Search Results (67)

Illegal dumping poses serious risks to ecosystems and human health, requiring effective and timely monitoring strategies. Advances in uncrewed aerial vehicles (UAVs), photogrammetry, and deep learning (DL) have created new opportunities for detecting and characterizing waste objects over large areas. Within the framework of the EMERITUS Project, an EU Horizon Europe initiative supporting the fight against environmental crimes, this study evaluates the performance of pre-trained prompt-based multimodal (PBM) DL models integrated into ArcGIS Pro for object detection and segmentation. To test such models, UAV surveys were specially conducted at a semi-controlled test site in northern Italy, producing very high-resolution orthoimages and video frames populated with simulated waste objects such as tyres, barrels, and sand piles. Three PBM models (CLIPSeg, GroundingDINO, and TextSAM) were tested under varying hyperparameters and input conditions, including orthophotos at multiple resolutions and frames extracted from UAV-acquired videos. Results show that model performance is highly dependent on object type and imagery resolution. In contrast, within the limited ranges tested, hyperparameter tuning rarely produced significant improvements. The evaluation of the models was performed using low IoU to generalize across different types of detection models and to focus on the ability of detecting object. When evaluating the models with orthoimagery, CLIPSeg achieved the highest accuracy with F1 scores up to 0.88 for tyres, whereas barrels and ambiguous classes consistently underperformed. Video-derived (oblique) frames generally outperformed orthophotos, reflecting a closer match to model training perspectives. Despite the current limitations in performances highlighted by the tests, PBM models demonstrate strong potential for democratizing GeoAI (Geospatial Artificial Intelligence). These tools effectively enable non-expert users to employ zero-shot classification in UAV-based monitoring workflows targeting environmental crime. Full article

Establishing digital twin scenes facilitates the understanding of geospatial phenomena, representing a significant research focus for GIS scientists and engineers. However, current research on digital twin scenes modeling relies on manual intervention or the overlay of static models, resulting in low modeling efficiency and poor standardization. To address these challenges, this paper proposes a knowledge graph-guided and multimodal data fusion-driven rapid modeling method for digital twin scenes, using bridge tower construction as an illustrative example. We first constructed a knowledge graph linking the three domains of “event-object-data” in bridge tower construction. Guided by this graph, we designed a knowledge graph-guided multimodal data association and fusion algorithm. Then a rapid modeling method for bridge tower construction scenes based on dynamic data was established. Finally, a prototype system was developed, and a case study area was selected for analysis. Experimental results show that the knowledge graph we built clearly captures all elements and their relationships in bridge tower construction scenes. Our method enables precise fusion of 5 types of multimodal data: BIM, DEM, images, videos, and point clouds. It improves spatial registration accuracy by 21.83%, increases temporal fusion efficiency by 65.6%, and reduces feature fusion error rates by 70.9%. Local updates of the 3D geographic scene take less than 30 ms, supporting millisecond-level digital twin modeling. This provides a practical reference for building geographic digital twin scenes. Full article

Forest fires in Yanyuan County, a typical dry-hot valley region, pose serious threats to ecological security and public safety. Conventional fire warning methods rely heavily on manual surveys, making them time-consuming, labor-intensive, and prone to missing the critical window for effective intervention. This paper presents a 3D visualization decision support system for fire prevention, developed on a Web-GIS platform using the Cesium engine. The system integrates multi-source data, including a 12.5 m DEM, remote sensing imagery, and real-time video streams. It employs a YOLO11 model for automated fire and smoke detection, achieving a precision of 82.4%. Compared to conventional 2D systems, the platform enhances emergency response speed by 37% while significantly improving spatial awareness and operational coordination. This cross-platform tool facilitates sustainable forest management through efficient resource allocation and real-time monitoring, offering a scalable and practical solution for fire prevention in complex terrains. Full article

