Search Results (11,597)

The integration of a pixelated Fabry–Pérot filter array onto the image sensor enables on-chip snapshot multispectral imaging, significantly reducing the size and weight of conventional spectral imaging equipment. However, a traditional Fabry–Pérot cavity, based on metallic or dielectric layers, exhibits a narrow bandwidth, which restricts their utility in broader applications. In this work, we propose novel Fabry–Pérot filter structures that employ dielectric thin films for phase modulation, enabling single-peak filtering across a broad operational wavelength range from 400 nm to 1100 nm. The proposed structures are easy to fabricate and compatible with complementary metal-oxide-semiconductor (CMOS) image sensors. Moreover, the structures show low sensitivity to oblique incident angles of up to 30° with minimal wavelength shifts. This advanced Fabry–Pérot filter design provides a promising pathway for expanding the operational wavelength of snapshot spectral imaging systems, thereby potentially extending their application across numerous related fields. Full article

Nepal is highly susceptible to natural hazards, including earthquakes, flooding, and landslides, all of which may occur independently or in combination. Climate change is projected to increase the frequency and intensity of these natural hazards, posing growing risks to Nepal’s infrastructure and development. To the authors’ knowledge, the majority of existing geohazard research in Nepal is typically limited to single hazards or localised areas. To address this gap, MiMapper was developed as a cloud-based, open-access multi-hazard mapping tool covering the full national extent. Built on Google Earth Engine and using only open-source spatial datasets, MiMapper applies an Analytical Hierarchy Process (AHP) to generate hazard indices for earthquakes, floods, and landslides. These indices are combined into an aggregated hazard layer and presented in an interactive, user-friendly web map that requires no prior GIS expertise. MiMapper uses a standardised hazard categorisation system for all layers, providing pixel-based scores for each layer between 0 (Very Low) and 1 (Very High). The modal and mean hazard categories for aggregated hazard in Nepal were Low (47.66% of pixels) and Medium (45.61% of pixels), respectively, but there was high spatial variability in hazard categories depending on hazard type. The validation of MiMapper’s flooding and landslide layers showed an accuracy of 0.412 and 0.668, sensitivity of 0.637 and 0.898, and precision of 0.116 and 0.627, respectively. These validation results show strong overall performance for landslide prediction, whilst broad-scale exposure patterns are predicted for flooding but may lack the resolution or sensitivity to fully represent real-world flood events. Consequently, MiMapper is a useful tool to support initial hazard screening by professionals in urban planning, infrastructure development, disaster management, and research. It can contribute to a Level 1 Integrated Geohazard Assessment as part of the evaluation for improving the resilience of hydropower schemes to the impacts of climate change. MiMapper also offers potential as a teaching tool for exploring hazard processes in data-limited, high-relief environments such as Nepal. Full article

To address the issues of small-target missed detection, false alarms from cloud/fog interference, and low computational efficiency in traditional wildfire detection for transmission line corridors, this paper proposes a YOLOv11_MDS detection model by integrating Multi-Scale Convolutional Attention (MSCA) and Distribution-Shifted Convolution (DSConv). The MSCA module is embedded in the backbone and neck to enhance multi-scale dynamic feature extraction of flame and smoke through collaborative depth strip convolution and channel attention. The DSConv with a quantized dynamic shift mechanism is introduced to significantly reduce computational complexity while maintaining detection accuracy. The improved model, as shown in experiments, achieves an mAP@0.5 of 88.21%, which is 2.93 percentage points higher than the original YOLOv11. It also demonstrates a 3.33% increase in recall and a frame rate of 242 FPS, with notable improvements in detecting small targets (pixel occupancy < 1%). Generalization tests demonstrate mAP improvements of 0.4% and 0.7% on benchmark datasets, effectively resolving false/missed detection in complex backgrounds. This study provides an engineering solution for real-time wildfire monitoring in transmission lines with balanced accuracy and efficiency. Full article

