Search Results (42)

Robust visual perception and geometric alignment are crucial for intelligent automation in various domains, such as industrial processes and infrastructure monitoring. Accurately aligning structured visual elements, such as floor markings or road-marking templates, is essential for tasks like automated guidance, verification, and condition assessment. However, traditional feature-based methods struggle with templates that feature simple geometries and lack rich textures, making reliable feature matching and alignment difficult, even under controlled conditions. To address this, we propose GeoTemplateKPNet, a novel self-supervised deep-learning framework, built upon Convolutional Neural Networks (CNNs), designed to learn robust, geometrically consistent keypoints specifically in synthetic template images. The model is trained exclusively in a synthetic template dataset by enforcing equivariance to geometric transformations and utilizing self-supervised losses, including inside mask loss, peakiness loss, repulsion loss, and keypoint-driven image reprojection loss, thereby eliminating the need for manual keypoint annotations. We evaluate the method in a synthetic template test set, using metrics such as a keypoint-matching comparison, the Inside Mask Rate (IMR), and the Alignment Reconstruction Error (ARE). The results demonstrate that GeoTemplateKPNet successfully learns to predict meaningful keypoints on template structures, enabling accurate alignment between templates and their transformed counterparts. Ablation studies reveal that the number of keypoints (K) impacts the performance, with K = 3 providing the most suitable balance for the overall alignment accuracy, although the performance varies across different template geometries. GeoTemplateKPNet offers a foundational self-supervised solution for the robust geometric analysis of templates, which is crucial for downstream alignment tasks and applications. Full article

Arecaceae (palms) play a crucial role for native communities and wildlife in the Amazon region. This study presents a first-of-its-kind regional-scale spatial cataloging of palms using remotely sensed data for the country of Guyana. Using very high-resolution satellite images from the GeoEye-1 and WorldView-2 sensor platforms, which collectively cover an area of 985 km², a total of 472,753 individual palm crowns are detected with F1 scores of 0.76 and 0.79, respectively, using a convolutional neural network (CNN) instance segmentation model. An example of CNN model transference between images is presented, emphasizing the limitation and practical application of this approach. A method is presented to optimize precision and recall using the confidence of the detection features; this results in a decrease of 45% and 31% in false positive detections, with a moderate increase in false negative detections. The sensitivity of the CNN model to the size of the training set is evaluated, showing that comparable metrics could be achieved with approximately 50% of the samples used in this study. Finally, the diameter of the palm crown is calculated based on the polygon identified by mask detection, resulting in an average of 7.83 m, a standard deviation of 1.05 m, and a range of {4.62, 13.90} m for the GeoEye-1 image. Similarly, for the WorldView-2 image, the average diameter is 8.08 m, with a standard deviation of 0.70 m and a range of {4.82, 15.80} m. Full article

Generating aerial shoreline segmentation masks can be a daunting task, often requiring manual labeling or correction. This is further problematic because neural segmentation models require decent and abundant data for training, requiring even more manpower to automate the process. In this paper, we propose utilizing Unmanned Surface Vehicles (USVs) in an automated shoreline segmentation system on satellite imagery. The remotely controlled vessel first collects above- and underwater shoreline information using light detection and ranging (LiDAR) and multibeam echosounder (MBES) measuring instruments, resulting in a geo-referenced 3D point cloud. After cleaning and processing these data, the system integrates the projected map with an aerial image of the region. Based on the height values of the mapped points, the image is segmented. Finally, post-processing methods and the k-NN algorithm are introduced, resulting in a complete binary shoreline segmentation mask. The obtained data were used for training U-Net-type segmentation models with pre-trained backbones. The InceptionV3-based model achieved an accuracy of 96% and a dice coefficient score of 93%, demonstrating the effectiveness of the proposed system as a source of data acquisition for training deep neural networks. Full article

