Search Results (35)

Maps of road layouts play an essential role in autonomous driving, and it is often advantageous to represent them in a compact form, using a sparse set of surveyed points of the lane boundaries. While lane centerlines are valuable references in the prediction and planning of trajectories, most centerline extraction methods only achieve satisfactory accuracy with high computational cost and limited performance in sparsely described scenarios. This paper explores the problem of centerline extraction based on a sparse set of border points, evaluating the performance of different approaches on both a self-created and a public dataset, and proposing a novel method to extract the lane centerline by searching and linking the internal maximal circles along the lane. Compared with other centerline extraction methods producing similar numbers of center points, the proposed approach is significantly more accurate: in our experiments, based on a self-created dataset of road layouts, it achieves a max deviation below 0.15 m and an overall RMSE less than 0.01 m, against the respective values of 1.7 m and 0.35 m for a popular approach based on Voronoi tessellation, and 1 m and 0.25 m for an alternative approach based on distance transform. Full article

Agricultural navigation, as an essential part of smart agriculture, is a crucial step in realizing intelligence and, compared with the structured features of urban roads, such as lane-keeping lines, traffic guidance lines, etc., the field environment is more complex. Especially at agricultural intersections, traditional navigation line extraction algorithms make it difficult to achieve the automatic prediction of multiple road navigation lines due to complex unstructured features such as weeds and trees. Therefore, this study proposed a field road navigation line prediction method based on an improved context guided network (CGNet), which can quickly, stably, and accurately detect intersection fields and promptly predict navigation lines for two different directional paths at intersections. Firstly, CGNet will be used to learn the local features of intersections and the joint features of video frames before and after the surrounding environment. Then, the CGNet with a self-attention block module is proposed by adding the self-attention mechanism to improve the semantic segmentation accuracy of CGNet in field road scenes, and the detection speed is not significantly reduced. The semantic segmentation accuracy mIoU is 0.89, and the processing speed is 104 FPS. Subsequently, a field road centerline extraction algorithm is proposed based on the partitioning idea, which can accurately obtain the centerlines of road intersections in the image. The average lateral deviation of each centerline is less than 4%. This study achieved the prediction of intersection navigation lines in mountainous field road scenes, which can provide technical support for field operation road planning of agricultural equipment such as plant protection and harvesting. At the same time, the research findings provide theoretical references for sustainable agricultural development. Full article

Promoting the deployment and application of embedded systems in complex forest scenarios is an inevitable developmental trend in advanced intelligent forestry equipment. Unstructured roads, which lack effective artificial traffic signs and reference objects, pose significant challenges for driverless technology in forest scenarios, owing to their high nonlinearity and uncertainty. In this research, an unstructured road parameterization construction method, “DeepLab-Road”, based on tight coupling of multisource information is proposed, which aims to provide a new segmented architecture scheme for the embedded deployment of a forestry engineering vehicle driving assistance system. DeepLab-Road utilizes MobileNetV2 as the backbone network that improves the completeness of feature extraction through the inverse residual strategy. Then, it integrates pluggable modules including DenseASPP and strip-pooling mechanisms. They can connect the dilated convolutions in a denser manner to improve feature resolution without significantly increasing the model size. The boundary pixel tensor expansion is then completed through a cascade of two-dimensional Lidar point cloud information. Combined with the coordinate transformation, a quasi-structured road parameterization model in the vehicle coordinate system is established. The strategy is trained on a self-built Unstructured Road Scene Dataset and transplanted into our intelligent experimental platform to verify its effectiveness. Experimental results show that the system can meet real-time data processing requirements (≥12 frames/s) under low-speed conditions (≤1.5 m/s). For the trackable road centerline, the average matching error between the image and the Lidar was 0.11 m. This study offers valuable technical support for the rejection of satellite signals and autonomous navigation in unstructured environments devoid of high-precision maps, such as forest product transportation, agricultural and forestry management, autonomous inspection and spraying, nursery stock harvesting, skidding, and transportation. Full article