A lateral overflow integration capacitor (LOFIC) CMOS image sensor (CIS) can achieve high-dynamic-range (HDR) imaging by combining a low-conversion-gain (LCG) signal with a high-conversion-gain (HCG) signal. However, the signal-to-noise ratio (SNR) drops at the switching point from HCG signal to LCG signal due to the significant pixel noise in the LCG signal. To address this issue, a triple-gain LOFIC CIS with a middle-conversion-gain (MCG) signal has been introduced. In this work, we propose an area-efficient readout circuit for the triple-gain LOFIC CIS, using amplifier and capacitor sharing techniques to process the HCG, MCG, and LCG signals. A test chip of the proposed readout circuit was fabricated using the $0.18\mathsf{\mu }$m CMOS process. The area overhead was only $7.6\%$, and the SNR drop was improved by $8.05$ dB compared to the readout circuit for a dual-gain LOFIC CIS. Full article

As a key target area in China’s new round of strategic mineral exploration initiatives, Tibet possesses favorable metallogenic conditions shaped by its unique geological evolution and tectonic setting. In this paper, the Saga region of Tibet is the research object, and Level-2A Sentinel-2 imagery is utilized. By applying mixed pixel decomposition, interfering endmembers were identified, and spectral unmixing and reconstruction were performed, effectively avoiding the drawback of traditional methods that tend to remove mineral alteration signals and masking interference. Combined with band ratio analysis and principal component analysis (PCA), various types of remote sensing alteration anomalies in the region were extracted. Furthermore, the fractal box-counting method was employed to quantify the fractal dimensions of the different alteration anomalies, thereby delineating their spatial distribution and fractal structural characteristics. Based on these results, two prospective mineralization zones were identified. The results indicate the following: (1) In areas of Tibet with low vegetation cover, applying spectral mixture analysis (SMA) effectively removes substantial background interference, thereby enabling the extraction of subtle remote sensing alteration anomalies. (2) The fractal dimensions of various remote sensing alteration anomalies were calculated using the fractal box-counting method over a spatial scale range of 0.765 to 6.123 km. These values quantitatively characterize the spatial fractal properties of the anomalies, and the differences in fractal dimensions among alteration types reflect the spatiotemporal heterogeneity of the mineralization system. (3) The high-potential mineralization zones identified in the composite contour map of fractal dimensions of alteration anomalies show strong spatial agreement with known mineralization sites. Additionally, two new prospective mineralization zones were delineated in their periphery, providing theoretical support and exploration targets for future prospecting in the study area. Full article

Background/Objectives: The spinal cord is a critical component of the central nervous system that transmits neural signals between the brain and the body’s peripheral regions through its nerve roots. Despite being partially protected by the vertebral column, the spinal cord remains highly vulnerable to trauma, tumors, infections, and degenerative or inflammatory disorders. These conditions can disrupt neural conduction, resulting in severe functional impairments, such as paralysis, motor deficits, and sensory loss. Therefore, accurate and comprehensive spinal cord segmentation is essential for characterizing its structural features and evaluating neural integrity. Methods: In this study, we propose a fully automated method for segmentation of the cervical spinal cord in sagittal magnetic resonance (MR) images. This method facilitates rapid clinical evaluation and supports early diagnosis. Our approach uses a Swin-Unet architecture, which integrates vision transformer blocks into the U-Net framework. This enables the model to capture both local anatomical details and global contextual information. This design improves the delineation of the thin, curved, low-contrast cervical cord, resulting in more precise and robust segmentation. Results: In experimental studies, the proposed Swin-Unet model (SWU1), which uses transformer blocks in the encoder layer, achieved Dice Similarity Coefficient (DSC) and Hausdorff Distance 95 (HD95) scores of 0.9526 and 1.0707 mm, respectively, for cervical spinal cord segmentation. These results confirm that the model can consistently deliver precise, pixel-level delineations that are structurally accurate, which supports its reliability for clinical assessment. Conclusions: The attention-enhanced Swin-Unet architecture demonstrated high accuracy in segmenting thin and complex anatomical structures, such as the cervical spinal cord. Its ability to generalize with limited data highlights its potential for integration into clinical workflows to support diagnosis, monitoring, and treatment planning. Full article

