Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (6,807)

Search Parameters:
Keywords = ground images

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
24 pages, 7800 KB  
Article
Effects of Spatial Resolution on Reflectance Responses to Soil Salinity in Plastic-Mulched Farmland
by Weitong Ma, Wenting Han, Xin Cui, Liyuan Zhang, Yaxiao Niu and Xinyang Fu
Agronomy 2026, 16(9), 863; https://doi.org/10.3390/agronomy16090863 (registering DOI) - 24 Apr 2026
Abstract
Spectral remote sensing enables efficient acquisition of large-scale land surface information and is a key approach for monitoring soil salinity content (SSC). However, surface mulching significantly alters the spectral reflectance responses of croplands, increasing the uncertainty of SSC retrieval using remote sensing. This [...] Read more.
Spectral remote sensing enables efficient acquisition of large-scale land surface information and is a key approach for monitoring soil salinity content (SSC). However, surface mulching significantly alters the spectral reflectance responses of croplands, increasing the uncertainty of SSC retrieval using remote sensing. This study aimed to systematically identify SSC-sensitive spectral features under different mulching conditions and to evaluate the effects of spatial resolution on SSC–spectral relationships. Multi-resolution datasets were constructed based on plastic mulch geometric parameters, and SSC–spectral relationships were analyzed using correlation methods and recursive feature elimination (RFE). Results indicate that under near-ground ultra-high-resolution conditions, the correlation between inter-mulch bare soil spectral features and SSC was weakly influenced by mulch type, and distinguishing mulch types provides limited improvement in inter-variable relationships. Pearson’s r exceeded 0.40 for both white- and black-mulched samples, and distinguishing mulch types provided only marginal gains in model accuracy (RFR–RFE R2 = 0.9524 for white-mulched and 0.9252 without distinguishing; R2 = 0.9387 for black-mulched). In contrast, under multi-resolution settings at the field scale, separating black-mulched, white-mulched, and non-mulched fields significantly enhanced the correlation between spectral indices (SIs) and SSC, with the coefficient of determination (R2) based on the recursive feature elimination (RFE) algorithm increasing by up to 0.28. The highly sensitive SIs of non-mulched farmland are generally consistent with those of white-mulched farmland but differ markedly from those of black-mulched farmland. Scale optimization analysis further indicated that the optimal spatial resolution was 1.35 m for white-mulched and non-mulched farmland. Black-mulched farmland performed best at 5.4 m, likely because stronger spectral masking by black mulch increases mixed-pixel dominance and benefits from spatial aggregation. These findings provide methodological guidance and practical approaches to accurately retrieve SSC in plastic-mulched croplands and to determine the optimal image spatial resolution. Full article
(This article belongs to the Special Issue Smart Agriculture for Crop Phenotyping)
19 pages, 9670 KB  
Article
The Comparison of Selected Approaches to 3D Reconstruction of Anatomical Structures Based on Synthetic Data for Use in Medical Diagnostics
by Miłosz Komada, Zbigniew Omiotek, Piotr Lichograj, Magda Konieczna and Natalia Krukar
Electronics 2026, 15(9), 1812; https://doi.org/10.3390/electronics15091812 - 24 Apr 2026
Abstract
There are numerous benefits associated with creating digital copies of anatomical structures, which can be used during patient diagnosis. Such models can be used not only for visualization, but also in order to assess the condition of the patient. As advances in both [...] Read more.
There are numerous benefits associated with creating digital copies of anatomical structures, which can be used during patient diagnosis. Such models can be used not only for visualization, but also in order to assess the condition of the patient. As advances in both medical imaging and 3D graphics are made, it is necessary to determine areas of application of the known reconstruction algorithms. Specifically, it is crucial to find advantages and disadvantages of known approaches to mesh generation, depending on the properties of the object and compare the quality of their results. In order to provide reliable ground-truth data, three 3D models with features resembling those identified in anatomical structures have been created. Based on these meshes, sets of CT-like DICOM images have been generated. Five different reconstruction approaches were proposed: using 3D occupancy information directly, two ways of obtaining point clouds and two methods that utilize Signed Distance Field. A neural network architecture for the SDF upsampling has also been presented. The obtained results justify the popularity of the Marching Cubes algorithm, as it produced accurate reconstructions most reliably. However, for certain scenarios, promising alternatives have been found. The presented outcomes make it clear that the approach to reconstruction must be tailored to the specific problem. Full article
Show Figures