Converting tower-mounted videos from perspective to orthographic view is beneficial for their integration with maps and remote sensing images and can provide a clearer and more real-time data source for earth observation. This paper addresses the issue of low geometric accuracy in orthographic video generation by proposing a method that incorporates 3D GIS view matching. Firstly, a geometric alignment model between video frames and 3D GIS views is established through camera parameter mapping. Then, feature point detection and matching algorithms are employed to associate image coordinates with corresponding 3D spatial coordinates. Finally, an orthographic video map is generated based on the color point cloud. The results show that (1) for tower-based video, a 3D GIS constructed from publicly available DEMs and high-resolution remote sensing imagery can meet the spatialization needs of large-scale tower-mounted video data. (2) The feature point matching algorithm based on deep learning effectively achieves accurate matching between video frames and 3D GIS views. (3) Compared with the traditional method, such as the camera parameters method, the orthographic video map generated by this method has advantages in terms of geometric mapping accuracy and visualization effect. In the mountainous area, the RMSE of the control points is reduced from 137.70 m to 7.72 m. In the flat area, it is reduced from 13.52 m to 8.10 m. The proposed method can provide a near-real-time orthographic video map for smart cities, natural resource monitoring, emergency rescue, and other fields. Full article

Background/Objectives: Healthcare accounts for approximately 4.4% of global carbon emissions. Gastroenterology is a particularly heavy producer, with professional organisations outlining targets to move towards carbon neutrality. Missed hospital appointments, associated with poor medical outcomes, also represent physical and economic waste to the sector. COVID-19 expedited the shift toward virtual clinics, but tele-diagnostics have not expanded similarly. We aimed to assess the feasibility of a virtual C13 urea breath test clinic for H. pylori in Ireland. Methods: C13 urea breath test kits were provided to patients in the community, who were subsequently invited to book an online video appointment with a GI lab technician to assist them in performing the test at home. Completed tests were returned to the hospital via local GP, by post, or a specified hospital drop-off point, and analysed using our standard protocol. Results: 423 virtual appointments were reviewed. 135 (32%) were male, and the mean age was 42 years. The test positivity rate was 22%, similar to a matched in-person testing cohort (21%). In all, there were no non-attenders, and two cancellations. Virtual patients were more likely to attend their appointments (OR = 153.9, p = 0.0004) than in-person patients. Virtual UBT appointments saved 9943.5 Km of road journeys, equivalent to 254 person-hours of travel time and 1.24 metric tonnes of CO₂. Additionally, 300 (71%) patients returned a feedback questionnaire, of which 276 (92%) rated the overall home breath test experience as ‘good’ or ‘excellent’. Conclusions: Home testing for H. pylori is effective, acceptable, and reduces both reliance on invasive procedures such as endoscopy and carbon emissions. Full article

This study presents a validated drone-based methodology for inspecting fire protection belts in Galicia, Spain, with a focus on secondary protection belts surrounding settlements. Current manual inspection methods are limited by resource constraints and inefficiency, especially given Galicia’s steep slopes and fragmented, vegetated terrain. Our integrated approach combines high-resolution drone imagery, RTK positioning, GIS tools, and the Time2Parcel algorithm, enabling synchronized, parcel-level documentation at cadastral scale and allowing office-based technicians to directly review automatically generated video segments specific to each parcel for inspection verification. The methodology employs a hybrid classification system: automated assessments via orthophoto and LiDAR analysis and manual verification for cases with low confidence scores. Government technicians can perform office-based reviews without GIS expertise; the system automatically matches video to cadastral records, eliminating manual video review. Key results include the Time2Parcel algorithm for automatic video-to-parcel correlation, completion of inspections for 4934 parcels, and an operational efficiency increase of 68–70% reduction in inspection time compared with traditional methods. This workflow enables faster, safer, and more accurate inspections in highly fragmented rural contexts, improving legal compliance and environmental management. Full article