Semantic segmentation of building facade images has enabled a lot of intelligent support for architectural research and practice in the last decade. However, the classifiers for semantic segmentation usually predict facade elements (e.g., windows) as graphics in irregular shapes. The non-smooth edges and hard-to-define shapes impede the further use of the predicted graphics. This study proposes a method to regularize the predicted graphics following the prior knowledge of composition principles of building facades. Specifically, we define four types of boxes for each predicted graphic, namely minimum circumscribed box (MCB), maximum inscribed box (MIB), candidate box (CB), and best overlapping box (BOB). Based on these boxes, a three-stage process, consisting of denoising, BOB finding, and BOB stacking, was established to regularize the predicted graphics of facade elements into basic rectilinear polygons. To compare the proposed and existing methods of graphic regularization, an experiment was conducted based on the predicted graphics of facade elements obtained from four pixel-wise annotated building facade datasets, Irregular Facades (IRFs), CMP Facade Database, ECP Paris, and ICG Graz50. The results demonstrate that the graphics regularized by our method align more closely with real facade elements in shape and edge. Moreover, our method avoids the prevalent issue of correctness degradation observed in existing methods. Compared with the predicted graphics, the average IoU and F1-score of our method-regularized graphics respectively increase by 0.001–0.017 and 0.000–0.012 across the datasets, while those of previous method-regularized graphics decrease by 0.002–0.021 and 0.002–0.015. The regularized graphics contribute to improving the precision and depth of semantic segmentation-based applications of building facades. They are also expected to be useful for the exploration of data mining on urban images in the future. Full article

Cropland abandonment, a global challenge, necessitates comprehensive monitoring to achieve the zero hunger goal. Prior monitoring approaches to cropland abandonment often face constraints in resolution, time series, drivers, prediction, or a combination of these. Here, we proposed an artificial intelligence framework to comprehensively monitor cropland abandonment and tested the framework in Hengyang City, China. Specifically, we first mapped land cover at 30 m resolution from 1985 to 2023 using Landsat, stable sample points, and a machine learning model. Subsequently, we constructed the extent, time, and frequency of cropland abandonment from 1986 to 2022 by analyzing pixel-level land-use trajectories. Finally, we quantified the drivers of cropland abandonment using machine learning models and predicted the spatial distribution of cropland abandonment risk from 2032 to 2062. Our results indicated that the abandonment maps achieved overall accuracies of 0.88 and 0.78 for identifying abandonment locations and timing, respectively. From 1986 to 2022, the proportion of cropland abandonment ranged between 0.15% and 4.06%, with an annual average abandonment rate of 1.32%. Additionally, the duration of abandonment varied from 2 to 38 years, averaging approximately 14 years, indicating widespread cropland abandonment in the study area. Furthermore, 62.99% of the abandoned cropland experienced abandonment once, 27.17% experienced it twice, and only 0.23% experienced it five times or more. Over 50% of cropland abandonment remained unreclaimed or reused. During the study period, tree cover, soil pH, soil total phosphorus, potential crop yield, and the multiresolution index of valley bottom flatness emerged as the five most important environmental covariates, with relative importances of 0.087, 0.074, 0.068, 0.050, and 0.043, respectively. Temporally, cropland abandonment in 1992 was influenced by transportation inaccessibility and low agricultural productivity, soil quality degradation became an additional factor by 2010, and synergistic effects of all three drivers were observed from 2012 to 2022. Notably, most cropland had a low abandonment risk (mean: 0.36), with only 0.37% exceeding 0.7, primarily distributed in transitional zones between cropland and non-cropland. Future risk predictions suggested a gradual decline in both risk values and the spatial extent of cropland abandonment from 2032 to 2062. In summary, we developed a comprehensive framework for monitoring cropland abandonment using artificial intelligence technology, which can be used in national or regional land-use policies, warning systems, and food security planning. Full article