Geomasking is a set of techniques that introduces noise or intentional errors into geospatial data to minimize the risk of identifying exact location information related to individuals while preserving the utility of the data to a controlled extent. It protects the geoprivacy of the data contributor and mitigates potential harm from data breaches while promoting safer data sharing. The development of digital health technologies and the extensive use of individual geospatial data in health studies have raised concerns about geoprivacy. The individual tracking data and health information, if accessed by unauthorized parties, may lead to privacy invasions, criminal activities, and discrimination. These risks underscore the importance of robust protective measures in the collection, management, and sharing of sensitive data. Geomasking techniques have been developed to safeguard geoprivacy in geospatial health data, addressing the risks and challenges associated with data sharing. This entry paper discusses the importance of geoprivacy in geospatial health data and introduces various kinds of geomasking methods and their applications in balancing the protection of individual privacy with the need for data sharing to ensure scientific reproducibility, highlighting the urgent need for more effective geomasking techniques and their applications. Full article

Point cloud registration is one of the fundamental tasks in computer vision, but faces challenges under low overlap conditions. Recent approaches use transformers and overlapping masks to improve perception, but mask learning only considers Euclidean distances between features, ignores mismatches caused by fuzzy geometric structures, and is often computationally inefficient. To address these issues, we introduce a novel matching framework. Firstly, we fuse adaptive graph convolution with PPF features to obtain rich feature perception. Subsequently, we construct a PGT framework that uses GeoTransformer and combines it with location information encoding to enhance the geometry perception between source and target clouds. In addition, we improve the visibility of overlapping regions through information exchange and the AIS module, aiming at subsequent keypoint extraction, preserving points with distinct geometrical structures while suppressing the influence of non-overlapping regions to improve computational efficiency. Finally, the mask is refined through contrast learning to preserve geometric and distance similarity, which helps to compute the transformation parameters more accurately. We have conducted comprehensive experiments on synthetic and real-world scene datasets, demonstrating superior registration performance compared to recent deep learning methods. Our approach shows remarkable improvements of 68.21% in $R_{RMSE}$ and 76.31% in $t_{RMSE}$ on synthetic data, while also excelling in real-world scenarios with enhancements of 76.46% in $R_{RMSE}$ and 45.16% in $t_{RMSE}$. Full article

Studies addressing the supervised extraction of geospatial elements from aerial imagery with semantic segmentation operations (including road surface areas) commonly feature tile sizes varying from 256 × 256 pixels to 1024 × 1024 pixels with no overlap. Relevant geo-computing works in the field often comment on prediction errors that could be attributed to the effect of tile size (number of pixels or the amount of information in the processed image) or to the overlap levels between adjacent image tiles (caused by the absence of continuity information near the borders). This study provides further insights into the impact of tile overlaps and tile sizes on the performance of deep learning (DL) models trained for road extraction. In this work, three semantic segmentation architectures were trained on data from the SROADEX dataset (orthoimages and their binary road masks) that contains approximately 700 million pixels of the positive “Road” class for the road surface area extraction task. First, a statistical analysis is conducted on the performance metrics achieved on unseen testing data featuring around 18 million pixels of the positive class. The goal of this analysis was to study the difference in mean performance and the main and interaction effects of the fixed factors on the dependent variables. The statistical tests proved that the impact on performance was significant for the main effects and for the two-way interaction between tile size and tile overlap and between tile size and DL architecture, at a level of significance of 0.05. We provide further insights and trends in the predictions of the extensive qualitative analysis carried out with the predictions of the best models at each tile size. The results indicate that training the DL models on larger tile sizes with a small percentage of overlap delivers better road representations and that testing different combinations of model and tile sizes can help achieve a better extraction performance. Full article