Traditional playground settings are often less effective in fostering STEAM (Science, Technology, Engineering, Arts, and Mathematics)-related activities, as fixed play structures tend to restrict the diversity of play behaviors and inhibit children’s ability to engage in self-directed, imaginative exploration. Using a research-through-design methodology, this study investigated how playground design (temporary landscape interventions) influences children’s engagement in informal STEAM learning activities and enhances the STEAM learning affordances of the playground. Conducted at an early learning center in Lubbock, Texas, the research involved GIS-based Environment–Behavior Mapping (E-B Mapping) and video analysis of 21 preschool-age children to compare pre- and post-intervention STEAM learning behaviors. The intervention incorporated fourteen nature-based landscape elements—such as sand and water play areas, sensory gardens, loose parts, art areas, etc.—to enhance affordances for informal STEAM activities. The results showed a marked decrease in passive behaviors and a notable rise in constructive play; collaborative interactions; and STEAM-related activities such as building, hypothesizing, observing, and experimenting. Engagement shifted away from fixed play structures to more diverse and naturalized play settings. The findings underscore the critical role of integrating diverse landscape settings and elements into playgrounds in enriching STEAM learning experiences for young children. Full article

Accurate analysis of medical videos remains a major challenge in deep learning (DL) due to the need for effective spatiotemporal feature mapping that captures both spatial detail and temporal dynamics. Despite advances in DL, most existing models in medical AI focus on static images, overlooking critical temporal cues present in video data. To bridge this gap, a novel DL-based framework is proposed for spatiotemporal feature extraction from medical video sequences. As a feasibility use case, this study focuses on gastrointestinal (GI) endoscopic video classification. A 3D convolutional neural network (CNN) is developed to classify upper and lower GI endoscopic videos using the hyperKvasir dataset, which contains 314 lower and 60 upper GI videos. To address data imbalance, 60 matched pairs of videos are randomly selected across 20 experimental runs. Videos are resized to 224 × 224, and the 3D CNN captures spatiotemporal information. A 3D version of the parallel spatial and channel squeeze-and-excitation (P-scSE) is implemented, and a new block called the residual with parallel attention (RPA) block is proposed by combining P-scSE3D with a residual block. To reduce computational complexity, a (2 + 1)D convolution is used in place of full 3D convolution. The model achieves an average accuracy of 0.933, precision of 0.932, recall of 0.944, F1-score of 0.935, and AUC of 0.933. It is also observed that the integration of P-scSE3D increased the F1-score by 7%. This preliminary work opens avenues for exploring various GI endoscopic video-based prospective studies. Full article

Background/Objectives: Potassium-competitive acid blockers (P-CABs) offer rapid gastric acid inhibition and lower toxicity compared to proton pump inhibitors (PPIs). This study investigates the drug–drug interaction between P-CABs and immunosuppressants tacrolimus and mycophenolate in kidney transplant recipients (KTRs). Methods: Sixty-two KTRs were randomized to receive either 50 mg of tegoprazan or 20 mg of pantoprazole. Patients were monitored using a smart clinical trial platform incorporating remote monitoring and safety management systems, which tracked drug adherence and vital signs. General and gastrointestinal (GI) symptoms were surveyed via a self-developed app on patients’ phones. Trough levels of tacrolimus and mycophenolate were measured every 4 weeks over 12 weeks. Results: Medication adherence was 100% in both groups. A total of 13,726 biometric data points and 5031 questionnaire responses were collected, with 5704 feedback messages and 56 video visits conducted. At 12 weeks, the mean trough levels of tacrolimus and mycophenolate were similar between the tegoprazan and pantoprazole groups (5.5 ± 1.6 vs. 5.8 ± 2.0 ng/mL, p = 0.50 and 2.7 ± 1.4 vs. 2.6 ± 1.4 µg/mL, p = 0.57, respectively). The intragroup difference in trough levels from baseline to week 12 was not significant in either group. GI symptoms scores, vital signs, and allograft function remained stable and comparable between groups. Conclusions: Tegoprazan does not alter the blood trough levels of tacrolimus and mycophenolate during the 12-week follow-up in KTRs and has a similar impact on GI symptoms as pantoprazole. This study confirms the feasibility and safety of using a smart clinical trial system with remote monitoring for randomized trials. Full article

