Search

This paper focuses on converting complex 3D maps created by LiDAR and SLAM technology into simple 2D maps to make them easier to understand. While 3D maps provide a lot of useful details for robots and computer programs, they can be difficult to read for humans who are used to flat maps. We developed a new system to clean up these 3D maps and convert them into intuitive and accurate 2D maps. The system uses three steps designed to correct different kinds of errors found in 3D LiDAR scan data: clustering-based denoising, height-based denoising, and Statistical Outlier Removal. In particular, height-based denoising is the method we propose in this paper, an algorithm that leaves only indoor structures such as walls. The paper proposes an algorithm that considers the entire range of the point cloud, rather than just the points near the ceiling, as is the case with existing methods, to make denoising more effective. This makes the final 2D map easy to understand and useful for building planning or emergency preparedness. Our main goal is to map the interior of buildings faster and more effectively, creating 2D drawings that reflect accurate and current information. We want to make it easier to use LiDAR and SLAM data in our daily work and increase productivity. [ABSTRACT FROM AUTHOR]

Roads are the fundamental elements of transportation, connecting cities and rural areas, as well as people's lives and work. They play a significant role in various areas such as map updates, economic development, tourism, and disaster management. The automatic extraction of road features from high-resolution remote sensing images has always been a hot and challenging topic in the field of remote sensing, and deep learning network models are widely used to extract roads from remote sensing images in recent years. In light of this, this paper systematically reviews and summarizes the deep-learning-based techniques for automatic road extraction from high-resolution remote sensing images. It reviews the application of deep learning network models in road extraction tasks and classifies these models into fully supervised learning, semi-supervised learning, and weakly supervised learning based on their use of labels. Finally, a summary and outlook of the current development of deep learning techniques in road extraction are provided. [ABSTRACT FROM AUTHOR]

At present, UAV aerial photography has a good prospect in agricultural production, disaster response, and other aspects. The application of UAVs can greatly improve work efficiency and decision-making accuracy. However, owing to inherent features such as a wide field of view and large differences in the target scale in UAV aerial photography images, this can lead to existing target detection algorithms missing small targets or causing incorrect detections. To solve these problems, this paper proposes a small target detection algorithm for UAV aerial photography based on improved YOLOv5s. Firstly, a small target detection layer is applied in the algorithm to improve the detection performance of small targets in aerial images. Secondly, the enhanced weighted bidirectional characteristic pyramid Mul-BiFPN is adopted to replace the PANet network to improve the speed and accuracy of target detection. Then, CIoU was replaced by Focal EIoU to accelerate network convergence and improve regression accuracy. Finally, a non-parametric attention mechanism called the M-SimAM module is added to enhance the feature extraction capability. The proposed algorithm was evaluated on the VisDrone-2019 dataset. Compared with the YOLOV5s, the algorithm improved by 7.30%, 4.60%, 5.60%, and 6.10%, respectively, in mAP@50, mAP@0.5:0.95, the accuracy rate (P), and the recall rate (R). The experiments show that the proposed algorithm has greatly improved performance on small targets compared to YOLOv5s. [ABSTRACT FROM AUTHOR]

Object detection in images captured by unmanned aerial vehicles (UAVs) holds great potential in various domains, including civilian applications, urban planning, and disaster response. However, it faces several challenges, such as multi-scale variations, dense scenes, complex backgrounds, and tiny-sized objects. In this paper, we present a novel scale-adaptive YOLO framework called SMFF-YOLO, which addresses these challenges through a multi-level feature fusion approach. To improve the detection accuracy of small objects, our framework incorporates the ELAN-SW object detection prediction head. This newly designed head effectively utilizes both global contextual information and local features, enhancing the detection accuracy of tiny objects. Additionally, the proposed bidirectional feature fusion pyramid (BFFP) module tackles the issue of scale variations in object sizes by aggregating multi-scale features. To handle complex backgrounds, we introduce the adaptive atrous spatial pyramid pooling (AASPP) module, which enables adaptive feature fusion and alleviates the negative impact of cluttered scenes. Moreover, we adopt the Wise-IoU(WIoU) bounding box regression loss to enhance the competitiveness of different quality anchor boxes, which offers the framework a more informed gradient allocation strategy. We validate the effectiveness of SMFF-YOLO using the VisDrone and UAVDT datasets. Experimental results demonstrate that our model achieves higher detection accuracy, with AP50 reaching 54.3% for VisDrone and 42.4% for UAVDT datasets. Visual comparative experiments with other YOLO-based methods further illustrate the robustness and adaptability of our approach. [ABSTRACT FROM AUTHOR]

