used to fill the holes inside the road regions. The experimental results show that the method proposed can effectively extract roads from remote sensing images. This research also has broad prospects in dealing with traffic emergency management by the government.

Road network extraction in classified SAR images using genetic algorithm

Due to the complicated background of objectives and speckle noise, it is almost impossible to extract roads directly from original synthetic aperture radar(SAR) images. A method is proposed for extraction of road network from high-resolution SAR image. Firstly, fuzzy C means is used to classify the filtered SAR image unsupervisedly, and the road pixels are isolated from the image to simplify the extraction of road network. Secondly, according to the features of roads and the membership of pixels to roads, a road model is constructed, which can reduce the extraction of road network to searching globally optimization continuous curves which pass some seed points. Finally, regarding the curves as individuals and coding a chromosome using integer code of variance relative to coordinates, the genetic operations are used to search global optimization roads. The experimental results show that the algorithm can effectively extract road network from high-resolution SAR images.

Automatic Road Extraction in Rural Areas Based on Digital Imaging and Laser Scanner Data

Digitizing road maps manually is an expensive and time-consuming task. Several methods that intend to develop fully or semi-automated systems have been proposed. In this work we introduce a method, based on the Radon transform and optimal algorithms, which extracts automatically roads on images of rural areas, images that were acquired by digital cameras and airborne laser scanners. The proposed method detects linear segments iteratively and starting from this it generates the centerlines of the roads. The method is based on an objective function which depends on three parameters related to the correlation between the cross-sections, spectral similarity and directions of the segments. Different tests were performed using aerial photos, Ikonos images and laser scanner data of an area located in the state of Parana （Brazil） and their results are presented and discussed. The quality of the detection of the roads centerlines was computed using several indexes - completeness, correctness and RMS. The values obtained reveal the good performance of the proposed methodology.

Automatic Horizontal Road Design Information Extraction from Georeferenced Polygonals： A Brazilian Federal Highway Network Study

Road geometric design data are a vital input for diverse transportation studies. This information is usually obtained from the road design project. However, these are not always available and the as-built course of the road may diverge considerably from its projected one, rendering subsequent studies inaccurate or impossible. Moreover, the systematic acquisition of this data for the entire road network of a country or even a state represents a very challenging and laborious task. This study＇s goal was the extraction of geometric design data for the paved segments of the Brazilian federal highway network, containing more than 47,000 km of highways. It presents the details of the method＇s adoption process, the particularities of its application to the dataset and the obtained geometric design information. Additionally, it provides a first overview of the Brazilian federal highway network composition （curves and tangents） and geometry.

Road network extraction from high resolution satellite images

In this paper, an approach of roads network extraction from high resolution satellite images is presented. First, the approach extracts road surface from satellite image using one-class support vector machine （SVM）. Second, the road topology is built from the road surface. The last output of the approach is a series of road segments which is represented by a sequence of points as well as the topological relations among them. The approach includes four steps. In the first step one-class support vector machine is used for classifying pixel of the satellite images to road class or non-road class. In the second step filling holes and connecting gaps for the SVM＇s classification result is applied through mathematical morphology close operation. In the third step the road segment is extracted by a series of operations which include skeletonization, thin, branch pruning and road segmentation. In the last step a geometrical adjustment process is applied through analyzing the road segment curvature. The experiment results demonstrate its robustness and viability on extracting road network from high resolution satellite images.

Application of PDE and Mathematical Morphology in the Extraction Validation of the Roads

The digital images generated by remote sensors often contain noises that are inherent in the process of imaging and transmission. The application of digital processing techniques greatly enhances the ability to extract information on surface targets from remote sensing data. When digital images are used with high spatial resolution, one of the problems emerging the high variability of targets presents in such images. From the computational point of view, the use of partial differential equations is favored by the large number of numerical methods showed in the literature. Many of the models are considered non-complex both from the mathematical and computational standpoints, due to the characteristics of explicit equations. This work uses techniques of the partial differential equations (PDE) and mathematical morphology to extract cartographic features in digital images of the remote sensing. The selected study area corresponds to an image containing part of the Mário Covas Ring Road, located in the metropolitan region of Sao Paulo (SP), Brazil. The results are promising and show the high potential of using mathematical morphology in the field of cartography.

A Review on Extraction of Lakes from Remotely Sensed Optical Satellite Data with a Special Focus on Cryospheric Lakes

