Search Results (284)

In remote sensing image processing, cloud and cloud shadow detection is of great significance, which can solve the problems of cloud occlusion and image distortion, and provide support for multiple fields. However, the traditional convolutional or Transformer models and the existing studies combining the two have some shortcomings, such as insufficient feature fusion, high computational complexity, and difficulty in taking into account local and long-range dependent information extraction. In order to solve these problems, this paper proposes the MCloud model based on Mamba architecture is proposed, which takes advantage of its linear computational complexity to effectively model long-range dependencies and local features through the coordinated work of state space and convolutional support and the Mamba-convolutional fusion module. Experiments show that MCloud have the leading segmentation performance and generalization ability on multiple datasets, and provides more accurate and efficient solutions for cloud and cloud shadow detection. Full article

Land use/land cover (LULC) data serve as a critical information source for understanding the complex interactions between human activities and global environmental change. The subtropical karst region, characterized by fragmented terrain, spectral confusion, topographic shadowing, and frequent cloud cover, represents one of the most challenging natural scenes for remote sensing classification. This study reviews the evolution of multi-source data acquisition (optical, SAR, LiDAR, UAV) and preprocessing strategies tailored for subtropical regions. It evaluates the applicability and limitations of various methodological frameworks, ranging from traditional approaches and GEOBIA to machine learning and deep learning. The importance of uncertainty modeling and robust accuracy assessment systems is emphasized. The study identifies four major bottlenecks: scarcity of high-quality samples, lack of scale awareness, poor model generalization, and insufficient integration of geoscientific knowledge. It suggests that future breakthroughs lie in developing remote sensing intelligent models that are driven by few samples, integrate multi-modal data, and possess strong geoscientific interpretability. The findings provide a theoretical reference for LULC information extraction and ecological monitoring in heterogeneous geomorphic regions. Full article

Cloud detection is one of the primary challenges in preprocessing high-resolution remote sensing imagery, the accuracy of which is severely constrained by the multi-scale and complex morphological characteristics of clouds. Many approaches have been proposed to detect cloud. However, these methods still face significant challenges, particularly in handling the complexities of multi-scale cloud clusters and reliably distinguishing clouds from snow, ice and complex cloud shadows. To overcome these challenges, this paper proposes a novel cloud detection network based on the state space model (SSM), termed the Hierarchical Dilated Adaptive Mamba Network (HDAMNet). This network utilizes an encoder–decoder architecture, significantly expanding the receptive field and improving the capture of fine-grained cloud boundaries by introducing the Hierarchical Dilated Cross Scan (HDCS) mechanism in the encoder module. The multi-resolution adaptive feature extraction (MRAFE) integrates multi-scale semantic information to reduce channel confusion and emphasize essential features effectively. The Layer-wise Adaptive Attention (LAA) mechanism adaptively recalibrates features at skip connections, balancing fine-grained boundaries with global semantic information. On three public cloud detection datasets, HDAMNet achieves state-of-the-art performance across key evaluation metrics. Particularly noteworthy is its superior performance in identifying small-scale cloud clusters, delineating complex cloud–shadow boundaries, and mitigating interference from snow and ice. Full article

Unmanned aerial vehicles (UAVs) are an ideal platform for the remote sensing of riverbeds in small, tree-lined streams, allowing unobstructed viewing of the channel at high spatial resolution. However, effective UAV surveying of these riverbeds is hindered by a range of phenomena associated with the complex light environments of rivers, and small tree-lined streams in particular, including reflections of the overlying cloud layer from the water surface, sunglint on the water surface, and shadows from topography and riparian vegetation. We used UAV imagery acquired from small, tree-lined streams under different light conditions to identify the prevalence of the main phenomena—reflections of clouds, sunglint, and shadows—that hinder the ability to discern the riverbed. We characterized how large a constraint these phenomena are on the optimal imaging window. We then examined the degree to which sub-optimal light conditions may restrict this window, both within the year and within the day, across Europe. Our investigations suggest that different regions across Europe will have different priorities with regard to imaging, with surveys in northern rivers emphasizing avoiding low irradiant intensity in winter and those in southern rivers emphasizing avoiding sunglint around midday. We use our findings to suggest a protocol for improved riverbed imaging that is specific to the light environment of the stream under investigation. Full article

