High-precision Mapping Research Articles

Lane extraction from trajectories at road intersections based on Graph Transformer Network

Lane-level road networks are crucial components of high-precision maps and play a significant role in intelligent transportation systems. Extracting lane-level road networks at intersections presents considerable challenges due to the complex structures of intersections and diverse driving behaviors. A graph-learning based method is proposed for extracting lanes from high-precision trajectories at road intersections. A trajectory relation graph is designed to encode the directional, shape, and distance features of trajectories, capturing both the intrinsic and extrinsic relationships between trajectories. Subsequently, a Graph Transformer Network is developed to extract a representative subset of trajectories as lanes. To alleviate the problem of generating missing and extraneous lanes, a set-based lane extraction loss is introduced to achieve implicit pruning of redundancy through the attention mechanism. Comprehensive experimental results demonstrate that the proposed method outperforms state-of-the-art methods in three positional and topological accuracy metrics. The method achieves lane extraction with minimal omissions and redundancies and exhibits strong performance in complex scenarios such as U-turns, lane merging, and lane diverging regions.

Road boundary extraction method from mobile laser scanning point clouds

Abstract With the rapid development of mobile laser scanning (MLS) technology, high-precision three-dimensional point cloud data has shown great potential in different fields such as topographic mapping, road asset management and smart city construc-tion. Three-dimensional point cloud data contains not only position information, but also the shape and attributes of the target, which is very convenient for obtaining road information. Accurate extraction of the road boundary is a basic task for obtaining road infrastructural data, which can support the generation of high-precision maps, vehicle navigation and auton-omous driving. However, road boundary extraction in urban environments is easily occluded such as vehicles and pedestri-ans on the road, which leads to problems such as difficulty and incomplete extraction of MLS point cloud road boundaries. To address this problem, this study proposes a road boundary extraction method that integrates pavement edge information, accurately considers the position of the road boundary from two dimensions, eliminates false boundaries, and completes the missing boundary through the extracted boundary spatial relationship. First, grid elevation filtering is used to remove high-level non-ground points. Then the pavement edges and curb stone points are extracted from the preprocessed point cloud, and they are superimposed to remove false boundary points to obtain accurate road boundaries. Finally, based on the spatial relationship of road boundaries, missing parts are detected and repaired to obtain complete road boundaries. Experimental results show that the accuracy on real road scenes exceeds 98%, the completeness rate is above 91%, and the extraction quality is above 90%, which verifies the effectiveness and accuracy of this method.

MSCPUnet: A multi-task neural network for plot-level crop classification in complex agricultural areas

High-precision mapping of agricultural crops in complex planting areas is a prerequisite for precision agricultural management. This paper first proposes a novel multi-task neural network, Multi-task Multi-Scale Convolutional Pooling Unet (MSCPUnet), for extracting vector plots. MSCPUnet is based on the Unet model and enhances performance through the incorporation of attention mechanisms, multi-scale pooling layers, and a multi-task learning approach for parallel processing. A ZiYuan-1 02D (ZY1E) satellite image collected from the He-Tao irrigation district in China is selected for plot extraction experiments, where MSCPUnet is compared with three other deep learning network variants. The Inter section over Union (IoU) and Accuracy metrics for the MSCPUnet model achieve the highest values, converging at 0.837 and 0.928, respectively. Leveraging this capability, a crop classification framework is proposed, which first extracts crop attributes from Sentinel-2 (S2) time series data. The plot information obtained from the MSCPUnet model is then combined with the area dominance method to assign crop attributes to vector plots, facilitating crop structure identification at the plot scale. Results indicate that this method significantly improves classification accuracy for fragmented farmlands, with overall accuracy (OA) rising to 91 % and Kappa coefficient increasing to 0.84 compared to a random forest classifier. This integrated crop classification approach has been validated in this study for high-precision crop mapping in complex planting areas.