Despite impressive progress, obtaining appropriate data for instance-level lane segmentation remains a significant challenge. This limitation hinders the refinement of granular lane-related applications such as lane line crossing surveillance, pavement maintenance, and management. To address this gap, we introduce a benchmark for lane instance segmentation called InstLane. To the best of our knowledge, InstLane constitutes the first publicly accessible instance-level segmentation standard for lane line detection. The complexity of InstLane emanates from the fact that the original data are procured using cameras mounted laterally, as opposed to traditional front-mounted sensors. InstLane encapsulates a range of challenging scenarios, enhancing the generalization and robustness of the lane line instance segmentation algorithms. In addition, we propose GeoLaneNet, a real-time, geometry-aware lane instance segmentation network. Within GeoLaneNet, we design a finer localization of lane proto-instances based on geometric features to counteract the prevalent omission or multiple detections in dense lane scenarios resulting from non-maximum suppression (NMS). Furthermore, we present a scheme that employs a larger receptive field to achieve profound perceptual lane structural learning, thereby improving detection accuracy. We introduce an architecture based on partial feature transformation to expedite the detection process. Comprehensive experiments on InstLane demonstrate that GeoLaneNet can achieve up to twice the speed of current State-Of-The-Artmethods, reaching 139 FPS on an RTX3090 and a mask AP of 73.55%, with a permissible trade-off in AP, while maintaining comparable accuracy. These results underscore the effectiveness, robustness, and efficiency of GeoLaneNet in autonomous driving. Full article

A typhoon disaster is a common meteorological disaster that seriously impacts natural ecology, social economy, and even human sustainable development. It is crucial to access the typhoon disaster information, and the corresponding disaster prevention and reduction strategies. However, traditional question and answering (Q&A) methods exhibit shortcomings like low information retrieval efficiency and poor interactivity. This makes it difficult to satisfy users’ demands for obtaining accurate information. Consequently, this work proposes a typhoon disaster knowledge Q&A approach based on LLM (T5). This method integrates two technical paradigms of domain fine-tuning and retrieval-augmented generation (RAG) to optimize user interaction experience and improve the precision of disaster information retrieval. The process specifically includes the following steps. First, this study selects information about typhoon disasters from open-source databases, such as Baidu Encyclopedia and Wikipedia. Utilizing techniques such as slicing and masked language modeling, we generate a training set and 2204 Q&A pairs specifically focused on typhoon disaster knowledge. Second, we continuously pretrain the T5 model using the training set. This process involves encoding typhoon knowledge as parameters in the neural network’s weights and fine-tuning the pretrained model with Q&A pairs to adapt the T5 model for downstream Q&A tasks. Third, when responding to user queries, we retrieve passages from external knowledge bases semantically similar to the queries to enhance the prompts. This action further improves the response quality of the fine-tuned model. Finally, we evaluate the constructed typhoon agent (Typhoon-T5) using different similarity-matching approaches. Furthermore, the method proposed in this work lays the foundation for the cross-integration of large language models with disaster information. It is expected to promote the further development of GeoAI. Full article

This paper describes the creation of a fast, deterministic, 3D fractal cloud renderer for the AFIT Sensor and Scene Emulation Tool (ASSET). The renderer generates 3D clouds by ray marching through a volume and sampling the level-set of a fractal function. The fractal function is distorted by a displacement map, which is generated using horizontal wind data from a Global Forecast System (GFS) weather file. The vertical windspeed and relative humidity are used to mask the creation of clouds to match realistic large-scale weather patterns over the Earth. Small-scale detail is provided by the fractal functions which are tuned to match natural cloud shapes. This model is intended to run quickly, and it can run in about 700 ms per cloud type. This model generates clouds that appear to match large-scale satellite imagery, and it reproduces natural small-scale shapes. This should enable future versions of ASSET to generate scenarios where the same scene is consistently viewed from both GEO and LEO satellites from multiple perspectives. Full article

