High-definition (HD) mapping is essential for autonomous driving and localization services, providing detailed lane-level road graphs for various applications. Current methodologies primarily segment the geometric structure of lane lines from remote sensing images and extract vectorized road graphs using heuristic methods. However, these approaches fail to adequately account for lane instance information and topological structures. Furthermore, the semi-automated process imposes constraints on the spatial scalability of HD maps. To overcome these limitations, we propose AutoLRG, a two-stage method for lane-level road graph construction. In lane geometry prediction, we propose a lane segmentation network based on directional supervision and multimodal fusion, incorporating an angle-direction loss and a cross-attention-based fusion module to enhance lane perception and connectivity. In lane instance modeling, we develop a Transformer-based lane decoder, which leverages an object detection architecture to extract vectorized lane instances and road vertices in an end-to-end manner. In lane topology construction, we introduce a "road segment–intersection" decoupled model, which establishes the connectivity relationships of intersection nodes based on traffic regulations to form a lane-level topological directed road graph. The ablation studies conducted on the two benchmark datasets (UrbanLaneGraph and OpenSatMap) have validated the effectiveness of the method. Comparative experiments with other methods demonstrate that our approach exhibits superior performance in lane segmentation, instance modeling, and topology construction. Code is available at https://github.com/EchoQiHeng/AutoLRG.

Detecting vulnerable road users (VRUs) at night presents significant challenges. Numerous methods rely heavily on annotations, yet the low visibility of nighttime images poses difficulties for labeling. To obviate the need for nighttime annotations, unsupervised domain adaptation manifests as a viable solution. However, existing approaches primarily focus on semantic-level domain gaps, often overlooking pixel-level discrepancies caused by inherent degradations in the nighttime domain. These degradations can impair machine vision and limit detection performance. In this paper, we propose TripleA, an unsupervised domain adaptation framework tailored for nighttime VRU detection. TripleA includes triple alignment. First, it aligns daytime and nighttime images to generate synthetic nighttime images, which are then enhanced for illumination and noise. To remove noise, we introduce an illumination difference-aware denoising network, incorporating a novel pseudo-supervised attention to achieve pixel-wise noise distribution alignment. This alignment is driven by pseudo-ground truth generated through a carefully designed exchange-recombination strategy, facilitating self-supervised training of the denoising network. Additionally, we introduce degradation alignment to ensure domain-invariant degradation encoding, which enhances the network’s robustness for real-world nighttime images. Extensive experiments demonstrate the effectiveness of our framework for nighttime VRU detection, all without the need for annotated nighttime data.

Unmanned aerial vehicles (UAVs) have made significant contributions to landslide emergency response operations due to their precise and flexible imaging capabilities. However, the conventional workflow of generating orthophotos from UAV imagery and subsequent interpretation often exceeds the critical 72-hour rescue window. To address this challenge, this paper presents a onboard landslide extraction method for original UAV images utilizing a convolutional neural network (CNN). Given the abundance of overlapping images, the CNN is trained on labeled orthophotos. To minimize discrepancies between orthophotos and original UAV images, the proposed method integrates local and non-local features. Built upon the ResNet architecture, the method incorporates modules for extracting both shallow and deep features, enabling effective fusion through self-learning. This approach mitigates the issue of accuracy degradation caused by variations between training and testing data. Furthermore, considering the necessity of deploying the CNN-based landslide extraction model on low-power embedded platforms to achieve onboard landslide extraction, this paper introduces a quantitative model compression technique. Specifically, the model’s weight and activation value data precision are linearly mapped from 32-bit floating-point type to 8-bit integer type, guided by relative entropy minimization. This results in substantial reductions in memory access and computational complexity during model inference. Experimental results demonstrate that the proposed method yields outstanding extraction performance on both the Jiuzhaigou and Bijie landslide datasets. The time taken for extracting landslides from a single 6000x4000 pixel UAV image is reduced from 109.47 seconds to 4.75 seconds, which is less than the 5.13-second interval between camera shots, thereby achieving onboard landslide extraction.