Deviation Aware Mask for Localizing Ground Penetrating Radar Data Alignment

Abstract This paper proposes a data align pipeline for LGPR (Localization Ground Penetrating Radar). LGPR achieves robot localization by matching prior underground data map, therefore high-precision maps are essential. Utilizing GPR in a time acquisition mode for robot localization enables the technology to generate maps with resolutions far superior to those produced by camera or lidar mapping methods. However, it also introduces several challenges. On one hand, the process of map generation heavily relies on velocity control of the moving platform, and non-uniform motion in the localization scenario can result in feature deformation of GPR images. On the other hand, in the absence of relative a priori position conditions, there exists a certain degree of spatial dimension offset between the multiple data acquisitions from array GPR systems, rendering existing time-series deformation correction schemes ineffective. To address these challenges, by designing a deviation-aware distance, we aim to enhance existing time-series regularization approaches without relying on additional sensor position information, thus achieving synchronized alignment of multiple rounds of ground-penetrating radar data for the generation of high-quality underground map data used to evaluate LGPR performance. In this work, we compare existing synchronization strategies of LGPR with those of other sensors and alignment schemes, and validate the effectiveness of our proposed approach.

GPR Image Retrieval and Localization Based on Spatial Prior Constraints

Abstract Localizing Ground Penetrating Radar (LGPR) offers the distinct advantage of being unaffected by weather and light conditions changes. As a novel auxiliary driving localizing system, LGPR enhances the robustness of the auto-drive system. Traditional ground penetrating radar localizing technologies rely heavily on high-quality map data, exhibiting optimal performance in environments with complete, high-precision maps. However, deviations from the mapped trajectory can compromise localization accuracy. We introduce a novel approach: a ground penetrating radar image retrieval and localization method based on spatial prior constraints of array antennas to address this challenge. This method aims to mitigate mismatches in ground penetrating radar navigation and localization encountered under incomplete map coverage. We performed a comparative analysis with the LGPR baseline and then validated them experimentally on our dataset. The results show that the proposed method achieved significant enhancement in accuracy. In particular, the superiority of the proposed method is demonstrated in low overlap GPR image matching and localisation.

Commutative Encryption and Reversible Watermarking Algorithm for Vector Maps Based on Virtual Coordinates

The combination of encryption and digital watermarking technologies is an increasingly popular approach to achieve full lifecycle data protection. Recently, reversible data hiding in the encrypted domain (RDHED) has greatly aroused the interest of many scholars. However, the fixed order of first encryption and then watermarking makes these algorithms unsuitable for many applications. Commutative encryption and watermarking (CEW) technology realizes the flexible combination of encryption and watermarking, and suits more applications. However, most existing CEW schemes for vector maps are not reversible and are unsuitable for high-precision maps. To solve this problem, here, we propose a commutative encryption and reversible watermarking (CERW) algorithm for vector maps based on virtual coordinates that are uniformly distributed on the number axis. The CERW algorithm consists of a virtual interval step-based encryption scheme and a coordinate difference-based reversible watermarking scheme. In the encryption scheme, the map coordinates are moved randomly by multiples of virtual interval steps defined as the distance between two adjacent virtual coordinates. In the reversible watermarking scheme, the difference expansion (DE) technique is used to embed the watermark bit into the coordinate difference, computed based on the relative position of a map coordinate in a virtual interval. As the relative position of a map coordinate in a virtual interval remains unchanged during the coordinate scrambling encryption process, the watermarking and encryption operations do not interfere with each other, and commutativity between encryption and watermarking is achieved. The results show that the proposed method has high security, high capacity, and good invisibility. In addition, the algorithm applies not only to polyline and polygon vector data, but also to sparsely distributed point data, which traditional DE watermarking algorithms often fail to watermark.