This article presents a principled framework for selecting and tuning classical computer vision algorithms in the context of optical displacement sensing. By isolating key factors that affect algorithm behavior—such as feed window size and motion step size—the study seeks to move beyond intuition-based practices and provide rigorous, repeatable performance evaluations. Computer vision-based optical odometry sensors offer non-contact, high-precision measurement capabilities essential for modern metrology and robotics applications. This paper presents a systematic comparative analysis of three classical tracking algorithms—phase correlation, template matching, and optical flow—for 2D surface displacement measurement using synthetic image sequences with subpixel-accurate ground truth. A virtual camera system generates controlled test conditions using a multi-circle trajectory pattern, enabling systematic evaluation of tracking performance using 400 × 400 and 200 × 200 pixel feed windows. The systematic characterization enables informed algorithm selection based on specific application requirements rather than empirical trial-and-error approaches. Full article

Manual pixel-level annotation remains a major bottleneck in deploying deep learning models for dense prediction and semantic segmentation tasks across domains. This challenge is especially pronounced in applications involving fine-scale structures, such as cracks in infrastructure or lesions in medical imaging, where annotations are time-consuming, expensive, and subject to inter-observer variability. To address these challenges, this work proposes a weakly supervised and annotation-efficient segmentation framework that integrates sparse bounding-box annotations with a limited subset of strong (pixel-level) labels to train robust segmentation models. The fundamental element of the framework is a lightweight Bounding Box Encoder that converts weak annotations into multi-scale attention maps. These maps guide a ConvNeXt-Base encoder, and a lightweight U-Net–style convolutional neural network (CNN) decoder—using nearest-neighbor upsampling and skip connections—reconstructs the final segmentation mask. This design enables the model to focus on semantically relevant regions without relying on full supervision, drastically reducing annotation cost while maintaining high accuracy. We validate our framework on two distinct domains, road crack detection and skin cancer segmentation, demonstrating that it achieves performance comparable to fully supervised segmentation models using only 10–20% of strong annotations. Given the ability of the proposed framework to generalize across varied visual contexts, it has strong potential as a general annotation-efficient segmentation tool for domains where strong labeling is costly or infeasible. Full article

Synthetic aperture radar (SAR) exhibits all-day and all-weather capabilities, granting it significant application in remote sensing. However, interpreting SAR images requires extensive expertise, making SAR-to-optical remote sensing image translation a crucial research direction. While conditional generative adversarial networks (CGANs) have demonstrated exceptional performance in image translation tasks, their massive number of parameters pose substantial challenges. Therefore, this paper proposes ILF-BDSNet, a compressed network for SAR-to-optical image translation. Specifically, first, standard convolutions in the feature-transformation module of the teacher network are replaced with depthwise separable convolutions to construct the student network, and a dual-resolution collaborative discriminator based on PatchGAN is proposed. Next, knowledge distillation based on intermediate-layer features and channel pruning via weight sharing are designed to train the student network. Then, the bio-inspired dynamic search of channel configuration (BDSCC) algorithm is proposed to efficiently select the optimal subnet. Meanwhile, the pixel-semantic dual-domain alignment loss function is designed. The feature-matching loss within this function establishes an alignment mechanism based on intermediate-layer features from the discriminator. Extensive experiments demonstrate the superiority of ILF-BDSNet, which significantly reduces number of parameters and computational complexity while still generating high-quality optical images, providing an efficient solution for SAR image translation in resource-constrained environments. Full article