The safe and efficient operation of highways minimizes the environmental impact, reduces accidents, and promotes the reliability of the transportation infrastructure, all in support of sustainable transportation. The horizontal alignment of highways holds particular importance as it directly impacts driver behavior, vehicle stability, and overall road safety. In many cases, highway inventory data held by infrastructure operators may contain inaccurate or outdated information. The accuracy of the variables used in crash prediction models eliminates possible bias in the variable estimators. This research proposes a methodology to obtain accurate horizontal geometric features from digital imagery based on the analysis of the planimetry, feature geolocation and centerline azimuth sequence. The reliability of the method is verified by means of numerical and statistical procedures. This methodology is applied to 150 km of motorway segments in Portugal. Although it is found that the geometric characteristics of most of the inventory segments closely matched the extracted alignments, very significant differences are found in some sections. The results of the proposed procedure are illustrated with several examples. Finally, the propagation of error in the determination of the geometric design independent variables in the fitting of the statistical models is discussed based on the results. Full article

Traditional DeepLabV3+ image semantic segmentation methods face challenges in pitaya orchard environments characterized by multiple interference factors, complex image backgrounds, high computational complexity, and extensive memory consumption. This paper introduces an improved visual navigation path recognition method for pitaya orchards. Initially, DeepLabV3+ utilizes a lightweight MobileNetV2 as its primary feature extraction backbone, which is augmented with a Pyramid Split Attention (PSA) module placed after the Atrous Spatial Pyramid Pooling (ASPP) module. This improvement enhances the spatial feature representation of feature maps, thereby sharpening the segmentation boundaries. Additionally, an Efficient Channel Attention Network (ECANet) mechanism is integrated with the lower-level features of MobileNetV2 to reduce computational complexity and refine the clarity of target boundaries. The paper also designs a navigation path extraction algorithm, which fits the road mask regions segmented by the model to achieve precise navigation path recognition. Experimental findings show that the enhanced DeepLabV3+ model achieved a Mean Intersection over Union (MIoU) and average pixel accuracy of 95.79% and 97.81%, respectively. These figures represent increases of 0.59 and 0.41 percentage points when contrasted with the original model. Furthermore, the model’s memory consumption is reduced by 85.64%, 84.70%, and 85.06% when contrasted with the Pyramid Scene Parsing Network (PSPNet), U-Net, and Fully Convolutional Network (FCN) models, respectively. This reduction makes the proposed model more efficient while maintaining high segmentation accuracy, thus supporting enhanced operational efficiency in practical applications. The test results for navigation path recognition accuracy reveal that the angle error between the navigation centerline extracted using the least squares method and the manually fitted centerline is less than 5°. Additionally, the average deviation between the road centerlines extracted under three different lighting conditions and the actual road centerline is only 2.66 pixels, with an average image recognition time of 0.10 s. This performance suggests that the study can provide an effective reference for visual navigation in smart agriculture. Full article

The complexity inherent in navigating intricate traffic environments poses substantial hurdles for intelligent driving technology. The continual progress in mapping and sensor technologies has equipped vehicles with the capability to intricately perceive their exact position and the intricate interplay among surrounding traffic elements. Building upon this foundation, this paper introduces a deep reinforcement learning method to solve the decision-making and trajectory planning problem of intelligent vehicles. The method employs a deep learning framework for feature extraction, utilizing a grid map generated from a blend of static environmental markers such as road centerlines and lane demarcations, in addition to dynamic environmental cues including vehicle positions across varied lanes, all harmonized within the Frenet coordinate system. The grid map serves as the input for the state space, and the input for the action space comprises a vector encompassing lane change timing, velocity, and vertical displacement at the lane change endpoint. To optimize the action strategy, a reinforcement learning approach is employed. The feasibility, stability, and efficiency of the proposed method are substantiated via experiments conducted in the CARLA simulator across diverse driving scenarios, and the proposed method can increase the average success rate of lane change by 6.8% and 13.1% compared with the traditional planning control algorithm and the simple reinforcement learning method. Full article