One of the persistent challenges in multispectral image analysis is the interference caused by dense cloud cover and its resulting shadows, which can significantly obscure surface features. This becomes especially problematic when attempting to monitor surface changes over time using satellite imagery, such as from Landsat-8. In this study, rather than simply masking visual obstructions, we aimed to investigate the role and influence of clouds within the spectral data itself. To achieve this, we employed Independent Component Analysis (ICA), a statistical method capable of decomposing mixed signals into independent source components. By applying ICA to selected Landsat-8 bands and analyzing each component individually, we assessed the extent to which cloud signatures are entangled with surface data. This process revealed that clouds contribute to multiple ICA components simultaneously, indicating their broad spectral influence. With this influence on multiple wavebands, we managed to configure a set of components that could perfectly delineate the extent and location of clouds. Moreover, because Landsat-8 lacks cloud-penetrating wavebands, such as those in the microwave range (e.g., SAR), the surface information beneath dense cloud cover is not captured at all, making it physically impossible for ICA to recover what is not sensed in the first place. Despite these limitations, ICA proved effective in isolating and delineating cloud structures, allowing us to selectively suppress them in reconstructed images. Additionally, the technique successfully highlighted features such as water bodies, vegetation, and color-based land cover differences. These findings suggest that while ICA is a powerful tool for signal separation and cloud-related artifact suppression, its performance is ultimately constrained by the spectral and spatial properties of the input data. Future improvements could be realized by integrating data from complementary sensors—especially those operating in cloud-penetrating wavelengths—or by using higher spectral resolution imagery with narrower bands. Full article

Low-altitude unmanned aerial vehicle (UAV) vision is critically hindered by the Sim-to-Real Gap, where models trained exclusively on simulation data degrade under real-world variations in lighting, texture, and weather. To address this problem, we propose RA3T (Region-Aligned 3D Transformer), a novel self-supervised framework that enables robust Sim-to-Real adaptation. Specifically, we first develop a dual-branch strategy for self-supervised feature learning, integrating Masked Autoencoders and contrastive learning. This approach extracts domain-invariant representations from unlabeled simulated imagery to enhance robustness against occlusion while reducing annotation dependency. Leveraging these learned features, we then introduce a 3D Transformer fusion module that unifies multi-view RGB and LiDAR point clouds through cross-modal attention. By explicitly modeling spatial layouts and height differentials, this component significantly improves recognition of small and occluded targets in complex low-altitude environments. To address persistent fine-grained domain shifts, we finally design region-level adversarial calibration that deploys local discriminators on partitioned feature maps. This mechanism directly aligns texture, shadow, and illumination discrepancies which challenge conventional global alignment methods. Extensive experiments on UAV benchmarks VisDrone and DOTA demonstrate the effectiveness of RA3T. The framework achieves +5.1% mAP on VisDrone and +7.4% mAP on DOTA over the 2D adversarial baseline, particularly on small objects and sparse occlusions, while maintaining real-time performance of 17 FPS at 1024 × 1024 resolution on an RTX 4080 GPU. Visual analysis confirms that the synergistic integration of 3D geometric encoding and local adversarial alignment effectively mitigates domain gaps caused by uneven illumination and perspective variations, establishing an efficient pathway for simulation-to-reality UAV perception. Full article