Figure 1

25 pages, 3097 KB  
Article
Healthcare AI as Critical Digital Health Infrastructure: A Public Health Preparedness Framework for Systemic Risk
by Nikolay Lipskiy and Stephen V. Flowerday
Future Internet 2026, 18(5), 232; https://doi.org/10.3390/fi18050232 - 24 Apr 2026
Abstract
Healthcare artificial intelligence (AI) is moving from the laboratory into the infrastructure of care. As these systems become embedded in imaging, electronic health records, triage, and clinical decision support, their failures can affect not only individual encounters but also institutions and patient populations. [...] Read more.
Healthcare artificial intelligence (AI) is moving from the laboratory into the infrastructure of care. As these systems become embedded in imaging, electronic health records, triage, and clinical decision support, their failures can affect not only individual encounters but also institutions and patient populations. Yet governance still centers on model development, local validation, and one-time compliance, with limited attention to cross-site failure after deployment. This article examines how public health preparedness can help close that gap. It presents a conceptual analysis grounded in two cases: a pneumonia-screening convolutional neural network that learned institutional confounders rather than portable clinical signals, and a widely deployed sepsis prediction model whose external performance and alert burden fell short of developer claims. Together, these cases reveal five governance features of systemic healthcare AI risk: population-level exposure, cascade effects across shared infrastructures, unequal vulnerability, delayed recognition, and coordination needs beyond any single institution. In response, we propose a tripartite framework combining stronger pre-deployment assurance, post-deployment surveillance with escalation thresholds, and tertiary response through investigation, rollback, remediation, and cross-site learning. The argument is not that AI failures are epidemics, but that high-impact clinical AI systems now function as critical digital health infrastructure requiring preparedness alongside lifecycle oversight. Full article
(This article belongs to the Section Techno-Social Smart Systems)
Show Figures