Remote-sensing images of high spatial resolution (HSR) are valuable sources of fine-grained spatial information for various applications, such as urban surveys and governance. There is continuing research on positional errors in remote-sensing images and their impacts in geoprocessing and applications. This paper explores the combined use of multi-point geostatistics (MPS), machine learning—in particular, generalized additive modeling (GAM)—and computer-image correlation for characterizing positional errors in images—in particular, HSR images. These methods are employed because of the merits of MPS in being flexible for non-parametric and joint simulation of positional errors in X and Y coordinates, the merits of GAM in being capable of handling non-stationarity in-positional errors through error de-trending, and the merits of computer-image correlation in being cost-effective in furnishing the training data (TD) required in MPS. Procedurally, image correlation is applied to identify homologous image points in reference-test image pairs to extract image displacements automatically in constructing TD. To cope with the complexity of urban scenes and the unavailability of truly orthorectified images, visual screening is performed to clean the raw displacement data to create quality-enhanced TD, while manual digitization is used to obtain reference sample data, including conditioning data (CD), for MPS and test data for performance evaluation. GAM is used to decompose CD and TD into trends and residuals. With CD and TD both de-trended, the direct sampling (DS) algorithm for MPS is applied to simulate residuals over a simulation grid (SG) at 80 m spatial resolution. With the realizations of residuals and, hence, positional errors generated in this way, the means, standard deviation, and cross correlation in bivariate positional errors at SG nodes are computed. The simulated error fields are also used to generate equal-probable realizations of vertices that define some road centerlines (RCLs), selected for this research through interpolation over the aforementioned simulated error fields, leading to error metrics for the RCLs and for the lengths of some RCL segments. The enhanced georectification of the RCLs is facilitated through error correction. A case study based in Shanghai municipality, China, was carried out, using HSR images as part of generalized point clouds that were developed. The experiment results confirmed that by using the proposed methods, spatially explicit positional-error metrics, including means, standard deviation, and cross correlation, can be quantified flexibly, with those in the selected RCLs and the lengths of some RCL segments derived easily through error propagation. The reference positions of these RCLs were obtained through error correction. The positional accuracy gains achieved by the proposed methods were found to be comparable with those achieved by conventional image georectification, in which the CD were used as image-georectification control data. The proposed methods are valuable not only for uncertainty-informed image geolocation and analysis, but also for integrated geoinformation processing. Full article

Road geometric information and a digital model based on light detection and ranging (LiDAR) can perform accurate geometric inventories and three-dimensional (3D) descriptions for as-built roads and infrastructures. However, unorganized point clouds and complex road scenarios would reduce the accuracy of geometric information extraction and digital modeling. There is a standardization need for information extraction and 3D model construction that integrates point cloud processing and digital modeling. This paper develops a framework from semantic segmentation to geometric information extraction and digital modeling based on LiDAR data. A semantic segmentation network is improved for the purpose of dividing the road surface and infrastructure. The road boundary and centerline are extracted by the alpha-shape and Voronoi diagram methods based on the semantic segmentation results. The road geometric information is obtained by a coordinate transformation matrix and the least square method. Subsequently, adaptive road components are constructed using Revit software. Thereafter, the road route, road entity model, and various infrastructure components are generated by the extracted geometric information through Dynamo and Revit software. Finally, a detailed digital model of the road scenario is developed. The Toronto-3D and Semantic3D datasets are utilized for analysis through training and testing. The overall accuracy (OA) of the proposed net for the two datasets is 95.3 and 95.0%, whereas the IoU of segmented road surfaces is 95.7 and 97.9%. This indicates that the proposed net could accomplish superior performance for semantic segmentation of point clouds. The mean absolute errors between the extracted and manually measured geometric information are marginal. This demonstrates the effectiveness and accuracy of the proposed extraction methods. Thus, the proposed framework could provide a reference for accurate extraction and modeling from LiDAR data. Full article