Inflammatory bowel diseases (IBDs), comprising Crohn’s disease (CD) and ulcerative colitis (UC), are chronic immune-mediated inflammatory diseases of the gastrointestinal (GI) tract with still-elusive etiopathogeneses and an increasing prevalence worldwide. Despite the growing availability of more advanced therapies in the last two decades, there are still a number of unmet needs. For example, the achievement of mucosal healing has been widely demonstrated as a prognostic marker for better outcomes and a reduced risk of dysplasia and cancer; however, the accuracy of endoscopy is crucial for both this aim and the precise and reproducible evaluation of endoscopic activity and the detection of dysplasia. Artificial intelligence (AI) has drastically altered the field of GI studies and is being extensively applied to medical imaging. The utilization of deep learning and pattern recognition can help the operator optimize image classification and lesion segmentation, detect early mucosal abnormalities, and eventually reveal and uncover novel biomarkers with biologic and prognostic value. The role of AI in endoscopy—and potentially also in histology and imaging in the context of IBD—is still at its initial stages but shows promising characteristics that could lead to a better understanding of the complexity and heterogeneity of IBDs, with potential improvements in patient care and outcomes. The initial experience with AI in IBDs has shown its potential value in the differentiation of UC and CD when there is no ileal involvement, reducing the significant amount of time it takes to review videos of capsule endoscopy and improving the inter- and intra-observer variability in endoscopy reports and scoring. In addition, these initial experiences revealed the ability to predict the histologic score index and the presence of dysplasia. Thus, the purpose of this review was to summarize recent advances regarding the application of AI in IBD endoscopy as there is, indeed, increasing evidence suggesting that the integration of AI-based clinical tools will play a crucial role in paving the road to precision medicine in IBDs. Full article

Conventional endoscopy is limited in its ability to examine the small bowel and perform long-term monitoring due to the risk of infection and tissue perforation. Wireless Capsule Endoscopy (WCE) is a painless and non-invasive method of examining the body’s internal organs using a small camera that is swallowed like a pill. The existing active locomotion technologies do not have a practical localization system to control the capsule’s movement within the body. A robust localization system is essential for safely guiding the WCE device through the complex gastrointestinal (GI) tract. Moreover, having access to the capsule’s trajectory data is highly desirable for drug delivery and surgery, as well as for creating accurate user profiles for diagnosis and future reference. Therefore, a robust, real-time, and practical localization system is imperative to advance the field of WCE and make it desirable for clinical trials. In this work, we have identified salient features of different localization techniques and categorized studies in comprehensive tables. This study is self-contained as it offers a comprehensive overview of emerging localization techniques based on magnetic field, radio frequency (RF), video, and hybrid methods. A summary at the end of each method is provided to point out the potential gaps and give directions for future research. The main point of this work is to present an in-depth review of the most recent localization techniques published in the past five years. This will assist researchers in comprehending current techniques and pinpointing potential areas for further investigation. This review can be a significant reference and guide for future research on WCE localization. Full article

Surveillance video has emerged as a crucial data source for web Geographic Information Systems (GIS), playing a vital role in traffic management, facility monitoring, and anti-terrorism inspections. However, previous methods encountered significant challenges in achieving effective large-scale multi-video overlapping visualization and efficiency, particularly when organizing and visualizing large-scale video-augmented geographic scenes. Therefore, we propose a parallel-optimized visualization method specifically for large-scale multi-video augmented geographic scenes on Cesium. Firstly, our method employs an improved octree-based model for the unified management of large-scale overlapping videos. Then, we introduce a novel scheduling algorithm based on Cesium, which leverages a Web Graphics Library (WebGL) parallel-optimized and dynamic Level-of-Detail (LOD) strategy. This algorithm is designed to enhance the visualization effects and efficiency of large-scale video-integrated geographic scenes. Finally, we perform comparative experiments to demonstrate that our proposed method significantly optimizes the visualization of video overlapping areas and achieves a rendering efficiency increase of up to 95%. Our method can provide a solid technical foundation for large-scale surveillance video scene management and multi-video joint monitoring. Full article