Figure 1

20 pages, 4123 KB  
Article
Surveying Techniques for Built Heritage Conservation: A Comparative Perspective of Workflows for Monument Restoration
by George Cristian, Sorin Herban, Clara-Beatrice Vîlceanu, Andreea-Diana Clepe and Carmen Grecea
Sustainability 2026, 18(9), 4237; https://doi.org/10.3390/su18094237 (registering DOI) - 24 Apr 2026
Abstract
This study presents a comparative evaluation of three modern surveying techniques—UAV photogrammetry, static tripod-based LiDAR scanning, and handheld mobile LiDAR—applied in the context of historic monument restoration. The focus is on analysing workflow efficiency, data accuracy, and adaptability to complex architectural features, including [...] Read more.
This study presents a comparative evaluation of three modern surveying techniques—UAV photogrammetry, static tripod-based LiDAR scanning, and handheld mobile LiDAR—applied in the context of historic monument restoration. The focus is on analysing workflow efficiency, data accuracy, and adaptability to complex architectural features, including interior wall paintings, which are integral to the monument’s heritage value. Particular attention is given to how each technique captures surface texture, color fidelity, and material deterioration. The study also examines performance around intricate architectural elements such as vaulted ceilings, apses, cornices, columns, and carved stone portals, where occlusions, tight clearances, and fine ornamentation challenge coverage and resolution. By evaluating the strengths and limitations of each approach, the research highlights methodological considerations relevant for conservation professionals. The results indicate that the Static TLS is the most demanding workflow, requiring complex total station integration for control and station points. It produced the highest data density, with acquisition rates of one million points per second, making it the most hardware-intensive and difficult to manipulate. UAV photogrammetry provided a balanced middle-ground; it required minimal physical effort during acquisition and produced datasets that were significantly easier to manage. Handheld SLAM LiDAR emerged as the most productive solution for rapid coverage. While the handheld scanner’s image quality was lower than the photogrammetry, it still provided enough detail for the structural assessment and documentation needed. Although the point cloud lacked the extreme geometric detail provided by the TLS, the FARO Connect software made georeferencing and data manipulation significantly more efficient. Full article
12 pages, 4014 KB  
Communication
Anthropogenic Vessel Strike as a Threat to Spotted Seals (Phoca largha) in Korean Waters: A Multimodal Forensic Investigation
by Ji-Hyung Park, Hae Suk Choi, Daji Noh, Sooyoung Choi, Seung Hyeok Seok, Sang Wha Kim and Adams Hei Long Yuen
Animals 2026, 16(9), 1306; https://doi.org/10.3390/ani16091306 - 23 Apr 2026
Abstract
The spotted seal (Phoca largha) is a flagship species and natural monument inhabiting Korean coastal waters. Due to its conservation importance and the rarity of carcass discoveries, determining the cause of death of each individual is critical. A juvenile female spotted [...] Read more.
The spotted seal (Phoca largha) is a flagship species and natural monument inhabiting Korean coastal waters. Due to its conservation importance and the rarity of carcass discoveries, determining the cause of death of each individual is critical. A juvenile female spotted seal carcass was discovered on the eastern coast of Korea in May 2025. External examination revealed multiple parallel lacerations consistent with propeller strike injuries. Post-mortem computed tomography (PMCT) was performed prior to necropsy to provide a comprehensive forensic analysis. CT imaging revealed the longest wound measured 10.49 cm in length and 1.58 cm in depth, suggesting a minimum propeller diameter of approximately 19 cm. Skeletal injuries included a coccygeal vertebral fracture and subluxation of the left astragalus and calcaneus. CT images of the respiratory tract showed frothy fluid in the nasal cavity and trachea, as well as ground-glass opacity and consolidation in the lung parenchyma. Necropsy findings confirmed severe pulmonary edema, congestion, and abundant frothy foam throughout the respiratory tract. Histological analysis revealed pulmonary edema with eosinophilic fluid and erythrocytes in alveolar spaces, markedly distended blood vessels, and intra-alveolar hemorrhage. This comprehensive approach demonstrated that the cause of death was drowning, secondary to propeller strike by a small vessel (<4.5 m). To the authors’ knowledge, this is the first case report providing a detailed forensic analysis of a juvenile spotted seal found on the eastern coast of Korea. This case highlights the importance of integrating PMCT with conventional necropsy to improve cause-of-death determination in marine mammal conservation. Full article
(This article belongs to the Section Veterinary Clinical Studies)
33 pages, 24046 KB  
Article
CoDA: A Cognitive-Inspired Approach for Domain Adaptation
by Cavide Balkı Gemirter, Emin Erkan Korkmaz and Dionysis Goularas
Appl. Sci. 2026, 16(9), 4115; https://doi.org/10.3390/app16094115 - 23 Apr 2026
Abstract
Modern neural networks have achieved remarkable success in visual recognition; however, due to their sensitivity to domain shifts, Unsupervised Domain Adaptation (UDA) remains an open research problem. A key reason for this limitation is that source-trained models rely primarily on texture, lacking the [...] Read more.
Modern neural networks have achieved remarkable success in visual recognition; however, due to their sensitivity to domain shifts, Unsupervised Domain Adaptation (UDA) remains an open research problem. A key reason for this limitation is that source-trained models rely primarily on texture, lacking the explicit geometric information required for object recognition. To overcome this problem, we introduce CoDA, an object-centric learning framework inspired by infant cognitive development, specifically the process of object individuation. By introducing a geometric prior, our approach employs a physically grounded generation pipeline that uses a textureless “Sculpture Mode” and object isolation to complement textural information with 3D geometric features, capturing shape information that is often ignored during training. To enable robust training from scratch, we further integrate two control mechanisms: a Network Stability Scheduler to orchestrate training progression based on convergence stability, and a Dynamic Top-K Pseudo-Labeling strategy that adapts confidence thresholds for each individual class. Extensive evaluations on three real-world target datasets (VegFru, Fruits-262, and Open Images v7) demonstrate that CoDA, trained on a source dataset of just 12,000 synthetic images, achieves comparable results to (and in specific domains surpasses) ImageNet-pretrained models (leveraging 1.2 million images), significantly outperforming state-of-the-art adversarial and semi-supervised domain adaptation methods. Full article
(This article belongs to the Special Issue Advanced Signal and Image Processing for Applied Engineering)
Show Figures