In landslide disaster warning, a variety of monitoring and warning methods are commonly adopted. However, most monitoring and warning methods cannot provide information in advance, and serious losses are often caused when landslides occur. To advance the warning time before a landslide, an innovative advance landslide prediction and warning model based on a stacking fusion algorithm using Baishuihe landslide data is proposed in this paper. The Baishuihe landslide area is characterized by unique soil and is in the Three Gorges region of China, with a subtropical monsoon climate. Based on Baishuihe historical data and real-time monitoring of the landslide state, four warning level thresholds and trigger conditions for each warning level are established. The model effectively integrates the results of multiple prediction and warning submodels to provide predictions and advance warnings through the fusion of two stacking learning layers. The possibility that a risk priority strategy can be used as a substitute for the stacking model is also discussed. Finally, an experimental simulation verifies that the proposed improved model can not only provide advance landslide warning but also effectively reduce the frequency of false warnings and mitigate the issues of traditional single models. The stacking model can effectively support disaster prevention and reduction and provide a scientific basis for land use management. [ABSTRACT FROM AUTHOR]

Regarding the problem of epidemic outbreak prevention and control, infectious disease dynamics models cannot support urban managers in reducing urban-scale healthcare costs through community-scale control measures, as they usually have difficulty meeting the requirements for simulation at different scales. In this paper, we propose combining contact networks at different spatial scales to study the COVID-19 outbreak in Shanghai from March to July 2022, calculate the initial R t through the number of cases at the beginning of the outbreak, and evaluate the effectiveness of dynamic non-pharmaceutical interventions (NPIs) adopted at different time periods in Shanghai using our proposed approach. In particular, our proposed contact network is a three-layer multi-scale network that is used to distinguish social interactions occurring in areas of different sizes, as well as to distinguish between intensive and non-intensive population contacts. This susceptible–exposure–infection–quarantine–recovery (SEIQR) epidemic model constructed based on a multi-scale network can more effectively assess the feasibility of small-scale control measures, such as assessing community quarantine measures and mobility restrictions at different moments and phases of an epidemic. Our experimental results show that this model can meet the simulation needs at different scales, and our further discussion and analysis show that the spread of the epidemic in Shanghai from March to July 2022 can be successfully controlled by implementing a strict long-term dynamic NPI strategy. [ABSTRACT FROM AUTHOR]

When an indoor disaster occurs, the disaster site can become very difficult to escape from due to the scenario or building. Most people evacuate when a disaster situation occurs, but there are also disaster victims who cannot evacuate and are isolated. Isolated disaster victims often cannot move quickly because they do not have all the necessary information about the disaster, and secondary damage can occur. Rescue workers must rescue disaster victims quickly, before secondary damage occurs, but it is not always easy to locate isolated victims within a disaster site. In addition, rescue operators can also suffer from secondary damage because they are exposed to disaster situations. We present a HHD technique that can detect isolated victims in indoor disasters relatively quickly, especially when covered by fire smoke, by merging one-stage detectors YOLO and RetinaNet. HHD is a technique with a high human detection rate compared to other techniques while using a 1-stage detector method that combines YOLO and RetinaNet. Therefore, the HHD of this paper can be beneficial in future indoor disaster situations. [ABSTRACT FROM AUTHOR]

