Cesare Davide Pace, Alessandro Marco De Nunzio, Claudio De Stefano
et al.
Markerless biomechanics increasingly relies on 3D skeletal keypoints extracted from video, yet downstream biomechanical mappings typically treat these estimates as deterministic, providing no principled mechanism for frame-wise quality control. In this work, we investigate predictive uncertainty as a quantitative measure of confidence for mapping 3D pose keypoints to 3D anatomical landmarks, a critical step preceding inverse kinematics and musculoskeletal analysis. Within a temporal learning framework, we model both uncertainty arising from observation noise and uncertainty related to model limitations. Using synchronized motion capture ground truth on AMASS, we evaluate uncertainty at frame and joint level through error--uncertainty rank correlation, risk--coverage analysis, and catastrophic outlier detection. Across experiments, uncertainty estimates, particularly those associated with model uncertainty, exhibit a strong monotonic association with landmark error (Spearman $ρ\approx 0.63$), enabling selective retention of reliable frames (error reduced to $\approx 16.8$ mm at 10% coverage) and accurate detection of severe failures (ROC-AUC $\approx 0.92$ for errors $>50$ mm). Reliability ranking remains stable under controlled input degradation, including Gaussian noise and simulated missing joints. In contrast, uncertainty attributable to observation noise provides limited additional benefit in this setting, suggesting that dominant failures in keypoint-to-landmark mapping are driven primarily by model uncertainty. Our results establish predictive uncertainty as a practical, frame-wise tool for automatic quality control in markerless biomechanical pipelines.
We present an empirical case study of cinema SDR-to-HDR mapping using ASC StEM2, a rare common-source dataset containing EXR scene-referred images and matched SDR/HDR cinema release masters from the same ACES-based mastering workflow. Based on pixel-wise statistics over all 18,580 frames of the test film, we construct a three-domain comparison involving EXR source data, SDR release masters, and HDR release masters to characterize their luminance and color structural relationships within this controlled workflow. In the luminance dimension, SDR and HDR masters exhibit a highly stable global monotonic correspondence, with geometric structure remaining largely consistent overall; sparse and structured deviations appear in self-luminous highlights and specific material regions. In the color dimension, the two masters remain largely consistent in hue, with saturation exhibiting a redistribution pattern of shadow suppression, midtone expansion, and highlight convergence. Using EXR as a scene-referred anchor, we further define a pixel-level decision map that operationally separates EXR-closer recovery regions from content-adaptive adjustment regions. Under this operational definition, 82.4% of sampled image regions are classified as EXR-closer recovery, while the remainder require localized adaptive adjustment. Rather than claiming a universal law for all cinema mastering pipelines, the study provides an interpretable quantitative baseline for structure-aware SDR-to-HDR analysis and for designing learning-based models under shared-source mastering conditions.
Стаття присвячена інтелектуалізації електронні геодезичні прилади (ЕГП) та розробленню концептуальних основ інтеграції технологій штучного інтелекту (ШІ) в геоінформаційне середовище (ГІС) з метою підвищення ефективності систем просторового управління. У досліджені представлено розроблену архітектурну модель інтелектуалізованої системи просторового управління, яка включає взаємодію електронних приладів, сенсорних модулів, ГІС-платформ та аналітичних ШІ-сервісів. Запропоновано концепцію інтелектуалізації ЕГП, яка ґрунтується на трьох основних векторах: автономність вимірювального процесу (за допомогою машинного навчання МН для розпізнавання об’єктів, самодіагностики), адаптивність до умов навколишнього середовища (через корекцію впливу навколишнього середовища, зменшення шуму) та інтегративність у ГІС. У роботі описано застосування ШІ-методів, включаючи глибинні нейронні мережі (YOLO, Mask R-CNN, U-Net, PointNet) для автоматичної детекції та класифікації об’єктів на зображеннях і хмарах точок, а також для оцінювання та корекції GNSS-похибок у реальному часі за допомогою нейро-Калманівських фільтрів. Практичні напрями впровадження моделі включають автоматизований моніторинг деформацій інженерних споруд та інтелектуальну обробку даних БПЛА для оновлення топографічних планів. Згідно з висновками, поетапна інтеграція ШІ перетворює ЕГП на інтелектуальні сенсори, здатні самостійно оцінювати якість даних та взаємодіяти з ГІС, що забезпечує надійну основу для «розумних» міст та стійкого територіального розвитку.
Ключові слова: інтелектуалізація, штучний інтелект (ШІ), електронні геодезичні прилади (ЕГП), ГІС-середовище, системи просторового управління, детекція об’єктів, GNSS-корекція.