With the continuous advancement of remote sensing technology and its growing importance, the need for ready-to-use data has increased exponentially. Satellite platforms such as Sentinel-2, which carries the Multispectral Instrument (MSI) sensor, known for their cost-effectiveness, capture valuable information about Earth in the form of images. However, they encounter a significant challenge in the form of clouds and their shadows, which hinders the data acquisition and processing for regions of interest. This article undertakes a comprehensive literature review to systematically analyze the critical cloud-related challenges. It explores the need for accurate cloud detection, reviews existing datasets, and evaluates contemporary cloud detection methodologies, including their strengths and limitations. Additionally, it highlights the inaccuracies introduced by varying atmospheric and environmental conditions, emphasizing the importance of integrating advanced techniques that can utilize local and global semantics. The review also introduces a structured intercomparison framework to enable standardized evaluation across binary and multiclass cloud detection methods using both qualitative and quantitative metrics. To facilitate fair comparison, a conversion mechanism is highlighted to harmonize outputs across methods with different class granularities. By identifying gaps in current practices and datasets, the study highlights the importance of innovative, efficient, and scalable solutions for automated cloud detection, paving the way for unbiased evaluation and improved utilization of satellite imagery across diverse applications. Full article

The accurate identification of water bodies in hyperspectral images (HSIs) remains challenging due to hierarchical representation imbalances in deep learning models, where shallow layers overly focus on spectral features, boundary ambiguities caused by the relatively low spatial resolution of satellite imagery, and limited detection capability for small-scale aquatic features such as narrow rivers. To address these challenges, this study proposes Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evaluation (HASSDE-NAS). The architecture integrates three specialized units; a spectral-aware dynamic band selection cell suppresses redundant spectral bands, while a geometry-enhanced edge attention cell refines fragmented spatial boundaries. Additionally, a bidirectional fusion alignment cell jointly optimizes spectral and spatial dependencies. A heuristic cell search algorithm optimizes the network architecture through architecture stability, feature diversity, and gradient sensitivity analysis, which improves search efficiency and model robustness. Evaluated on the Gaofen-5 datasets from the Guangdong and Henan regions, HASSDE-NAS achieves overall accuracies of 92.61% and 96%, respectively. This approach outperforms existing methods in delineating narrow river systems and resolving water bodies with weak spectral contrast under complex backgrounds, such as vegetation or cloud shadows. By adaptively prioritizing task-relevant features, the framework provides an interpretable solution for hydrological monitoring and advances neural architecture search in intelligent remote sensing. Full article

Cloud detection is a critical preprocessing step for optical remote sensing imagery. However, traditional CNN-based methods have limitations in global feature modeling, while Transformer models, despite their strong global modeling capability, struggle to capture fine-grained local details effectively. To tackle these challenges, this study introduces a dual-path neural network framework that synergistically combines convolutional neural networks (CNNs) and architectures. By capitalizing on their complementary strengths, this work proposed a dual-branch feature extraction architecture that utilizes two different feature aggregation modes to effectively aggregate features of CNN and Transformer at different levels. Specifically, two novel modules are introduced: the Dual-branch Lightweight Aggregation Module (DLAM), which fuses CNN and Transformer features in the early encoding stage and emphasizes key information through a feature weight allocation mechanism; and the Dual-branch Attention Aggregation Module (DAAM), which further integrates local and global features in the late encoding stage, improving the model’s differentiation performance between cloud and cloud shadow areas. The collaboration between DLAM and DAAM enables the model to efficiently learn multi-scale and spatially hierarchical information, thereby improving detection performance. The experimental findings validate the superior performance of our model over state-of-the-art methods on diverse remote sensing datasets, attaining enhanced accuracy in cloud detection. Full article