To effectively manage the terrestrial firefighting fleet in a forest fire scenario, namely, to optimize its displacement in the field, it is crucial to have a well-structured and accurate mapping of rural roads. The landscape’s complexity, mainly due to severe shadows cast by the wild vegetation and trees, makes it challenging to extract rural roads based on processing aerial or satellite images, leading to heterogeneous results. This article proposes a method to improve the automatic detection of rural roads and the extraction of their centerlines from aerial images. This method has two main stages: (i) the use of a deep learning model (DeepLabV3+) for predicting rural road segments; (ii) an optimization strategy to improve the connections between predicted rural road segments, followed by a morphological approach to extract the rural road centerlines using thinning algorithms, such as those proposed by Zhang–Suen and Guo–Hall. After completing these two stages, the proposed method automatically detected and extracted rural road centerlines from complex rural environments. This is useful for developing real-time mapping applications. Full article

Road networks play a fundamental role in our daily life. It is of importance to extract the road structure in a timely and precise manner with the rapid evolution of urban road structure. Recently, road network extraction using deep learning has become an effective and popular method. The main shortcoming of the road extraction using deep learning methods lies in the fact that there is a need for a large amount of training datasets. Additionally, the datasets need to be elaborately annotated, which is usually labor-intensive and time-consuming; thus, lots of weak annotations (such as the centerline from OpenStreetMap) have accumulated over the past a few decades. To make full use of the weak annotations, we propose a novel semi-weakly supervised method based on adversarial learning to extract road networks from remote sensing imagery. Our method uses a small set of pixel-wise annotated data and a large amount of weakly annotated data for training. The experimental results show that the proposed approach can achieve a maintained performance compared with the methods that use a large number of full pixel-wise annotations while using less fully annotated data. Full article

At present, road continuity is a major challenge, and it is difficult to extract the centerline vector of roads, especially when the road view is obstructed by trees or other structures. Most of the existing research has focused on optimizing the available deep-learning networks. However, the segmentation accuracy is also affected by the loss function. Currently, little research has been published on road segmentation loss functions. To resolve this problem, an attention loss function named GapLoss that can be combined with any segmentation network was proposed. Firstly, a deep-learning network was used to obtain a binary prediction mask. Secondly, a vector skeleton was extracted from the prediction mask. Thirdly, for each pixel, eight neighboring pixels with the same value of the pixel were calculated. If the value was 1, then the pixel was identified as the endpoint. Fourth, according to the number of endpoints within a buffered range, each pixel in the prediction image was given a corresponding weight. Finally, the weighted average value of the cross-entropy of all the pixels in the batch was used as the final loss function value. We employed four well-known semantic segmentation networks to conduct comparative experiments on three large datasets. The results showed that, compared to other loss functions, the evaluation metrics after using GapLoss were nearly all improved. From the predicted image, the road prediction by GapLoss was more continuous, especially at intersections and when the road was obscured from view, and the road segmentation accuracy was improved. Full article

Road centerline extraction is the foundation for integrating the segmented road map from a remote sensing image into a geographic information system (GIS) database. Considering that existing approaches tend to have a decline in performance for centerline and junction extraction when segmented road structures are irregular, this paper proposes a novel method which models the road network as a sequence of connected spline curves. Based on this motivation, the ratio of cross operators is firstly proposed to detect direction and width features of roads. Then, road pixels are divided into different clusters by local features using three perceptual grouping principles (i.e., direction grouping, proximity grouping, and continuity grouping). After applying a polynomial curve fitting on each cluster using pixel coordinates as observation data, the internal control points are determined according to the adjacency relation between clusters. Finally, road centerlines are generated based on spline fitting with constraints. We test our approach on segmented road maps which were obtained previously by machine recognition, or manual extraction from real optical (WorldView-2) and synthetic aperture radar (TerraSAR-X, Radarsat-2) images. Depending on the accuracy of the input segmented road maps, experimental results from our test data show that both the completeness and correctness of extracted centerlines are over 84% and 68% for optical and radar images, respectively. Furthermore, experiments also demonstrate the advantages of our proposed method, in contrast to existing methods for gaining smooth centerlines and precise junctions. Full article

