Jul 2026· ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XI-2-2026, pp. 615-622· 1 citation· 6 references
Abstract
Abstract. To robustly support glacier calving monitoring at high temporal resolution and enable future AI-based calving forecasts, this study presents an optimized Multi-Epoch Multi-Imagery (MEMI) strategy for automated 4D point cloud model generation. To date, the dataset comprises over 160,000 images acquired since December 2024 by an autonomous multi-camera system operating at 30 min intervals at Glacier Perito Moreno (GPM), Argentina. Despite high scene variability and harsh environmental conditions, the proposed MEMI workflow effectively addresses constraints imposed by continuous glacier motion and image degradation. The enhanced strategy aims to generate precise dense clouds with high alignment accuracy and computational efficiency, forming the basis for subsequent analysis of glacier front evolution. To achieve this, various parameter configurations are evaluated, including AI-based image masking and adaptive, optimized alignment-adjustment settings. Results from a representative eight-day subset show that variations in the tie point computation strategy lead to measurable differences in alignment-adjustment efficiency, with the best configuration being about 11 % faster than the least efficient one. By contrast, adaptive alignment-adjustment consistently improves alignment accuracy. Moreover, masking enhances both image quality checking and reconstruction quality, and, albeit modestly, improves pre-failure deformation analysis. Furthermore, daily seasonal responses to alignment are observed, as accuracy varies with solar illumination relative to the camera positions. Applying the optimal configuration to 260 MEMI projects in under 42 h produced 518 high-precision dense clouds and detected calving retreat magnitudes of up to 17.5m, demonstrating the robustness and scalability of the proposed MEMI strategy for high-temporal-resolution 4D point cloud generation.
Abstract. We propose a systematic stepwise optimization pipeline for building change detection in dense urban environments using high-resolution CAS500-1 satellite imagery. To support robust model development, we constructed a dataset comprising 3,816 bi-temporal patch pairs across 28 urban regions. The framework employs a Mamba-based architecture as the baseline, leveraging its efficient global context modeling capability for binary change detection. The pipeline integrates three sequential optimization stages to enhance detection accuracy and stability. First, we evaluated normalization techniques tailored for 12-bit radiometric resolution, comparing percentile-based scaling, gamma correction, and log transformations. Second, we implemented an augmentation strategy that extends standard geometric transformations with optical and temporal methods to improve generalization in structurally complex urban settings. Third, we explored various ensemble configurations, including confidence-weighted and hierarchical aggregation to mitigate individual model scale limitations. Performance was validated through multi-faceted evaluation metrics covering pixel-level, contour-based, and object-based metrics. Experimental results demonstrate that gamma-based normalization, comprehensive augmentation, and hierarchical ensemble consistently outperform baseline configurations across multiple evaluation metrics. The final optimized pipeline achieved an F1-Score of 0.8070, making a significant improvement over the 0.7629 baseline. This work provides an extensible framework for operational satellite-based change detection and establishes a practical foundation for future ensemble-based architectures.
DongHyuk Jin, Junhwa Chi· The International Archives o...· 0 citations
Experimental results demonstrate that the adapted SAM2 model achieves stable segmentation under moderate environmental variability, while degrading under severe visibility loss, consistent across model scales and input resolutions.
Bindusara Nagathihalli Lokesh, Laura Camila Duran Vergara, Hans-Gerd Maas et al.· The International Archives o...· 1 citation
Monitoring glacier surface wetness and near-surface facies evolution with high spatiotemporal resolution is important for characterizing seasonal melt conditions and supporting downstream glaciological modeling. However, current remote sensing methods are hindered by cloud contamination in optical data and ambiguities in SAR backscatter interpretation. In this study, a novel framework for automated glacier surface-state mapping is proposed by integrating Sentinel-1 SAR and Sentinel-2 optical imagery. Pixel-wise wet snow probability maps are generated using a convolutional neural network trained on multitemporal optical data, which then guides an adaptive thresholding scheme for SAR-based wet snow detection. Finally, the wet snow maps are refined through a postprocessing scheme that leverages temporal consistency and spatial segmentation, and classification stability is significantly enhanced. The proposed algorithm is evaluated over three glaciers on the Tibetan Plateau using carefully constructed remote-sensing reference labels. The results show agreement with the reference labels, with mean F1-scores of 0.849 for Shenshe Glacier, 0.811 for Laohugou Glacier No.12, and 0.858 for Bayi Glacier, with peak values exceeding 0.93 during mid-season observations. The results also indicate relatively stable agreement under varying signal conditions. This study provides a flexible and transferable strategy for mapping wet-snow extent, wet-snow timing, and glacier surface facies evolution, which can provide useful constraints for subsequent mass-balance and runoff modelling in complex mountainous terrain.