Judy Long, Tao Liu, Sean Alexander Woznicki
et al.
Crop mapping involves identifying and classifying crop types using spatial data, primarily derived from remote sensing imagery. This study presents the first comprehensive review of large-scale, pixel-wise crop mapping workflows, encompassing both conventional supervised methods and emerging transfer learning approaches. To identify the optimal time-series generation approaches and supervised crop mapping models, we conducted systematic experiments, comparing six widely adopted satellite image-based preprocessing methods, alongside eleven supervised pixel-wise classification models. Additionally, we assessed the synergistic impact of varied training sample sizes and variable combinations. Moreover, we identified optimal transfer learning techniques for different magnitudes of domain shift. The evaluation of optimal methods was conducted across five diverse agricultural sites. Landsat 8 served as the primary satellite data source. Labels come from CDL trusted pixels and field surveys. Our findings reveal three key insights. First, fine-scale interval preprocessing paired with Transformer models consistently delivered optimal performance for both supervised and transferable workflows. RF offered rapid training and competitive performance in conventional supervised learning and direct transfer to similar domains. Second, transfer learning techniques enhanced workflow adaptability, with UDA being effective for homogeneous crop classes while fine-tuning remains robust across diverse scenarios. Finally, workflow choice depends heavily on the availability of labeled samples. With a sufficient sample size, supervised training typically delivers more accurate and generalizable results. Below a certain threshold, transfer learning that matches the level of domain shift is a viable alternative to achieve crop mapping. All code is publicly available to encourage reproducibility practice.
Cadastral mapping is a critical component of establishing a legal land administration system. Currently, an estimated 70% of the global population lacks access to formalized land rights through such systems, highlighting the urgency of accelerating the mapping of property rights. This study introduces an innovative methodology that integrates advanced deep learning techniques with remote sensing imagery to automate the extraction of cadastral boundaries. Our proposed model, CadNet, significantly outperforms baseline models. Moreover, CadNet is trained on a more extensive and diverse dataset than recent studies in this field. The results demonstrate a robust framework for advancing research in cadastral mapping leveraging deep learning and remote sensing technologies. Our codebase is available at https://github.com/jeroengrift/cadnet
This study investigates the use of unmanned aerial vehicles (UAVs) for geodetic surveys aimed at updating cadastral registers, which now function as geospatial databases. UAVs, using the aerial photogrammetric method, offer a cost-effective and efficient alternative to traditional airplane-mounted cameras. The research presents a comprehensive, step-by-step procedure for creating cadastral maps using UAV-acquired data, covering scope definition, preparatory work, flight planning, data processing, and final map production. The study includes an analysis of the resulting cadastral map and compares it with existing official maps to assess accuracy in determining parcel boundaries. The findings demonstrate that UAV-based surveys not only streamline the mapping process but also provide high levels of accuracy and reliability. This approach showcases the potential of UAV technology in modernizing cadaster systems, offering valuable insights into improving the precision and efficiency of geospatial data collection for land management and planning.
As a new technology in the surveying and mapping geographic information industry, UAV tilt photogrammetry has the advantages of high efficiency and is less restricted by environmental factors. The cadastral survey was carried out with the advantages of this method. After accuracy check, the mean square error of boundary points was 3 cm and the gross error rate was 3.92%, the mean square error of boundary length was 2.8 cm and the gross error rate was 3%. The results showed that the method of UAV tilt photography can be better applied to the cadastral survey in plain areas, and meet the basic requirements of accuracy.
An image processing unit (IPU), or image signal processor (ISP) for high dynamic range (HDR) imaging usually consists of demosaicing, white balancing, lens shading correction, color correction, denoising, and tone-mapping. Besides noise from the imaging sensors, almost every step in the ISP introduces or amplifies noise in different ways, and denoising operators are designed to reduce the noise from these sources. Designed for dynamic range compressing, tone-mapping operators in an ISP can significantly amplify the noise level, especially for images captured in low-light conditions, making denoising very difficult. Therefore, we propose a joint multi-scale denoising and tone-mapping framework that is designed with both operations in mind for HDR images. Our joint network is trained in an end-to-end format that optimizes both operators together, to prevent the tone-mapping operator from overwhelming the denoising operator. Our model outperforms existing HDR denoising and tone-mapping operators both quantitatively and qualitatively on most of our benchmarking datasets.