The Loess Plateau is an ecologically fragile area in China; furthermore, loess landslides are typical forms of geological disasters, which severely limit the sustainable development of the local societies and the economy. Studying the automatic detection of landslides can facilitate disaster prevention and mitigation in the Loess Plateau, and help realize the climate action goal (SDG 13) of the United Nations Sustainable Development Goals (SDGs). This paper takes typical loess areas in China as the research object, and establishes a historical loess landslide sample database based on Google Earth (GEE) image data, with a total of 1451 loess landslides. The automatic detection of loess landslides is implemented by improving the You Only Look Once X (YOLOX) algorithm. The results show that the average accuracy of landslide detection in this method is 95.43%, and the accuracy rate is 96.32%, which effectively combines the earth's big data to realize the automatic detection of loess landslides. The research results provide technical support for the promotion of disaster prevention and mitigation in China's loess regions, the realization of sustainable development goals, and the improvement of natural disaster prevention–resistance–reduction systems. [ABSTRACT FROM AUTHOR]

Street view images are emerging as new street-level sources of urban environmental information. Accurate detection and quantification of urban air conditioners is crucial for evaluating the resilience of urban residential areas to heat wave disasters and formulating effective disaster prevention policies. Utilizing street view image data to predict the spatial coverage of urban air conditioners offers a simple and effective solution. However, detecting and accurately counting air conditioners in complex street-view environments remains challenging. This study introduced 3D parameter-free attention and coordinate attention modules into the target detection process to enhance the extraction of detailed features of air conditioner external units. It also integrated a small target detection layer to address the challenge of detecting small target objects that are easily missed. As a result, an improved algorithm named SC4-YOLOv7 was developed for detecting and recognizing air conditioner external units in street view images. To validate this new algorithm, we extracted air conditioner external units from street view images of residential buildings in Guilin City, Guangxi Zhuang Autonomous Region, China. The results of the study demonstrated that SC4-YOLOv7 significantly improved the average accuracy of recognizing air conditioner external units in street view images from 87.93% to 91.21% compared to the original YOLOv7 method while maintaining a high speed of image recognition detection. The algorithm has the potential to be extended to various applications requiring small target detection, enabling reliable detection and recognition in real street environments. [ABSTRACT FROM AUTHOR]

This paper presents a new method, based on clustering and thresholding, to automatically perform binary change detection in multitemporal spectral indices. The method is denoted as Buffer-From-Cluster Approach (BFCA). To estimate the distributions of changed and unchanged pixels, as needed for the purpose of a reliable thresholding of a spectral index, a clustering algorithm is preliminarily applied to identify image objects possibly corresponding to areas where significant changes occurred. Then, a buffer zone is created around the selected cluster to identify unchanged areas surrounding changed ones. The cluster and the buffer zone are jointly analyzed to estimate the distributions of changed and unchanged pixels and to verify that they can be distinguished from each other. Finally, the results of thresholding and clustering are combined to generate the binary change map. The BFCA has been conceived to map the extent of the areas affected by a natural disaster like wildfire. To validate the proposed method, burned area maps produced by applying the BFCA to spectral indices derived from Sentinel-2 data have been compared to maps produced by the Copernicus Emergency Management Service. For testing the multi-hazard detection capability, the same kind of exercise has been carried out for a flooding test case too. The positive results of the comparison have confirmed the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Flood risk assessment is an important tool for disaster warning and prevention. In this study, an integrated approach based on a D-number-improved analytic hierarchy process (D-AHP) and a self-organizing map (SOM) clustering algorithm are proposed for urban flooding risk assessment. The urban flood inundation model and geographic information system (GIS) technology were used to quantify the assessment indices of urban flood risk. The D-AHP approach was adopted to determine the weights of the indices, which effectively makes up for the shortcomings of the AHP in dealing with uncertain evaluation information (such as fuzzy and incomplete information). In addition, the SOM clustering algorithm was applied to determine the flood risk level. It is a data-driven approach that avoids the subjective determination of a flood risk classification threshold. The proposed approach for flood risk assessment was implemented in Zhengzhou, China. The flood risk was classified into five levels: highest risk, higher risk, medium risk, lower risk, and the lowest risk. The proportion of the highest risk areas was 9.86%; such areas were mainly distributed in the central and eastern parts of the Jinshui District, the eastern part of the Huiji District, and the northeastern part of the Guancheng District, where there were low terrain and serious waterlogging. The higher risk areas accounted for 24.26% of the study area, and were mainly distributed in the western and southern parts of the Jinshui District, the southern part of the Huiji District, the middle and eastern parts of the Zhongyuan District, the northeastern part of the Erqi District, and the northwestern part of the Guancheng District, which consisted of economically developed areas of dense population and buildings, matching well with historical flooding events. To verify the effectiveness of the proposed approach, traditional approaches for risk assessment were compared. The comparison indicated that the proposed approach is more reasonable and accurate than the traditional approaches. This study showed the potential of a novel approach to flood risk assessment. The results can provide a reference for urban flood management and disaster reduction in the study area. [ABSTRACT FROM AUTHOR]

Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on machine learning to evaluate susceptibility to rotational landslides in an area near Cuenca city, Ecuador, which has a high incidence of these phenomena, mainly due to its environmental conditions, and in which, however, such studies are scarce. The implemented method consisted of an artificial neural network multilayer perceptron (ANN MLP), generated with the neuralnet R package, with which, by means of different backpropagation algorithms (RPROP+, RPROP−, SLR, SAG, and Backprop), five landslide susceptibility maps (LSMs) were generated for the study area. A landslide inventory updated to 2019 and 10 conditioning factors, mainly topographical, geological, land cover, and hydrological, were considered. The results obtained, which were validated through the AUC-ROC value and statistical parameters of precision, recall, accuracy, and F-Score, showed a good degree of adjustment and an acceptable predictive capacity. The resulting maps showed that the area has mostly sectors of moderate, high, and very high susceptibility, whose landslide occurrence percentages vary between approximately 63% and 80%. In this research, different variants of the backpropagation algorithm were implemented to verify which one gave the best results. With the implementation of additional methodologies and correct zoning, future analyses could be developed, contributing to adequate territorial planning and better disaster risk management in the area. [ABSTRACT FROM AUTHOR]

Regional landslide identification is important for the risk management of landslide hazards. The traditional methods of regional landslide identification were mainly conducted by a human being. In previous studies, automatic landslide recognition mainly focused on new landslides distinct from the environment induced by rainfall or earthquake, using the image classification method and semantic segmentation method of deep learning. However, there is a lack of research on the automatic recognition of old loess landslides, which are difficult to distinguish from the environment. Therefore, this study uses the object detection method of deep learning to identify old loess landslides with Google Earth images. At first, a database of loess historical landslide samples was established for deep learning based on Google Earth images. A total of 6111 landslides were interpreted in three landslide areas in Gansu Province, China. Second, three object detection algorithms including the one-stage algorithm RetinaNet and YOLO v3 and the two-stage algorithm Mask R-CNN, were chosen for automatic landslide identification. Mask R-CNN achieved the greatest accuracy, with an AP of 18.9% and F1-score of 55.31%. Among the three landslide areas, the order of identification accuracy from high to low was Site 1, Site 2, and Site 3, with the F1-scores of 62.05%, 61.04% and 50.88%, respectively, which were positively related to their recognition difficulty. The research results proved that the object detection method can be employed for the automatic identification of loess landslides based on Google Earth images. [ABSTRACT FROM AUTHOR]