Figure 1

43 pages, 15122 KB  
Article
CloudAHSI: A Hyperspectral Dataset for Cloud Segmentation from GF-5 AHSI
by Yuanyuan Jia, Siwei Zhao, Xuanbin Liu and Yinnian Liu
Remote Sens. 2026, 18(9), 1269; https://doi.org/10.3390/rs18091269 - 22 Apr 2026
Abstract
Cloud detection is essential for optical remote sensing data preprocessing. However, hyperspectral cloud detection datasets remain scarce, suffering from issues such as limited spectral coverage, small annotation scales, and a lack of scene diversity, which hinders the development of hyperspectral cloud detection algorithms. [...] Read more.
Cloud detection is essential for optical remote sensing data preprocessing. However, hyperspectral cloud detection datasets remain scarce, suffering from issues such as limited spectral coverage, small annotation scales, and a lack of scene diversity, which hinders the development of hyperspectral cloud detection algorithms. To address this, this paper constructs CloudAHSI—a multi-source hyperspectral cloud detection dataset for global complex scenes—based on the Advanced Hyperspectral Imager (AHSI) aboard the GF-5 01 satellite. The dataset comprises 45 original scenes and enhanced sub-scenes, achieving full-spectrum coverage from 400 to 2500 nm. Through a semi-supervised annotation framework combining “spectral prior-based rough labeling and manual refinement,” the dataset provides pixel-level labels for thick clouds, thin clouds, and non-cloud areas, with scenes further categorized by cloud coverage and primary land cover types. Experiments demonstrate that CloudAHSI effectively supports deep learning models in cloud detection tasks over complex surface backgrounds, particularly showing significant data value in the detection and evaluation of thin clouds, thereby meeting multi-level cloud detection requirements ranging from pixel segmentation to scene understanding. The release of this dataset provides a critical data foundation for overcoming spectral confusion bottlenecks in hyperspectral cloud detection and advancing the utilization of full-spectrum remote sensing information. Full article
(This article belongs to the Section Remote Sensing Image Processing)
17 pages, 4108 KB  
Article
Observation and Modeling of Polarization Jet During the 10 May 2024 Geomagnetic Storm: A Case Study for Kaliningrad and Eastern Europe
by Vladimir V. Klimenko, Maxim V. Klimenko, Kupriyan V. Belyuchenko, Ilya S. Yankovsky, Aleksandr V. Timchenko, Ilya A. Ryakhovsky and Galina A. Yakimova
Atmosphere 2026, 17(5), 426; https://doi.org/10.3390/atmos17050426 - 22 Apr 2026
Viewed by 66
Abstract
This study investigates subauroral phenomena during the main phase of the 10 May 2024 geomagnetic storm using a combination of ground-based observations from the WD IZMIRAN observatory (magnetometer, ionosonde, and all-sky imager) and Global Self-consistent Model of the Thermosphere, Ionosphere, Protonosphere (GSM TIP) [...] Read more.
This study investigates subauroral phenomena during the main phase of the 10 May 2024 geomagnetic storm using a combination of ground-based observations from the WD IZMIRAN observatory (magnetometer, ionosonde, and all-sky imager) and Global Self-consistent Model of the Thermosphere, Ionosphere, Protonosphere (GSM TIP) simulations. During 18:00–20:00 UT, we identified the simultaneous occurrence of ionospheric signatures of Polarization Jets (PJ)/Sub-Auroral Ion Drifts (SAID) and Strong Thermal Emission Velocity Enhancement (STEVE) over Kaliningrad, consistent with previously reported PJ/SAID identification from DMSP drift velocity measurements. This identification is supported by: (1) characteristic purple emissions (clearly visible in all three channels) moving rapidly westward; (2) U-shaped structures in ionogram sequences; (3) the reproduction of supersonic westward plasma drifts within a narrow latitudinal band by the first-principles model; and (4) observed and simulated significant Ne depletion. The estimated ion drift velocity from all-sky imaging (assuming an emission altitude of 200 km) is consistent with GSM TIP simulations, which predicted PJ/SAID velocities of ~750 m/s driven by a latitudinally narrow (~3°) but longitudinally extended (>50°) poleward electric field (40 mV/m). Simulations reveal that this PJ/SAID phenomenon causes a reversal of the zonal thermospheric wind at 250 km and induces Ne disturbances across the 200–700 km altitude range. The electron temperature enhancement (up to 1500 K) exhibits a “falling drop” shape, peaking at 350 km, while ion heating exceeds 150 K. The neutral temperature shows a dual response: frictional heating at 120–160 km and localized cooling at 175–250 km due to drop in electron density. Additionally, an increase in atomic oxygen concentration was predicted within the 90–200 km range across the PJ/SAID longitudinal sector. Full article
(This article belongs to the Special Issue Ionospheric Responses to Solar Activity)
Show Figures