We prove several rigidity properties for random quotients of mapping class groups of surfaces, namely whose kernel is normally generated by the n-th steps of finitely many independent random walks. Firstly, we generalise a celebrated theorem of Ivanov's: every automorphism of the corresponding quotient of the curve graph is induced by a mapping class. Next, we show that, if a finitely generated group is quasi-isometric to a random quotient, then the two groups are weakly commensurable. This uses techniques from the world of hierarchically hyperbolic groups: indeed, in the process we clarify a proof of Behrstock, Hagen, and Sisto on the quasi-isometric rigidity of mapping class groups, which might possibly be applied to other hierarchically hyperbolic groups. Finally, we show that the automorphisms groups of our quotients, as well as their abstract commensurators, coincide with the groups themselves. Our results hold for a wider family of quotients, namely those whose kernel act by sufficiently large translations on the curve graph. This class also includes quotients by suitable powers of a pseudo-Anosov element.
In many western countries, publicly led mapping activities and recording information of land parcels and buildings and the related rights, restrictions, and responsibilities have established their roles as important pillars of a functioning society. National mapping, cadastral, and land registry authorities as public agencies responsible for conducting these tasks are in a key position in shaping the development of the whole land administration sector. Most of these authorities have formulated their purposes, directions, and goals in the form of strategies. There is, however, a lack of understanding of the type of goals these authorities pursue through their strategies and why. Using an online questionnaire as a method, this study explores the strategy goals as well as the strategy drivers of national mapping, cadastral, and land registry authorities. We find that the strategy goals converge to a great extent and relate particularly to digitalization, data properties, customers and needs of society, and organizational development. Further, we observe that the strategy work of these authorities is most often driven by changes in the customer needs and by changes in the government’s policies. The contribution of the study lies in providing an overview of how national mapping, cadastral, and land registry authorities frame their near-future development and in highlighting that albeit the goals, for the most part, align with the qualities of a good, neutral land administration system, the authorities show low tendency to pursue transformative or paradigmatic changes through their strategies.
Siamo giunti al 2022, si intravedono nel mondo XR tendenze di sviluppo considerevolmente significative, destinate pertanto a svilupparsi ed evolvere nei prossimi anni, e con esse stanno prendendo forma più concreta i vari aspetti della ricerca afferente al settore, soprattutto per quanto concerne il cosiddetto Design Esperienziale.
Ciò che si verifica nell’interazione con i mondi artefatti immersivi ed interattivi costituisce una novità nel campo della percezione umana e pertanto ora che il sentiero di sviluppo delle tecnologie abilitanti sembra essersi stabilizzato e sulla via del perfezionamento, l’attenzione della ricerca si rivolge anche allo studio dei comportamenti umani nel processo interattivo con i nuovi ecosistemi.
Device localization and radar-like mapping are at the heart of integrated sensing and communication, enabling not only new services and applications, but can also improve communication quality with reduced overheads. These forms of sensing are however susceptible to data association problems, due to the unknown relation between measurements and detected objects or targets. In this chapter, we provide an overview of the fundamental tools used to solve mapping, tracking, and simultaneous localization and mapping (SLAM) problems. We distinguish the different types of sensing problems and then focus on mapping and SLAM as running examples. Starting from the applicable models and definitions, we describe the different algorithmic approaches, with a particular focus on how to deal with data association problems. In particular, methods based on random finite set theory and Bayesian graphical models are introduced in detail. A numerical study with synthetic and experimental data is then used to compare these approaches in a variety of scenarios.
During the past years, unmanned aerial vehicles (UAVs) gained importance as a tool to quickly collect high-resolution imagery as base data for cadastral mapping. However, the fact that UAV-derived geospatial information supports decision-making processes involving people’s land rights ultimately raises questions about data quality and accuracy. In this vein, this paper investigates different flight configurations to give guidance for efficient and reliable UAV data acquisition. Imagery from six study areas across Europe and Africa provide the basis for an integrated quality assessment including three main aspects: (1) the impact of land cover on the number of tie-points as an indication on how well bundle block adjustment can be performed, (2) the impact of the number of ground control points (GCPs) on the final geometric accuracy, and (3) the impact of different flight plans on the extractability of cadastral features. The results suggest that scene context, flight configuration, and GCP setup significantly impact the final data quality and subsequent automatic delineation of visual cadastral boundaries. Moreover, even though the root mean square error of checkpoint residuals as a commonly accepted error measure is within a range of few centimeters in all datasets, this study reveals large discrepancies of the accuracy and the completeness of automatically detected cadastral features for orthophotos generated from different flight plans. With its unique combination of methods and integration of various study sites, the results and recommendations presented in this paper can help land professionals and bottom-up initiatives alike to optimize existing and future UAV data collection workflows.