Water scarcity, driven by over-consumption, population growth, climate change, and pollution, poses severe threats to both human health and ecosystems. Rainwater harvesting (RWH) has emerged as a sustainable solution to mitigate these impacts, offering environmental, social, and economic benefits. Traditional RWH site selection methods rely heavily on GIS-based Multi-Criteria Approaches, such as the Analytical Hierarchy Process, which typically assess runoff potential at the pixel scale using proxy indicators like runoff coefficients or drainage density. However, these methods often overlook horizontal water fluxes and temporal variability, leading to underestimation of the actual runoff available for harvesting. This study introduces an innovative enhancement to AHP/GIS-based methodologies for rainwater harvesting (RWH) site selection by incorporating Aggregated Runoff (AR) as a key criterion. Unlike traditional approaches, the use of AR—representing the total upstream surface water collected at each pixel—enables a more realistic and accurate assessment of RWH potential without increasing data or computational requirements. The proposed criterion is independent of the specific methodology or data layers adopted, making it broadly applicable and easily integrable into existing frameworks. The methodology is applied to the upper Tiber River catchment in Central Italy, demonstrating that AR-based assessments yield more realistic RWH potential maps compared to conventional methods. Additionally, the study proposes a quantile-based scoring system to account for inter-annual hydrological variability, enhancing the robustness of site selection under changing climate conditions. Full article

With the rapid advancement of image processing techniques, digital image forgery detection has emerged as a critical research area in information forensics. This paper proposes a novel deep learning model based on Multi-view Multi-dimensional Forgery Detection Networks (MMFD-Net), designed to simultaneously determine whether an image has been tampered with and precisely localize the forged regions. By integrating a Multi-stream Edge Feature Learning module with a Multi-dimensional Information Fusion module, MMFD-Net employs joint supervised learning to extract semantics-agnostic forgery features, thereby enhancing both detection performance and model generalization. Extensive experiments demonstrate that MMFD-Net achieves state-of-the-art results on multiple public datasets, excelling in both pixel-level localization and image-level classification tasks, while maintaining robust performance in complex scenarios. Full article

To break through the bottleneck in the mapping of the mechanoluminescent (ML) intensity field to the strain field, a quantification method for full-field strain measurement based on pixel-level data fusion is proposed, integrating ML imaging with digital image correlation (DIC) to achieve precise reconstruction of the strain field. Experiments are conducted using aluminum alloy specimens coated with ML film sensor on their surfaces. During the tensile process, ML images of the films and speckle images of the specimen backsides are simultaneously acquired. Combined with DIC technology, high-precision full-field strain distributions are obtained. Through spatial registration and region matching algorithms, a quantitative calibration model between ML intensity and DIC strain is established. The research results indicate that the ML intensity and DIC strain exhibit a significant linear correlation (R² = 0.92). To verify the universality of the model, aluminum alloy notched specimen tests show that the reconstructed strain field is in good agreement with the DIC and finite element analysis results, with an average relative error of 0.23%. This method enables full-field, non-contact conversion of ML signals into strain distributions with high spatial resolution, providing a quantitative basis for studying ML response mechanisms under complex loading. Full article

Remote sensing provides a viable alternative for understanding landscape modifications attributed to beaver activity. The central objective of this study is to integrate multi-source remote sensing observations in tandem with a deep learning (DL) (convolutional neural net or transformer) model to automatically map beaver-influenced floodplain inundations (BIFI) over large geographical extents. We trained, validated, and tested eleven different model configurations in three architectures using five ResNet and five B-Finetuned encoders. The training dataset consisted of >25,000 manually annotated aerial image tiles of BIFIs in Connecticut. The YOLOv8 architecture outperformed competing configurations and achieved an F1 score of 80.59% and pixel-based map accuracy of 98.95%. SegFormer and U-Net++’s highest-performing models had F1 scores of 68.98% and 78.86%, respectively. The YOLOv8l-seg model was deployed at a statewide scale based on 1 m resolution multi-temporal aerial imagery acquired from 1990 to 2019 under leaf-on and leaf-off conditions. Our results suggest a variety of inferences when comparing leaf-on and leaf-off conditions of the same year. The model exhibits limitations in identifying BIFIs in panchromatic imagery in occluded environments. Study findings demonstrate the potential of harnessing historical and modern aerial image datasets with state-of-the-art DL models to increase our understanding of beaver activity across space and time. Full article