In this paper, a novel framework for the automatic extraction of road footprints from airborne LiDAR point clouds in urban areas is proposed. The extraction process consisted of three phases: The first phase is to extract road points by using the deep learning model PointNet++, where the features of the input data include not only those selected from raw LiDAR points, such as 3D coordinate values, intensity, etc., but also the digital number (DN) of co-registered images and generated geometric features to describe a strip-like road. Then, the road points from PointNet++ were post-processed based on graph-cut and constrained triangulation irregular networks, where both the commission and omission errors were greatly reduced. Finally, collinearity and width similarity were proposed to estimate the connection probability of road segments, thereby improving the connectivity and completeness of the road network represented by centerlines. Experiments conducted on the Vaihingen data show that the proposed framework outperformed others in terms of completeness and correctness; in addition, some narrower residential streets with 2 m width, which have normally been neglected by previous studies, were extracted. The completeness and the correctness of the extracted road points were 84.7% and 79.7%, respectively, while the completeness and the correctness of the extracted centerlines were 97.0% and 86.3%, respectively. Full article

Generating and updating roadway geometric elements from aerial images is necessary for multiple geospatial information system purposes, which have been addressed through various approaches. However, most existing methods cannot deal with challenges such as differently curved ramp characteristics, whereas measurements of geometric elements are still of low effectiveness and accuracy. This paper presents a new method for the semi-automatic extraction of horizontal parameters of curved highway ramps using Google Earth images. The proposed method first determines a road centerline manually using a graphics editor software; the file is then saved and processed with a program that analyzes and splits the centerline into its basic components. After that, the curvature analysis and linear fitting methods are integrated for automatic PC and PT determination. Finally, at the post-processing stage, the radii of the curves are computed automatically using the least-squares method. The proposed method was tested on four highway ramps and validated by comparison with the obtained design plans. Results show that the proposed method successfully detected the curves’ PC/PT and measured their radii with a high degree of accuracy. Full article

The road extraction task is mainly composed of two subtasks, namely, road detection and road centerline extraction. As the road detection task and road centerline extraction task are strongly correlated, in this paper, we introduce a multitask learning framework to detect roads and extract road centerlines simultaneously. For the road centerline extraction problem, existing works rely either on regression-based methods, or classification-based methods. The regression-based methods suffer from slow convergence and unsatisfactory local solutions. The classification-based methods ignore the fact that the closer the pixel is to the centerline, the higher our tolerance for its misclassification. To overcome these problems, we first convert the road centerline extraction problem into the problem of discrete normalized distance label prediction, which can be resolved by training an ordinal regressor. For the road extraction task, most of the previous studies apply pixel-wise loss function, for example, Cross-Entropy loss, which is not sufficient, as the road has special topology characteristics such as connectivity. Therefore, we propose a road-topology loss function to improve the connectivity and completeness of the extracted road. The road-topology loss function has two key characteristics: (i) The road-topology loss function combines road detection prediction and road centerline extraction prediction to promote the two subtasks to each other by using the correlation between the two subtasks; (ii) The road-topology loss can emphatically penalize gaps that often appear in road detection results and spurious segments that easily appear in centerline extraction results. In this paper, we select the AdamW optimizer to minimize the road-topology loss. Since there is no public dataset, we build a road extraction dataset to evaluate our method. State-of-the-art semantic segmentation networks (LinkNet34, DLinkNet34, DeeplabV3plus) are used as baseline methods to compare with two kinds of method. The first kind of method modifies the baseline method by adding the road centerline extraction task branch based on ordinal regression. The second kind of method uses the road topology loss and has the same network architecture as the first kind of method. For the road detection task, the two kinds of methods improve the baseline methods by up to $3.51\%$ and $11.98\%$ in $IoU$ metric on our test dataset, respectively. For the road centerline extraction task, the two kinds of methods improve the baseline methods by up to $8.22\%$ and $10.9\%$ in the Quality metric on our test dataset. Full article