We extend the Levi-Civita (L-C) and Kustaanheimo-Stiefel (K-S) regularization methods that maps the classical system where a particle moves under the combined influence of $\frac{1}{r}$ and $r^2$ potentials to a harmonic oscillator with inverted sextic potential and interactions to corresponding quantum mechanical counterparts, both in 2 and 3 dimensions. Using the perturbative solutions of the Schrödinger equation of the later systems, we derive the eigen spectrum of the Hydrogen atom in presence of an additional harmonic potential. We have also obtained the mapping of a particle moving in the shifted harmonic potential to H-atom using Bohlin-Sundman transformation, for quantum regime. Exploiting this equivalence, the solution to the Schrödinger equation of the former is obtained from the solutions of the later.
Julia Velastegui-Cáceres, Víctor M. Rodríguez-Espinosa, Oswaldo Padilla-Almeida
As 3D cadastres offer advantages in several areas by providing information with greater accuracy and a high level of detail, a diagnosis of the cadastral situation is required prior to the implementation of a 3D cadastral model. Therefore, this study focuses on diagnosing the urban cadastral situation in Ecuador based on an analysis of eight cantonal decentralized autonomous governments that were selected primarily for the availability of their cadastral information. The twelve characteristics included in the analysis supported the definition of a cadastral development scale based on the fulfillment of each characteristic. The official cadastral databases, meetings, and interviews with personnel related to the cadastres were used in the analysis to gain in-depth knowledge of the situation in each canton. The findings demonstrated that most cantons had similar characteristics and are at an intermediate level of cadastral development. Therefore, there is the need for cantons to have standardized cadastral information in accordance with national and international regulations. Thus, in this research, we developed an initial Ecuadorian land administration domain model country profile to initiate the transition towards 3D cadastre.
Bujar Fetai, Krištof Oštir, Mojca Kosmatin Fras
et al.
In order to transcend the challenge of accelerating the establishment of cadastres and to efficiently maintain them once established, innovative, and automated cadastral mapping techniques are needed. The focus of the research is on the use of high-resolution optical sensors on unmanned aerial vehicle (UAV) platforms. More specifically, this study investigates the potential of UAV-based cadastral mapping, where the ENVI feature extraction (FX) module has been used for data processing. The paper describes the workflow, which encompasses image pre-processing, automatic extraction of visible boundaries on the UAV imagery, and data post-processing. It shows that this approach should be applied when the UAV orthoimage is resampled to a larger ground sample distance (GSD). In addition, the findings show that it is important to filter the extracted boundary maps to improve the results. The results of the accuracy assessment showed that almost 80% of the extracted visible boundaries were correct. Based on the automatic extraction method, the proposed workflow has the potential to accelerate and facilitate the creation of cadastral maps, especially for developing countries. In developed countries, the extracted visible boundaries might be used for the revision of existing cadastral maps. However, in both cases, the extracted visible boundaries must be validated by landowners and other beneficiaries.
This paper investigates the relationship between strata of abelian differentials and various mapping class groups afforded by means of the topological monodromy representation. Building off of prior work of the authors, we show that the fundamental group of a stratum surjects onto the subgroup of the mapping class group which preserves a fixed framing of the underlying Riemann surface, thereby giving a complete characterization of the monodromy group. In the course of our proof we also show that these "framed mapping class groups" are finitely generated (even though they are of infinite index) and give explicit generating sets.
A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation. In PDI, a deep convolutional neural network (CNN) is used to represent the multivariate Gaussian distribution as the approximate posterior distribution of susceptibility given the input measured field. Such CNN is first trained on healthy subjects via posterior density estimation, where the training dataset contains samples from the true posterior distribution. Domain adaptations are then deployed on patient datasets with new pathologies not included in pre-training, where PDI updates the pre-trained CNN's weights in an unsupervised fashion by minimizing the Kullback-Leibler divergence between the approximate posterior distribution represented by CNN and the true posterior distribution from the likelihood distribution of a known physical model and pre-defined prior distribution. Based on our experiments, PDI provides additional uncertainty estimation compared to the conventional MAP approach, while addressing the potential issue of the pre-trained CNN when test data deviates from training.
On 12 January 2010, a terrible earthquake struck the Caribbean state of Haiti. In addition to the numerous victims and the huge damages, the earthquake seriously damaged the port of the capital, Port-au-Prince. In particular, it completely destroyed the 450-meter North Pier, dedicated to the container traffic, making it impossible to disembark humanitarian aid and goods.
Given the strategic importance of the infrastructure, the Ministry of Economy and Finance of Haiti has financed the design and reconstruction of Port-au-Prince, starting from the North pier.
After the earthquake, the first step was a series of bathymetric, hydrogeological, topographical and aerial surveys realized by an Italian company.