Figure 1

14 pages, 7605 KB  
Article
Automated Morphological Profiling via Deep Learning-Based Segmentation for High-Throughput Phenotypic Screening
by Bendegúz H. Zováthi and Philipp Kainz
J. Imaging 2026, 12(4), 179; https://doi.org/10.3390/jimaging12040179 - 21 Apr 2026
Viewed by 116
Abstract
Reproducible morphological profiling, particularly for drug discovery, has become an important tool for compound evaluation. Established workflows such as CellProfiler provide a widely adopted foundation for Cell Painting analysis. However, conventional pipelines often require substantial manual configuration and technical expertise, which can limit [...] Read more.
Reproducible morphological profiling, particularly for drug discovery, has become an important tool for compound evaluation. Established workflows such as CellProfiler provide a widely adopted foundation for Cell Painting analysis. However, conventional pipelines often require substantial manual configuration and technical expertise, which can limit scalability and accessibility. In this study, a fully automated deep learning-based workflow is presented for segmentation-driven morphological profiling from raw microscopy data. Using a curated subset of the JUMP Cell Painting pilot dataset, ground-truth masks were generated and used to train a U-net–based segmentation model in the IKOSA platform. Post-processing strategies were introduced to improve instance separation and reduce segmentation artifacts. The final model achieved strong segmentation performance (precision/recall/AP up to 0.98/0.94/0.92 for nuclei), with an average runtime of 2.2 s per 1080 × 1080 image. Segmentation outputs enabled large-scale feature extraction, yielding 3664 morphological descriptors that showed high correlation with CellProfiler-derived measurements (normalized MAE: 0.0298). Feature prioritization further reduced redundancy to 1145 informative descriptors. These results demonstrate that automated deep learning pipelines can complement established Cell Painting workflows by reducing configuration overhead while maintaining compatibility with validated morphological profiling standards. The proposed workflow may help improve resource efficiency in drug discovery and personalized medicine. Full article
(This article belongs to the Special Issue Imaging in Healthcare: Progress and Challenges)
Show Figures