Urban floods repeatedly threaten Barcelona, damaging the city infrastructure and endangering the safety of the population. The urban planning of the city, the socioeconomic distribution, its topography, and the characteristics of precipitation systems translate into these flood events having a heterogeneous effect across the city. It means that the coping capacity has a strong dependence on local factors that must be considered when management plans are developed by the municipality. This work aims to contribute to the better knowledge of precipitation structures associated with heavy rainfall events and floods in Barcelona based on radar data and an urban rain gauge network. Radar data have been provided by the Meteorological Service of Catalonia (SMC), while precipitation data, impact data, and early warnings, have been provided by Barcelona Cicle de l'Aigua S.A. (BCASA), for the period 2013–2018. A new radar-based methodology has been developed to identify convective rainfall structures from radar reflectivity volumes (CAPPI and TOP products) to make the analysis easier. The high computing speed of the procedure allows efficient analysis of a large set of convective cells without scarifying temporal resolution of radar data. Both rainfall fields (radar and rain gauge, respectively) have been compared. Then through the identified rainfall convective structures, thunderstorm hotspots have been identified. Considering an alert indicator from BCASA and the reported incidents, episodes with the highest impact have been analysed in depth. Results show 207 significant rainfall episodes in the ROI for the six years, which are mainly concentrated between September and November. The fact that significant episodes are usually produced by highly convective rain corroborates the advantage of using radar images as a tool to detect any maxima even when no rain gauge is there. In 64 of the episodes, the level of pre-alert was achieved with a maximum frequency between August and September. The proposed algorithm shows more than 8000 centroids of convective cells from 189 cases. Whilst maximum surface reflectivity over 45 dBZ is more prone to occur near the coastline, the centroids of storm cells tend to concentrate more inland. The final objective is to improve the actions taken by the organisation responsible for managing urban floods, which have seen Barcelona recognised as a model city for flood resilience by the United Nations. [ABSTRACT FROM AUTHOR]

Estimating the damaged area after a forest fire is important for responding to this natural catastrophe. With the support of aerial remote sensing, typically with unmanned aerial vehicles (UAVs), the aerial imagery of forest-fire areas can be easily obtained; however, retrieving the burnt area from the image is still a challenge. We implemented a new approach for segmenting burnt areas from UAV images using deep learning algorithms. First, the data were collected from a forest fire in Andong, the Republic of Korea, in April 2020. Then, the proposed two-patch-level deep-learning models were implemented. A patch-level 1 network was trained using the UNet++ architecture. The output prediction of this network was used as a position input for the second network, which used UNet. It took the reference position from the first network as its input and refined the results. Finally, the final performance of our proposed method was compared with a state-of-the-art image-segmentation algorithm to prove its robustness. Comparative research on the loss functions was also performed. Our proposed approach demonstrated its effectiveness in extracting burnt areas from UAV images and can contribute to estimating maps showing the areas damaged by forest fires. [ABSTRACT FROM AUTHOR]

Soil moisture is a key environmental variable, important to e.g., farmers, meteorologists, and disaster management units. We fuse surface soil moisture (SSM) estimates from spatio-temporally complementary radar sensors through temporal filtering of their joint signal and obtain a kilometre-scale, daily soil water content product named SCATSAR-SWI. With 25 km Metop ASCAT SSM and 1 km Sentinel-1 SSM serving as input, the SCATSAR-SWI is globally applicable and achieves daily full coverage over operated areas. We employ a near-real-time-capable SCATSAR-SWI algorithm on a fused 3 year ASCAT-Sentinel-1-SSM data cube over Italy, obtaining a consistent set of model parameters, unperturbed by coverage discontinuities. An evaluation of a therefrom generated SCATSAR-SWI dataset, involving a 1 km Soil Water Balance Model (SWBM) over Umbria, yields comprehensively high agreement with the reference data (median R = 0.61 vs. in situ; 0.71 vs. model; 0.83 vs. ASCAT SSM). While the Sentinel-1 signal is attenuated to some extent, the ASCAT's signal dynamics are fully transferred to the SCATSAR-SWI and benefit from the Sentinel-1 parametrisation. Using the SM2RAIN approach, the SCATSAR-SWI shows excellent capability to reproduce 5 day-accumulated rainfall over Italy, with R = 0.89 against observed rainfall. The SCATSAR-SWI is currently in preparation towards operational product dissemination in the Copernicus Global Land Service (CGLS). [ABSTRACT FROM AUTHOR]