The Internet of Things (IoT) network is one of the major sources of Big Data generation for Twin Virtual Geographic Environments (TVGE) in which ubiquitous interconnected sensors have been widely applied to monitor the urban environment, such as the air pollution in industrial parks. As the number of pollutants and the density of monitoring increase, the amount of data continues to accumulate. Challenges arise in quickly identifying the abnormal air pollutants and clearly visualizing their features. There is a necessity of having novel tools and techniques for processing the huge volume of data and transforming them into useful information and knowledge for situational awareness, risk prediction, and decision support. Aimed at dealing with these challenges, this paper proposes a sensor-based multi-modal spatial-temporal big data organization and visualization method ground on TVGE in response to imminent air pollution emergency in urban industrial parks. The proposed method dynamically expresses the real-time situation of different types of air pollution, and comprehensively analyzes diverse air pollutants from the macroscopic to the microscopic through three levels. Furthermore, this paper delivers a prototype TVGE for real-time air pollution monitoring and early warning, combing integrated data management framework, customized three-dimensional (3D) modeling techniques, and advanced data analytics.

In complex and heterogeneous geoenvironments, landslides exhibit varying features in different environments, and data in landslide inventories are imbalanced. Existing data-driven landslide susceptibility evaluation (LSE) methods overlook environmental heterogeneity and cannot reliably predict regions with few samples. Alternatively, global random negative sampling strategies may produce imbalanced positive and negative samples in some environments, contributing to inaccurate predictions. This article proposes a graph neural network (GNN) constrained by environmental consistency (GNN-EC) to overcome these problems. The GNN-EC consists of graphs with nodes, and edges. A graph represents the environmental relationships in the study area. Nodes are geographic units delineated from terrain polygon approximation. Edges capture the relationships between node-pairs. Additionally, the weights of edges reflect the similarity between two node environments. A GNN aggregates node information in the graph for LSE. Our experiment showed that the proposed method outperformed the common machine learning methods: increasing prediction accuracy by approximately 7, 5–6 and 3–4% compared to the artificial neural network (ANN), the support vector machine (SVM) and the random forest (RF), respectively. Moreover, our method can maintain high prediction accuracy, even with a small training set.

This article is focused on a challenging topic emerging from the registration of point clouds, specifically the registration of dynamic objects with low overlapping ratio. This problem is especially difficult when the static scanner is installed on a floating platform, and the objects it scans are also floating. These issues make most of the automatic registration methods and software solutions invalid. To solve this problem, explicit exploration of the static region is necessary for both the coarse and fine registration steps. Fortunately, determining the corresponding regions can be eased by the intuitive realization that in urban environments, natural objects neither present straight boundaries nor stack vertically. This intuition has guided the authors to develop a robust approach for the detection of static regions using planar structures. Then, silhouettes of the objects are extracted from the planar structures, which assist in the determination of an SE(2) transformation in the horizontal direction by a novel line matching method. The silhouettes also enable identification of the correspondences of planes in the step of fine registration using a variant of the iterative closest point method. Experimental evaluations using point clouds of cargo ships with different sizes and shapes reveal the robustness and efficiency of the proposed method, which gives 100% success and reasonable accuracy in rapid time, suitable for an online system. In addition, the proposed method is evaluated systematically with regard to several practical situations caused by the floating platform, and it demonstrates good robustness to limited scanning time and noise.

Stacked auto-encoder is mainly used for image classification and it can extract valid information from data through unsupervised pre-training and supervised fine-tuning. This paper is intended to improve the accuracy of image classification, we constructed a 6-layer stacked convolution neural network (CNN) based on stacked auto-encoders. The constructed CNN can extract effective features for image classification through greedy layer-wise training. In order to make the constructed CNN to have strong robustness to noise, we added a noisy-layer in the pre-training stage. Adding the sparsity constraint can make the training of the CNN more effective, and can also reduce data redundancy. For classification applications, our experiments show that the final classification results of the proposed model is superior to the combination of auto-encoders and the noisy auto-encoders.

Model checking is a promising technology, which has been applied for verification of many hardware and software systems. In this paper, we introduce the concept of model update towards the development of an automatic system modification tool that extends model checking functions. We define primitive update operations on the models of Computation Tree Logic (CTL) and formalize the principle of minimal change for CTL model update. These primitive update operations, together with the underlying minimal change principle, serve as the foundation for CTL model update. Essential semantic and computational characterizations are provided for our CTL model update approach. We then describe a formal algorithm that implements this approach. We also illustrate two case studies of CTL model updates for the well-known microwave oven example and the Andrew File System 1, from which we further propose a method to optimize the update results in complex system modifications.

Computation Tree Logic (CTL) model update is an approach for software verification and modification, where the minimal change principle is employed to generate admissible models that represent the corrected software design. In this paper, we apply CTL model update to models based on the well known Andrew File System protocols. We demonstrate the process of model update based on our previous theoretical results, and present a prototype implementation. Our case studies show that our model update system is sound and workable, which can be applied to different complex systems.