Figure 1

16 pages, 3621 KB  
Article
Influence of Rock Mass Discontinuity on Blast-Induced Vibration Attenuation in Quarry
by Chi-Han Wang, Yung-Chin Ding and Fu-Hao Lee
Appl. Sci. 2026, 16(8), 3990; https://doi.org/10.3390/app16083990 - 20 Apr 2026
Viewed by 162
Abstract
This study investigates the influence of rock mass discontinuities on blast-induced ground vibration attenuation in a marble quarry in eastern Taiwan. A total of 53 blasts and 106 vibration records were collected and analyzed using image-based rock mass characterization with WipFrag (Version 4) [...] Read more.
This study investigates the influence of rock mass discontinuities on blast-induced ground vibration attenuation in a marble quarry in eastern Taiwan. A total of 53 blasts and 106 vibration records were collected and analyzed using image-based rock mass characterization with WipFrag (Version 4) software. Discontinuity conditions were quantified through the joint factor (JF), defined by the median size (D50) and maximum size (D100) from cumulative size distribution curves. The PPV (peak particle velocity) data were fitted using the USBM, Sadovsky, and a modified Simangunsong equation incorporating a discontinuity correction factor. The modified Simangunsong model yielded the highest correlation (R2 = 0.8632), followed by the Sadovsky (R2 = 0.8067) and USBM (R2 = 0.7674) equations, indicating improved in-sample fitting performance when discontinuity effects are included. The results show that explicitly considering discontinuity effects enhances the reliability of PPV estimates for the studied site and that highly fractured rock masses with smaller block sizes result in greater vibration attenuation. The study demonstrates that a practical approach to quantify discontinuities through image analysis and embedding them into empirical PPV attenuation models can be used to refine quarry blasting design for vibration control purposes. Full article
(This article belongs to the Topic Environmental Pollution and Remediation in Mining Areas)
Show Figures

Figure 1

24 pages, 21145 KB  
Article
How Are the Parallel Channels of Visual Appearance and Social Vitality Helpful in Generating the Imageability of Characteristic Districts? An Empirical Study Grounded in the S-O-R Framework and Integrated Multi-Source Data
by Wenlong Lan, Yibo Zheng, Ze He and Qingwen Rong
Buildings 2026, 16(8), 1617; https://doi.org/10.3390/buildings16081617 - 20 Apr 2026
Viewed by 181
Abstract
Imageability is a cognitive measure of environmental differentiation and place memory. However, the existing literature focuses mainly on static morphological descriptions or subjective perception, without systematic quantitative studies of how physical environment and behavioral activity jointly generate the imageability of characteristic districts. This [...] Read more.
Imageability is a cognitive measure of environmental differentiation and place memory. However, the existing literature focuses mainly on static morphological descriptions or subjective perception, without systematic quantitative studies of how physical environment and behavioral activity jointly generate the imageability of characteristic districts. This limits active responses to the rise of “placelessness” in numerous cities. Based on the S-O-R theory, this study proposes a “visual–activity” two-channel mediation model. Based on 65 typical characteristic districts in Wuhan, and using multi-source data in the research, PLS-SEM was employed to systematically study the process that influences imageability in urban environments. It was found that (1) behavioral activity serves as the core mediating link between the physical environment and imageability; (2) scenic beauty exerts a partial mediating effect between visual sensitivity and imageability; (3) vitality exerts a full mediating effect between activity support and imageability. This study is expected to provide a scientific foundation for design refinements, quality enhancement, and place identity construction in urban characteristic districts oriented toward perceptual experience in the post-industrial era. Full article
(This article belongs to the Section Architectural Design, Urban Science, and Real Estate)
Show Figures