With the emergence of the Smart City concept, the rapid advancement of urban three-dimensional (3D) reconstruction becomes imperative. While current developments in the field of 3D reconstruction have enabled the generation of 3D products such as Digital Surface Models (DSM), challenges persist in accurately reconstructing shadows, handling occlusions, and addressing low-texture areas in very-high-resolution remote sensing images. These challenges often lead to difficulties in calculating satisfactory disparity maps using existing stereo matching methods, thereby reducing the accuracy of 3D reconstruction. This issue is particularly pronounced in urban scenes, which contain numerous super high-rise and densely distributed buildings, resulting in large disparity values and occluded regions in stereo image pairs, and further leading to a large number of mismatched points in the obtained disparity map. In response to these challenges, this paper proposes a method to refine the disparity in urban scenes based on open-source GIS data. First, we register the GIS data with the epipolar-rectified images since there always exists unignorable geolocation errors between them. Specifically, buildings with different heights present different offsets in GIS data registering; thus, we perform multi-modal matching for each building and merge them into the final building mask. Subsequently, a two-layer optimization process is applied to the initial disparity map based on the building mask, encompassing both global and local optimization. Finally, we perform a post-correction on the building facades to obtain the final refined disparity map that can be employed for high-precision 3D reconstruction. Experimental results on SuperView-1, GaoFen-7, and GeoEye satellite images show that the proposed method has the ability to correct the occluded and mismatched areas in the initial disparity map generated by both hand-crafted and deep-learning stereo matching methods. The DSM generated by the refined disparity reduces the average height error from 2.2 m to 1.6 m, which demonstrates superior performance compared with other disparity refinement methods. Furthermore, the proposed method is able to improve the integrity of the target structure and present steeper building facades and complete roofs, which are conducive to subsequent 3D model generation. Full article

Proton exchange membrane fuel cell (PEMFC) is a renewable energy source rapidly approaching commercial viability. The performance is significantly affected by the transfer of fluid, charges, and heat; gas diffusion layer (GDL) is primarily concerned with the consistent transfer of these components, which are heavily influenced by the material and design. High-efficiency GDL must have excellent thermal conductivity, electrical conductivity, permeability, corrosion resistance, and high mechanical characteristics. The first step in creating a high-performance GDL is selecting the appropriate material. Therefore, titanium is a suitable substitute for steel or carbon due to its high strength-to-weight and superior corrosion resistance. The second crucial parameter is the fabrication method that governs all the properties. This review seeks to comprehend numerous fabrication methods such as tape casting, 3D printing, freeze casting, phase separation technique, and lithography, along with the porosity controller in each process such as partial sintering, input design, ice structure, pore agent, etching time, and mask width. Moreover, other GDL properties are being studied, including microstructure and morphology. In the future, GeoDict simulation is highly recommended for optimizing various GDL properties, as it is frequently used for other porous materials. The approach can save time and energy compared to intensive experimental work. Full article

Vietnam has one of the most intensively energy-exploited riverscapes in Asia with at least 720 hydropower facilities of various capacities currently in operation or in some stage of construction. These facilities represent about 26 GW of installed capacity. This degree of domestic exploitation is often overshadowed by the geopolitically contested manipulation of the waters of the international Mekong River. In contrast, the utilization of Vietnam’s hydropower resources has unfolded gradually and largely unremarked for more than half a century. This perspective argues that the harnessing of rivers and streams for electricity generation is the result of not only the country’s abundant hydrologic resources, but also its history, culture, and (geo)politics. The paper traces the processes that have produced this high level of river exploitation, its ambiguous history, and the uncertain future of hydropower in Vietnam in the context of sustainability. Further, the renewed interest in dam-building in recent years is part of a “theater of decarbonization” that masks the operation of powerful domestic and international lobbies with an interest in “heavy engineering” projects that will do little to meet the nation’s rapidly growing electricity needs but will likely incur detrimental ecological and sociological impacts. The paper ends by positing that rather than forging ahead with the construction of additional small hydropower facilities, a more ecologically and socially equitable policy could instead critically examine the sustainability of existing capabilities, resolve the factors limiting the development of other renewable sources of energy, and face the fundamental challenge of curbing energy use. Full article