Learning to drive as humans do: Reinforcement learning for autonomous navigation

This article introduces an approach aimed at enabling self-driving cars to emulate human-learned driving behavior. We propose a method where the navigation challenge of autonomous vehicles, from starting to ending positions, is framed as a series of decision-making problems encountered in various states negating the requirement for high-precision maps and routing systems. Utilizing high-quality images and sensor-derived state information, we design rewards to guide an agent’s movement from the initial to the final destination. The soft actor-critic algorithm is employed to learn the optimal policy from the interaction between the agent and the environment, informed by these states and rewards. In an innovative approach, we apply the variational autoencoder technique to extract latent vectors from high-quality images, reconstructing a new state space with vehicle state vectors. This method reduces hardware requirements and enhances training efficiency and task success rates. Simulation tests conducted in the CARLA simulator demonstrate the superiority of our method over others. It enhances the intelligence of autonomous vehicles without the need for intermediate processes such as target detection, while concurrently reducing the hardware footprint, even though it may not perform as well as the currently available mature techniques.

RLI-SLAM: Fast Robust Ranging-LiDAR-Inertial Tightly-Coupled Localization and Mapping.

Simultaneous localization and mapping (SLAM) is an essential component for smart robot operations in unknown confined spaces such as indoors, tunnels and underground. This paper proposes a novel tightly-coupled ranging-LiDAR-inertial simultaneous localization and mapping framework, namely RLI-SLAM, which is designed to be high-accuracy, fast and robust in the long-term fast-motion scenario, and features two key innovations. The first one is tightly fusing the ultra-wideband (UWB) ranging and the inertial sensor to prevent the initial bias and long-term drift of the inertial sensor so that the point cloud distortion of the fast-moving LiDAR can be effectively compensated in real-time. This enables high-accuracy and robust state estimation in the long-term fast-motion scenario, even with a single ranging measurement. The second one is deploying an efficient loop closure detection module by using an incremental smoothing factor graph approach, which seamlessly integrates into the RLI-SLAM system, and enables high-precision mapping in a challenging environment. Extensive benchmark comparisons validate the superior accuracy of the proposed new state estimation and mapping framework over other state-of-the-art systems at a low computational complexity, even with a single ranging measurement and/or in a challenging environment.

A non-invasive nanobody probe for high precision mapping of Lck spatial distribution.

The tyrosine kinase Lck is mandatory for initiating signaling responses downstream the antigenic T cell receptor (TCR). Numerous studies have shown that a prerequisite for efficient and well-balanced Lck regulation and function is its finely orchestrated spatial distribution pattern, especially at the plane of the plasma membrane. There is a wealth of knowledge on Lck localization sites, preference for specialized lipid microenvironments and colocalization partners. However, several questions concerning the spatial organization of its differentially phosphorylated conformers and the dynamics of their juxtaposition in relation to ligated and non-ligated TCRs remain elusive. In this brief report we introduce a non-invasive nanobody-based approach for mapping Lck subcellular allocation with high precision. Our initial data using this methodology, provide insight into the topology of Lck in resting T cells and its confined localization in a strictly delimited environment within the plane of the plasma membrane.

What determines the boundaries of H2O maser emission in an X-ray illuminated gas disc?

ABSTRACT High precision mapping of H$_{2}$O megamaser emission from active galaxies has revealed more than a dozen Keplerian H$_{2}$O maser discs, which enable a $\sim$4 per cent uncertainty estimate of the Hubble constant as well as providing accurate masses for the central black holes. These discs often have well-defined inner and outer boundaries of maser emission on sub-parsec scales. In order to better understand the physical conditions that determine the inner and outer radii of a maser disc, we examine the distributions of gas density and X-ray heating rate in a warped molecular disc described by a power-law surface density profile. For a suitable choice of the disc mass, we find that the outer radius $R_{\rm out}$ of the maser disc predicted from our model can match the observed value, with $R_{\rm out}$ mainly determined by the maximum heating rate or the minimum density for efficient maser action, depending on the combination of the Eddington ratio, black hole mass, and disc mass. Our analysis also indicates that the inner radius for maser action is comparable to the dust sublimation radius, suggesting that dust may play a role in determining the inner radius of a maser disc. Finally, our model predicts that H$_{2}$O gigamaser discs could exist at the centres of high-z quasars, with disc sizes of $\gtrsim 10-30$ pc.