Figure 1

19 pages, 5438 KB  
Article
Chlorophyll-a Retrieval in Turbid Inland Waters Using BC-1A Multispectral Observations: A Case Study of Taihu Lake
by Wen Jiang, Qiyun Guo, Chen Cao and Shijie Liu
Sensors 2026, 26(8), 2535; https://doi.org/10.3390/s26082535 - 20 Apr 2026
Viewed by 164
Abstract
Turbid Class II inland waters such as Taihu Lake exhibit a “spectral uplift” effect driven by suspended particulate matter (SPM) scattering and colored dissolved organic matter (CDOM) absorption, which can obscure chlorophyll-a (Chl-a) signals in the visible–red-edge region and challenge retrieval under small-sample, [...] Read more.
Turbid Class II inland waters such as Taihu Lake exhibit a “spectral uplift” effect driven by suspended particulate matter (SPM) scattering and colored dissolved organic matter (CDOM) absorption, which can obscure chlorophyll-a (Chl-a) signals in the visible–red-edge region and challenge retrieval under small-sample, collinear feature settings. Using multispectral observations from the BC-1A satellite (carrying the Lightweight Hyperspectral Remote Sensing Imager, LHRSI) and synchronous satellite–ground in situ measurements acquired over Taihu Lake in late autumn, this study proposes Chl-a-oriented PCA–RF (COP-RF), a leakage-safe inversion framework integrating correlation screening, principal component analysis (PCA), and random forest (RF) regression. Candidate band-combination features are generated, and PCA is applied for orthogonal compression to mitigate collinearity before RF learning. A stratified five-fold cross-validation based on Chl-a quantile bins is adopted, with screening, standardization, and PCA fitted only on training folds. COP-RF achieves stable performance under the current dataset (R2=0.671, RMSE =1.80μg/L, MAE =1.25μg/L). Spatial inversion shows higher Chl-a near shores and bays and lower values in the lake center, consistent with Sentinel-2 hotspot ranks. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

33 pages, 5543 KB  
Article
The New Frontier of Quality Evaluation for Visual Sensors: A Survey of Large Multimodal Model-Based Methods
by Qihang Ge, Xiongkuo Min, Sijing Wu, Yunhao Li and Guangtao Zhai
Sensors 2026, 26(8), 2530; https://doi.org/10.3390/s26082530 - 20 Apr 2026
Viewed by 313
Abstract
Visual quality assessment is entering a new frontier as media evolve from static images to temporally dynamic videos and 3D content. These visual signals are typically captured by sensing devices such as cameras and depth sensors, whose acquisition characteristics significantly influence perceptual quality. [...] Read more.
Visual quality assessment is entering a new frontier as media evolve from static images to temporally dynamic videos and 3D content. These visual signals are typically captured by sensing devices such as cameras and depth sensors, whose acquisition characteristics significantly influence perceptual quality. Traditional quality models, including distortion-centric and regression-based approaches, perform well on conventional degradations but struggle to evaluate higher-level attributes such as semantic plausibility and structural coherence in modern AI-generated and multimodal scenarios. The emergence of large multimodal models (LMMs), including vision–language models (VLMs) and multimodal large language models (MLLMs), reshapes the evaluation paradigm by enabling semantic grounding, instruction-driven assessment, and explainable reasoning. This survey presents a unified perspective on visual quality assessment for sensor-captured visual data across image, video, and 3D modalities. We review conventional deep learning approaches and recent LMM-based methods, highlighting how multimodal fusion and language-conditioned reasoning transform quality assessment from scalar prediction to perceptual intelligence. Finally, we discuss key challenges and future opportunities for building efficient, robust, and sensor-aware visual quality assessment systems. Full article
(This article belongs to the Special Issue Perspectives in Intelligent Sensors and Sensing Systems)
Show Figures