Geolocation is a fundamental component of route planning and navigation for unmanned vehicles, but GNSS-based geolocation fails under denial-of-service conditions. Cross-view geo-localization (CVGL), which aims to estimate the geographic location of the ground-level camera by matching against enormous geo-tagged aerial (e.g., satellite) images, has received a lot of attention but remains extremely challenging due to the drastic appearance differences across aerial–ground views. In existing methods, global representations of different views are extracted primarily using Siamese-like architectures, but their interactive benefits are seldom taken into account. In this paper, we present a novel approach using cross-view knowledge generative techniques in combination with transformers, namely mutual generative transformer learning (MGTL), for CVGL. Specifically, by taking the initial representations produced by the backbone network, MGTL develops two separate generative sub-modules—one for aerial-aware knowledge generation from ground-view semantics and vice versa—and fully exploits the entirely mutual benefits through the attention mechanism. Moreover, to better capture the co-visual relationships between aerial and ground views, we introduce a cascaded attention masking algorithm to further boost accuracy. Extensive experiments on challenging public benchmarks, i.e., CVACT and CVUSA, demonstrate the effectiveness of the proposed method, which sets new records compared with the existing state-of-the-art models. Our code will be available upon acceptance. Full article

Accurate monitoring of rice phenology is critical for crop management, cultivars breeding, and yield estimating. Previously, research for phenology detection relied on time-series data and orthomosaic and manually plotted regions, which are difficult to automate. This study presented a novel approach for extracting and mapping phenological traits directly from the unmanned aerial vehicle (UAV) photograph sequence. First, a multi-stage rice field segmentation dataset containing four growth stages and 2600 images, namely PaddySeg, was built. Moreover, an efficient Ghost Bilateral Network (GBiNet) was proposed to generate trait masks. To locate the trait of each pixel, we introduced direct geo-locating (DGL) and incremental sparse sampling (ISS) techniques to eliminate redundant computation. According to the results on PaddySeg, the proposed GBiNet with 91.50% mean-Intersection-over-Union (mIoU) and 41 frames-per-second (FPS) speed outperformed the baseline model (90.95%, 36 FPS), while the fastest GBiNet_t reached 62 FPS which was 1.7 times faster than the baseline model, BiSeNetV2. Additionally, the measured average DGL deviation was less than 1% of the relative height. Finally, the mapping of rice phenology was achieved by interpolation on trait value–location pairs. The proposed approach demonstrated great potential for automatic rice phenology stage surveying and mapping. Full article

Thanks to the development of geographic information technology, geospatial representation learning based on POIs (Point-of-Interest) has gained widespread attention in the past few years. POI is an important indicator to reflect urban socioeconomic activities, widely used to extract geospatial information. However, previous studies often focus on a specific area, such as a city or a district, and are designed only for particular tasks, such as land-use classification. On the other hand, large-scale pre-trained models (PTMs) have recently achieved impressive success and become a milestone in artificial intelligence (AI). Against this background, this study proposes the first large-scale pre-training geospatial representation learning model called GeoBERT. First, we collect about 17 million POIs in 30 cities across China to construct pre-training corpora, with 313 POI types as the tokens and the level-7 Geohash grids as the basic units. Second, we pre-train GeoEBRT to learn grid embedding in self-supervised learning by masking the POI type and then predicting. Third, under the paradigm of “pre-training + fine-tuning”, we design five practical downstream tasks. Experiments show that, with just one additional output layer fine-tuning, GeoBERT outperforms previous NLP methods (Word2vec, GloVe) used in geospatial representation learning by 9.21% on average in F1-score for classification tasks, such as store site recommendation and working/living area prediction. For regression tasks, such as POI number prediction, house price prediction, and passenger flow prediction, GeoBERT demonstrates greater performance improvements. The experiment results prove that pre-training on large-scale POI data can significantly improve the ability to extract geospatial information. In the discussion section, we provide a detailed analysis of what GeoBERT has learned from the perspective of attention mechanisms. Full article