Designing Reward Functions Using Active Preference Learning for Reinforcement Learning in Autonomous Driving Navigation

This study presents a method based on active preference learning to overcome the challenges of designing reward functions for autonomous navigation. Results obtained from training with artificially designed reward functions may not accurately reflect human intentions. We focus on the limitations of traditional reward functions, which often fail to facilitate complex tasks in continuous state spaces. We propose the adoption of active preference learning to resolve these issues and to generate reward functions that align with human preferences. This approach leverages an individual’s subjective preferences to guide an agent’s learning process, enabling the creation of reward functions that reflect human desires. We utilize mutual information to generate informative queries and apply information gained to balance the agent’s uncertainty with the human’s response capacity, encouraging the agent to pose straightforward and informative questions. We further employ the No-U-Turn Sampler (NUTS) method to refine the belief model, which outperforms that constructed using the Metropolis algorithm. Subsequently, we retrain the agent using reward weights derived from active preference learning. As a result, our autonomous driving vehicle can navigate between random starting and ending points without dependence on high-precision maps or routing, relying solely on its forward vision. We validate our approach’s performance within the CARLA simulation environment. Our algorithm significantly improved the success rate of autonomous driving navigation tasks that originally failed due to artificially designed rewards, increasing it to approximately 60%. Experimental results show significant improvement over the baseline algorithm, providing a solid foundation for enhancing navigation capabilities in autonomous driving systems and advancing the field of autonomous driving intelligence.

BATSCCD: a new change detection method for mapping building age in rapidly changing urban areas using Landsat time series data

ABSTRACT The building age is an important feature in the vulnerability assessment of disasters and building energy consumption modeling. It provides indispensable information for the study of built environment. However, obtaining high-precision maps of building ages is challenging, which impedes the development of relevant research and applications. In this study, a new building age mapping method based on Landsat time series classification and change detection (BATSCCD) was proposed, which integrates Landsat time series data with random forest and LandTrendr algorithm to reflect non-building to building changes, building reconstruction, and corresponding change characteristics. The proposed method achieved overall building age mapping accuracies of 80.45% within a 2-year tolerance and 87.66% within a 3-year tolerance in Guangzhou and accuracies of 78.08% and 87.52%, respectively, in Beijing. The improvement was notable, especially compared with the continuous change detection and classification (CCDC) method, with corresponding accuracy values of 36.22% and 46.31%, respectively, in Guangzhou and 49.7% and 60.19%, respectively, in Beijing. The results suggest that the BATSCCD method can be used to accurately estimate the building age and provide reliable mapping results. Thanks to the accessibility of required data and its high accuracy of building age estimation, the proposed method exhibits great application potential.

High-resolution feature pyramid attention network for high spatial resolution images land-cover classification in arid oasis zones

ABSTRACT Land-cover classification based on remote sensing technology has been adopted for decision-making concerning agricultural development, urban planning, and ecosystem protection in arid oasis zones. The semantic segmentation method based on deep learning, as a new paradigm, can effectively overcome the limitations of traditional pixel-based and object-based methods and obtain good classification results from high spatial resolution (HSR) remote sensing images. However, how to extract the exact category boundary and realize the high precision mapping is still a problem. This paper proposes a novel high-resolution feature pyramid attention network (HRFPANet) for land-cover classification. It effectively integrates the advantages of multi-scale feature extraction, attention mechanism, and feature fusion and alleviates boundary inconsistency, roughness, and category fragmentation associated with previous semantic segmentation models. The experimental results show that the mIoU score of HRFPANet is 79.5%, which is 11.5% and 2.6% higher than that of PSPNet and UPerNet, respectively. It proves the proposed model can be used for qualified land-cover mapping in arid oasis zones. Our source code is available at https://github.com/HPU-CPD/HRFPANet.git.

Enhanced Path Planning and Obstacle Avoidance Based on High-Precision Mapping and Positioning.