Water on the Earth’s surface is an essential part of the hydrological cycle. Water resources include surface waters, groundwater, lakes, inland waters, rivers, coastal waters, and aquifers. Monitoring lake dynamics is critical to favor sustainable management of water resources on Earth. In cryosphere, lake ice cover is a robust indicator of local climate variability and change. Therefore, it is necessary to review recent methods, technologies, and satellite sensors employed for the extraction of lakes from satellite imagery. The present review focuses on the comprehensive evaluation of existing methods for extraction of lake or water body features from remotely sensed optical data. We summarize pixel-based, object-based, hybrid, spectral index based, target and spectral matching methods employed in extracting lake features in urban and cryospheric environments. To our knowledge, almost all of the published research studies on the extraction of surface lakes in cryospheric environments have essentially used satellite remote sensing data and geospatial methods. Satellite sensors of varying spatial, temporal and spectral resolutions have been used to extract and analyze the information regarding surface water. Multispectral remote sensing has been widely utilized in cryospheric studies and has employed a variety of electro-optical satellite sensor systems for characterization and extraction of various cryospheric features, such as glaciers, sea ice, lakes and rivers, the extent of snow and ice, and icebergs. It is apparent that the most common methods for extracting water bodies use single band-based threshold methods, spectral index ratio (SIR)-based multiband methods, image segmentation methods, spectral-matching methods, and target detection methods (unsupervised, supervised and hybrid). A Synergetic fusion of various remote sensing methods is also proposed to improve water information extraction accuracies. The methods developed so far are not generic rather they are specific to either the location or satellite imagery or to the type of the feature to be extracted. Lots of factors are responsible for leading to inaccurate results of lake-feature extraction in cryospheric regions, e.g. the mountain shadow which also appears as a dark pixel is often misclassified as an open lake. The methods which are working well in the cryospheric environment for feature extraction or landcover classification does not really guarantee that they will be working in the same manner for the urban environment. Thus, in coming years, it is expected that much of the work will be done on object-based approach or hybrid approach involving both pixel as well as object-based technology. A more accurate, versatile and robust method is necessary to be developed that would work independent of geographical location (for both urban and cryosphere) and type of optical sensor.

Extracting Campus’Road Network from Walking GPS Trajectories

Road network extraction is vital to both vehicle navigation and road planning.Existing approaches focus on mining urban trunk roads from GPS trajectories of floating cars.However,path extraction,which plays an important role in earthquake relief and village tour,is always ignored.Addressing this issue,we propose a novel approach of extracting campus’road network from walking GPS trajectories.It consists of data preprocessing and road centerline generation.The patrolling GPS trajectories,collected at Hunan University of Science and Technology,were used as the experimental data.The experimental evaluation results show that our approach is able to effectively and accurately extract both campus’trunk roads and paths.The coverage rate is 96.21%while the error rate is 3.26%.

融合注意力和扩张卷积的遥感影像道路信息提取方法

针对高分辨率遥感影像语义分割存在地物边缘分割不连续、道路及背景特征复杂多样导致道路提取分割精度不高的问题,提出了一种融合双通道注意力和扩张卷积的遥感影像道路信息提取语义分割网络(A 2DU-Net)。首先,在特征提取部分引入坐标注意力(coordinate attention,CA)模块,捕捉道路位置、方向和跨通道信息,精确定位道路信息。其次,针对网络对细节特征丢失的敏感问题,在编码器的末端利用不同扩张率的空洞卷积构建多尺度特征融合的空洞空间金字塔池化模块(multi-scale Atrous spatial pyramid pooling module,MASPPM)来获得更大的感受野,提高网络性能。最后,为了避免U-Net中纯跳跃连接在语义上不相似特征的融合,在编码器和解码器的跳跃连接之间增加了双通道注意力机制来实现门控筛选,抑制非目标区域的特征,提高网络的分割精度。实验在公共道路数据集Massachusetts上对网络模型进行测试,OA(准确率)、交并比(IoU)、平均交并比(mIoU)和F1等评价指标分别达到98.07%、64.39%、81.20%和88.67%。与主流方法U-Net和DDUNet进行比较,mIoU分别提升了3.07%、0.22%,IoU分别提升了1.98%、0.52%。实验结果表明,所提出的方法优于所有的比较方法,能够有效提高道路分割的精确度。

GCN引导模型视点的光学遥感道路提取网络

在光学遥感图像中,道路易受遮挡物、铺装材料以及周围环境等多重因素的影响,导致其特征模糊不清。然而,现有道路提取方法即使增强其特征感知能力,仍在特征模糊区域存在大量误判。为解决上述问题,本文提出基于GCN引导模型视点的道路提取网络(RGGVNet)。RGGVNet采用编解码结构,并设计基于GCN的视点引导模块(GVPG)在编解码器的连接处反复引导模型视点,从而增强对特征模糊区域的关注。GVPG利用GCN信息传播过程具有平均特征权重的特性,将特征图中不同区域道路显著性水平作为拉普拉斯矩阵,参与到GCN信息传播从而实现引导模型视点。同时,提出密集引导视点策略(DGVS),采用密集连接的方式将编码器、GVPG和解码器相互连接,确保有效引导模型视点的同时缓解优化困难。在解码阶段设计多分辨率特征融合(MRFF)模块,最小化不同尺度道路特征在特征融合和上采样过程中的信息偏移和损失。在两个公开遥感道路数据集中,本文方法IoU分别达到65.84%和69.36%,F1-score分别达到79.40%和81.90%。从定量和定性两方面实验结果可以看出,本文所提方法性能优于其他主流方法。

基于路网提取的公路规模估算方法研究

为了对所辖农村地区耕地区域公路需求规模进行估算,研究了一种基于高分遥感影像道路提取矢量路网的农村耕地区域公路网规模估算方法。综合考虑公路网密度及自然村分布情况,设计了路网估算密度系数、自然村密度系数,以所在地形环境作为分类,充分考虑了农村耕地区域公路建设的实际需求并量化计算。实验表明,与交通运输主管部门实际需求相比,该方法的估算准确率可达到实际需求的92.61%。该方法能够在国土系数法、连通度法等传统方法之外提供一种以遥感影像为基础数据的农村耕地区域公路规模测算方法,弥补了传统方法无法充分利用新一代信息技术数据的不足,是传统方法的有效补充。该方法的设计在适用性的角度上合理。