Zhenzhao Xing, Xin Zhou, Lingxiao Peng et al.· IEEE Journal of Selected Top...· 0 citations
Abstract. Satellite imagery offers a distinct advantage in Earth observation by providing expansive coverage and enabling the monitoring of inaccessible regions without physical on-site intervention, serving as a significantly more cost-effective and scalable alternative to traditional aerial or ground-based surveys. The task of 3D reconstruction from multi-view satellite images has therefore been a pivotal point of research at the intersection of photogrammetry and remote sensing. Recently, novel-view synthesis techniques such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have accelerated the accuracy and speed of topographic modeling. Among these, Earth Observation Gaussian Splatting (EOGS) has emerged as a state-of-the-art approach by adapting 3DGS to handle the unique geometric and radiometric characteristics of satellite data, including Rational Polynomial Coefficients (RPCs) and varying solar conditions. However, the standard EOGS pipeline relies on stochastic initialization, where Gaussians are distributed uniformly within a volumetric bounding box, leading to high computational overhead and dependency on aggressive pruning that can inadvertently remove critical geometric features, particularly in areas with complex urban structures. To address these limitations, we propose Bundle-Adjusted Initialization for Earth Observation Gaussian Splatting, which leverages sparse point clouds from bundle adjustment as geometric priors for Gaussian initialization. Combined with an adaptive densification strategy, our method achieves faster convergence and improved DSM accuracy on the DFC2019 dataset compared to the EOGS baseline.
Jiyong Kim, Shuang Song, Rongjun Qin· The International Archives o...· 0 citations
Abstract. Climate change is driving an increase in the frequency and intensity of extreme events in mountainous environments, amplifying geomorphological hazards and the need for accurate multi-temporal topographic monitoring. However, the integration of multi-source datasets remains challenging due to geolocation inconsistencies, heterogeneous data quality, and complex terrain conditions.This study presents a systematic benchmarking framework to evaluate the performance of local point cloud registration algorithms and their impact on geomorphological change detection. Three widely used methods—Iterative Closest Point (ICP), Point-to-Plane ICP, and Generalized ICP (GICP)—were tested across two alpine case studies in Italy (Rio Cucco catchment and Belvedere Glacier), considering different surface types and initial alignment conditions.Results demonstrate that registration performance is strongly controlled by surface morphology, with rocky areas ensuring stable and accurate alignment, while vegetated surfaces introduce significant uncertainties. Point-to-Plane ICP emerges as the most computationally efficient method, whereas GICP provides improved robustness under complex conditions.The study further highlights that integrating robust outlier rejection significantly improves statistical consistency and reduces LoD95. The proposed approach provides a reproducible framework for optimizing co-registration strategies and improving the accuracy of geomorphological monitoring in high-relief environments.
Tommaso Mainiero, Jad Ghantous, N. Grasso et al.· The International Archives o...· 0 citations
Abstract. In this paper, we propose a basic workflow for the automatic extraction of glacier contours from high-resolution multi-temporal 3D point clouds. Based on the hypothesis, that glacier movements cause changes in multi-temporal surface models, glacier contours can be detected even in scenarios where glacier margins are not clearly visible, such as in the case of debris-covered glaciers and rock glaciers. After applying a robust registration algorithm, glacier and non-glacier points are filtered in several steps and spatial resolutions based on dense clusters of significantly changed points. Finally, the glacier margin is mapped using a contour extraction algorithm. The method is applied to various datasets in two scenarios: first, to a slightly debris-covered glacier in Norway; second, to a rock glacier in the Austrian Alps. The results clearly demonstrate the basic functionality of the proposed method. However, morphological changes not caused by glacier movement limit the effectiveness of the filtering, which relies exclusively on density-based elevation changes. Against this background, future work will focus on incorporating additional features, such as velocity fields and prior knowledge of rock glacier dynamics, into the point cloud filtering.
S. Isfort, M. Elias, Hans-Gerd Maas· The International Archives o...· 0 citations