High-precision positioning and multi-target detection have been proposed as key technologies for robotic path planning and obstacle avoidance. First, the Cartographer algorithm was used to generate high-quality maps. Then, the iterative nearest point (ICP) and the occupation probability algorithms were combined to scan and match the local point cloud, and the positions and attitudes of the robot were obtained. Furthermore, Sparse Matrix Pose Optimization was carried out to improve the positioning accuracy. The positioning accuracy of the robot in x and y directions was kept within 5 cm, the angle error was controlled within 2°, and the positioning time was reduced by 40%. An improved timing elastic band (TEB) algorithm was proposed to guide the robot to move safely and smoothly. A critical factor was introduced to adjust the distance between the waypoints and the obstacle, generating a safer trajectory, and increasing the constraint of acceleration and end speed; thus, smooth navigation of the robot to the target point was achieved. The experimental results showed that, in the case of multiple obstacles being present, the robot could choose the path with fewer obstacles, and the robot moved smoothly when facing turns and approaching the target point by reducing its overshoot. The proposed mapping, positioning, and improved TEB algorithms were effective for high-precision positioning and efficient multi-target detection.

Experimental demonstration of wavefront reconstruction and correction techniques for variable targets based on distorted grating and deep learning

This research presents a practical approach for wavefront reconstruction and correction adaptable to variable targets, with the aim of constructing a high-precision, general extended target adaptive optical system. Firstly, we delve into the detailed design of a crucial component, the distorted grating, simplifying the optical system implementation while circumventing potential issues in traditional phase difference-based collection methods. Subsequently, normalized fine features (NFFs) and structure focus features (SFFs) which both are independent of the imaging target but corresponded precisely to the wavefront aberration are proposed. The two features provide a more accurate and robust characterization of the wavefront aberrations. Then, a Noise-to-Denoised Generative Adversarial Network (N2D-GAN) is employed for denoising real images. And a lightweight network, Attention Mechanism-based Efficient Network (AM-EffNet), is applied to achieve efficient and high-precision mapping between features and wavefronts. A prototype of object-independent adaptive optics system is demonstrated by experimental setup, and the effectiveness of this method in wavefront reconstruction for different imaging targets has been verified. This research holds significant relevance for engineering applications of adaptive optics, providing robust support for addressing challenges within practical systems.

农业环境高精度三维点云地图构建方法研究

In agricultural operation scenarios, the diversity of farmland terrain, crops and other forms, as well as uncertain factors such as weather changes and crop growth during agricultural operation, can have an impact on the construction of high-precision maps. To address these challenges and analyze operational scenarios based on the characteristics of agricultural scenarios, this paper proposes a point cloud map construction algorithm for plant point removal and locatability estimation. Based on the existing Simultaneous Localization and Mapping (SLAM) framework, plant point removal and locatability estimation are improved. Firstly, Red, Green, Blue (RGB) images and Near Infrared (NIR) images are fused to identify and remove plant point clouds, preserving effective inter frame matching information, reducing the impact of dynamic points on inter frame matching, and achieving high front-end motion estimation accuracy. Then, the localization estimation method based on learning is used to determine the motion estimation status and determine whether to execute the backend optimization algorithm. Finally, the back-end optimization algorithm based on Factor graph is designed, and the Factor graph, constraint relationship and optimization function are constructed to optimize the pose of all frames. The optimized map construction algorithm reduces the re projection errors between field roads, paths, and crop rows by 10.27%, 20.76%, and 14.36% compared to before optimization. To verify the actual operational effectiveness of the point cloud map construction algorithm, the hardware part of the multi-sensor information collection system was designed, and sensor internal and external parameter calibration were also carried out. A map information collection vehicle was built and field experiments were conducted. The results showed that the positioning error of the point cloud map construction method proposed in this paper is less than 0.5°, and the cumulative error of 30 m translation is less than 12 cm, which meets the actual operational requirements.