Background/Objectives: As musculoskeletal injuries in gastroenterologists related to the performance of endoscopic procedures are on the rise, solutions and new approaches are needed to prevent these undesired outcomes. In our study, we evaluated an approach to ergonomic challenges in the form of a belt-like endoscope holder designed to redistribute the weight of the endoscope across the whole body of the practitioner. The aim of the study was to determine how the use of this holder affected the body posture of practitioners during endoscopy. Methods: We designed a special endoscopic model that emulates basic endoscopic movement and maneuvers. With the use of the MoCap camera system, we recorded experienced endoscopists exercising a standardized set of tasks with and without the holder. Results: Following video and statistical analyses, the most significant differences were observed in the position of the left arm which pointed to a more relaxed arm position. Conclusions: The ergonomic benefits of the belt holder in this model merit testing in the clinical setting to evaluate its effectiveness and prevention of musculoskeletal injuries in GI endoscopy. Full article

Background: Colon capsule endoscopy (CCE) is becoming more widely available across Europe, but its uptake is slow due to the need for follow-up colonoscopy for therapeutic procedures and biopsies, which impacts its cost-effectiveness. One of the major factors driving the conversion to colonoscopy is the detection of excess polyps in CCE that cannot be matched during subsequent colonoscopy. The capsule’s rocking motion, which can lead to duplicate reporting of the same polyp when viewed from different angles, is likely a key contributor. Objectives: This review aims to explore the types of polyp matching reported in the literature, assess matching techniques and matching accuracy, and evaluate the development of machine learning models to improve polyp matching in CCE and subsequent colonoscopy. Methods: A systematic literature search was conducted in EMBASE, MEDLINE, and PubMed. Due to the scarcity of research in this area, the search encompassed clinical trials, observational studies, reviews, case series, and editorial letters. Three directly related studies were included, and ten indirectly related studies were included for review. Results: Polyp matching in colon capsule endoscopy still needs to be developed, with only one study focused on creating criteria to match polyps within the same CCE video. Another study established that experienced CCE readers have greater accuracy, reducing interobserver variability. A machine learning algorithm was developed in one study to match polyps between initial CCE and subsequent colonoscopy. Only around 50% of polyps were successfully matched, requiring further optimisation. As Artificial Intelligence (AI) algorithms advance in CCE polyp detection, the risk of duplicate reporting may increase when clinicians are presented with polyp images or timestamps, potentially complicating the transition to AI-assisted CCE reading in the future. Conclusions: Polyp matching in CCE is a developing field with considerable challenges, especially in matching polyps within the same video. Although AI shows potential for decent accuracy, more research is needed to refine these techniques and make CCE a more reliable, non-invasive alternative to complement conventional colonoscopy for lower GI investigations. Full article

This research explores the impact of urban design performance qualities on pedestrian behavior in a cultural heritage site designated by UNESCO. The study employs a multi-method approach, including a questionnaire survey, empirical observation of pedestrian activities, and empirical axial line and visibility graph analysis using the space syntax technique. The first part of the study involved a questionnaire formatted as a polling sheet to gather expert assessments of spatial performance measures. The second part used a pilot survey to capture the perspectives of end users regarding the study’s objectives and their perceptions of the site. Pedestrian flow was observed using a technique called “gate counts”, with observations recorded as video clips during specific morning and afternoon periods across three pedestrian zones. The study also examined the behavioral patterns of pedestrians, including their movement patterns. Finally, the ArcGIS 10.3.1 software was employed to evaluate the reliability of the results. The main finding of this research is that pedestrian behavior and walkability in the historical areas are significantly influenced by landmark integration, wayfinding behavior, and the socio-economic functions of heritage sites. This study highlights the importance of using cognitive and syntactic analysis, community engagement, and historical preservation to enhance walkability, accessibility, and social interaction in heritage contexts. In addition, it identifies the need for improvements in urban design to address inconsistencies between syntactic maps and actual pedestrian flow, emphasizing the role of imageability and the impact of environmental and aesthetic factors on pedestrian movement. This research provides valuable insights for urban designers and planners, environmental psychologists, architects, and policymakers by highlighting the key elements that make urban spaces walkable, aiming to enhance the quality of public spaces. Full article