Figure 1

18 pages, 2432 KB  
Article
Precision Without Complexity: A Comparative Study of YOLO26 Pose Variants for Distal Arm Landmark Detection
by Prathiksha Padmanabha, H. M. K. K. M. B. Herath, Nuwan Madusanka, Hi-Joon Park, Chang-Su Na, Myunggi Yi and Byeong-il Lee
Appl. Sci. 2026, 16(8), 3968; https://doi.org/10.3390/app16083968 - 19 Apr 2026
Viewed by 232
Abstract
Accurate anatomical landmark localization in clinical images requires millimeter-level spatial precision, yet whether increasing model scale improves such precision in structured medical imaging tasks remains unclear. Five YOLO26 pose-estimation variants (N, S, M, L, and X) were evaluated on 3679 RGB distal-arm images [...] Read more.
Accurate anatomical landmark localization in clinical images requires millimeter-level spatial precision, yet whether increasing model scale improves such precision in structured medical imaging tasks remains unclear. Five YOLO26 pose-estimation variants (N, S, M, L, and X) were evaluated on 3679 RGB distal-arm images from 262 participants under a standardized overhead imaging protocol, with five anatomical landmarks annotated across the proximal forearm, mid-forearm, and hand. Localization error was quantified in millimeters using ArUco-marker-based pixel-to-millimeter calibration; all models were initialized from COCO-pretrained weights, fine-tuned under identical conditions, and assessed using COCO-style detection metrics and physically grounded localization error. Detection performance saturated across all scales (mAP@0.5 = 99.5%), while localization performance differed substantially; YOLO26N achieved the lowest mean error (2.76 ± 0.96 mm) and the highest proportion of predictions within 4 mm (88.0%), whereas YOLO26X produced the highest mean error (4.08 ± 2.59 mm) despite a 26.9× higher computational cost. Landmark-wise analysis revealed a consistent proximal-to-distal error gradient, with the largest degradation at anatomically ambiguous proximal landmarks in larger models. These findings suggest that increasing model capacity does not improve clinically meaningful localization precision in structured distal-arm imaging, and lightweight models may offer the most favorable accuracy-efficiency trade-off in resource-constrained clinical settings. Full article
Show Figures

Figure 1

21 pages, 5315 KB  
Article
Design and On-Orbit Validation of a Compact Wide-Swath Spaceborne SWIR Push-Broom Camera
by Bo Cheng, Yongqian Zhu, Qianmin Liu, Jincai Wu, Bin Wu, Jiawei Lu, Zhihua Song, Bangjian Zhao, Chen Cao, Tianzhen Ma, Chunlai Li and Jianyu Wang
Sensors 2026, 26(8), 2494; https://doi.org/10.3390/s26082494 - 17 Apr 2026
Viewed by 262
Abstract
To address the demand for wide-swath, high-resolution short-wave infrared (SWIR) imaging on resource-constrained spaceborne platforms, this study presents the design and on-orbit validation of a compact dual-channel push-broom (line-scanning) imaging system. The system adopts a transmissive optical architecture and a centralized, compact electronic [...] Read more.
To address the demand for wide-swath, high-resolution short-wave infrared (SWIR) imaging on resource-constrained spaceborne platforms, this study presents the design and on-orbit validation of a compact dual-channel push-broom (line-scanning) imaging system. The system adopts a transmissive optical architecture and a centralized, compact electronic control unit (ECU) configuration. By interleaving and mosaicking sixteen InGaAs linear array detectors, the system achieves an imaging swath of approximately 187 km and a nominal ground sampling distance of about 24 m, while maintaining a total instrument mass of 10.62 kg and a power consumption of approximately 12 W, thereby demonstrating a high level of integration and efficient resource utilization. To address focal plane consistency issues arising from multi-detector mosaicking, a closed-loop leveling method was developed using the modulation transfer function (MTF) as the primary performance metric. Through defocus estimation and quantitative correction of protrusions on a SiC substrate, convergence toward a unified confocal focal plane among multiple detectors was achieved. On-orbit image quality assessment indicates that the full width at half maximum (FWHM) of the line spread function (LSF) for both channels is approximately 1.38 pixels, with favorable signal-to-noise ratio (SNR) performance. These results validate the effectiveness of the proposed focal plane leveling strategy as well as the opto-mechanical-thermal design of the system. The proposed approach provides a practical pathway for the engineering implementation and consistency control of multi-detector mosaicked SWIR payloads under stringent resource constraints. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

Back to TopTop