Air gap flux density measurement of PMSLM based on TMR sensing external stray magnetic field and CNN-LSTM

This paper presents a new non-invasive air gap flux density measurement method for permanent magnet synchronous linear motor (PMSLM) using tunneling magnetoresistance (TMR) sensor and convolutional neural networks-long short-term memory (CNN-LSTM) regression modeling. First, the analytical and finite element models of the air gap magnetic field of PMSLM are established as the data basis. Second, TMR sensor is used to measure the external stray magnetic density. Gramian Angular Field method combined with image similarity matching technology are used to obtain the optimal measurement position of the TMR sensor. Then, a new deep learning regression method as CNN-LSTM is introduced to establish a high-precision mapping model to realize non-invasive high-precision measurement of the air gap magnetic density by “substituting external to internal.” Finally, PMSLM prototype experimental platform with TMR sensor hardware acquisition circuit is built. Comparison confirmatory experiments with Gauss meter can verify the effectiveness and superiority of the proposed method.

Airborne Short-Baseline Millimeter Wave InSAR System Analysis and Experimental Results

For the challenges of high-precision mapping in complex terrain, a novel airborne Interferometric Synthetic Aperture Radar (InSAR) system is designed. This system, named ASMIS (Airborne Short-Baseline Millimeter-Wave InSAR System), adopts the coplanar antenna and a pod-type structure. This design makes the system lightweight and highly integrated. It can be compatible with small general aviation flight platforms. The baseline is millimeters in size, which greatly simplifies the unwrapping process. The coplanar antennas have two advantages: they maximize the baseline utilization and minimize the Doppler decorrelation and the motion error inconsistency. Acquisition campaigns of the system have been carried out in Boao, Bayannur, and Chengde, China. In the Chengde experimental area, we designed an antiparallel flight experiment to account for the topographic relief. High-precision Digital Orthophoto Maps (DOMs) and Digital Surface Models (DSMs) at a scale of 1:5000 were obtained. The coordinate Root Mean Square Error (RMSE) of the checkpoints within the obtained DSM is less than 0.82 m in altitude and 3 m horizontally. The RMSE of the Sparse Ground Control Points (GCPs) within the obtained DSM is less than 0.3 m in altitude. Experimental results from different areas, including plains, mountains, and coastlines, demonstrate the system’s performance.

Multi-Scale Feature Fusion Attention Network for Building Extraction in Remote Sensing Images

The efficient semantic segmentation of buildings in high spatial resolution remote sensing images is a technical prerequisite for land resource management, high-precision mapping, construction planning and other applications. Current building extraction methods based on deep learning can obtain high-level abstract features of images. However, the extraction of some occluded buildings is inaccurate, and as the network deepens, small-volume buildings are lost and edges are blurred. Therefore, we introduce a multi-resolution attention combination network, which employs a multiscale channel and spatial attention module (MCAM) to adaptively capture key features and eliminate irrelevant information, which improves the accuracy of building extraction. In addition, we present a layered residual connectivity module (LRCM) to enhance the expression of information at different scales through multi-level feature fusion, significantly improving the understanding of context and the capturing of fine edge details. Extensive experiments were conducted on the WHU aerial image dataset and the Massachusetts building dataset. Compared with state-of-the-art semantic segmentation methods, this network achieves better building extraction results in remote sensing images, proving the effectiveness of the method.

Research on the SLAM technology moving away from high-precision maps in the context of autonomous driving

SLAM(Simulation Localization and Mapping) technology is widely used in the fields of unmanned driving, autonomous robots and augmented reality. Real-time localization and mapping capabilities provide important support for autonomous driving. In this paper, we present a review of the implications of SLAM technology away from high-precision maps in autonomous driving scenarios, and the concept and production process of high-precision maps, as well as their role and advantages in autonomous driving, are discussed. Then, the application, significance, and advantages of SLAM technology in autonomous driving scenarios are discussed in detail, and the advantages of SLAM technology in environmental adaptability, real-time performance, cost and scalability, and safety in emergency situations are emphasized. Finally, the challenges faced by the current SLAM technology in autonomous driving are analyzed, and the development prospects of SLAM technology in the field of autonomous driving in the future are discussed.