Accurate cloud detection is a critical preprocessing step in remote sensing applications, as cloud and cloud shadow contamination can significantly degrade the quality of optical satellite imagery. In this paper, we propose CDWMamba, a novel dual-domain neural network that integrates the Mamba-based state space model with discrete wavelet transform (DWT) for effective cloud detection. CDWMamba adopts a four-direction Mamba module to capture long-range dependencies, while the wavelet decomposition enables multi-scale global context modeling in the frequency domain. To further enhance fine-grained spatial features, we incorporate a multi-scale depth-wise separable convolution (MDC) module for spatial detail refinement. Additionally, a spectral–spatial bottleneck (SSN) with channel-wise attention is introduced to promote inter-band information interaction across multi-spectral inputs. We evaluate our method on two benchmark datasets, L8 Biome and S2_CMC, covering diverse land cover types and environmental conditions. Experimental results demonstrate that CDWMamba achieves state-of-the-art performance across multiple metrics, significantly outperforming deep-learning-based baselines in terms of overall accuracy, mIoU, precision, and recall. Moreover, the model exhibits satisfactory performance under challenging conditions such as snow/ice and shrubland surfaces. These results verify the effectiveness of combining a state space model, frequency-domain representation, and spectral–spatial attention for cloud detection in multi-spectral remote sensing imagery. Full article

This study develops an optimized approach for small-scale forest area extraction in mountainous regions by integrating Landsat multispectral and ALOS PALSAR-2 radar data through threshold-based classification methods. The threshold fusion method proposed in this study achieves innovations in three key aspects: First, by integrating Landsat NDVI with PALSAR-2 polarization characteristics, it effectively addresses omission errors caused by cloud interference and terrain shadows. Second, the adoption of a decision-level (rather than feature-level) fusion strategy significantly reduces computational complexity. Finally, the incorporation of terrain correction (slope > 20° and aspect 60–120°) enhances classification accuracy, providing a reliable technical solution for small-scale forest monitoring. The results indicate that (1) the combination of Landsat multispectral remote sensing data and PALSAR-2 radar remote sensing data achieved the highest classification accuracy, with an overall forest classification accuracy of 97.62% in 2015 and 96.97% in 2022. The overall classification accuracy of Landsat multispectral remote sensing data alone was 93%, and that of PALSAR radar data alone was 85%, which is significantly lower than the results obtained using the combined data for forest classification. (2) Between 2015 and 2023, the forest area of Helan Mountain experienced certain fluctuations, primarily influenced by ecological and natural factors as well as variations in the accuracy of remote sensing data. In conclusion, the method proposed in this study enables more precise estimation of the forest area in the Helan Mountain region of Ningxia. This not only meets the management needs for forest resources in Helan Mountain but also provides valuable reference for forest area extraction in mountainous regions of Northwest China. Full article

The accurate detection of mowing events is important in many applications, including in agricultural contexts such as yield and fodder production, as well as biodiversity assessments, habitat modeling, and protected area monitoring. This work presents the first free and open dataset of mowing events covering the entire Austrian territory for the year 2023 at a spatial resolution of 10 × 10 m. We use the Sentinel-2 time series of the Normalized Difference Vegetation Index (NDVI) to detect mowing events, and additionally, we use the mean of the two ShortWave InfraRed (SWIR) bands to exclude misclassification caused by remaining cloud artifacts and shadows. The validation procedure builds on a visual interpretation of the Panomax webcam archive complemented by a selection of field observations. The final validation dataset consists of 211 mowing events recorded in 85 different locations across Austria. In total, 77.73% of these mowing events were detected with a mean time delay of 4 days. The detection delay in summer was smaller than the values recorded in spring and fall. The pixel-based approach exhibited superior efficacy, especially for meadows with three or more mowing events, compared to the polygon-based approach. The results of our study are consistent with those of previous works demonstrating the capacity to produce high-quality mowing event data for various grassland areas in a fully automated manner, independent from training datasets. The results could be used in research on biodiversity or in practical applications such as agricultural policy support and control, fodder supply evaluation, or impact assessment in nature restoration efforts. Full article

Light detection and ranging (LiDAR) sensor technology for people detection offers a significant advantage in data protection. However, to design these systems cost- and energy-efficiently, the relationship between the measurement data and final object detection output with deep neural networks (DNNs) has to be elaborated. Therefore, this paper presents augmentation methods to analyze the influence of the distance, resolution, noise, and shading parameters of a LiDAR sensor in real point clouds for people detection. Furthermore, their influence on object detection using DNNs was investigated. A significant reduction in the quality requirements for the point clouds was possible for the measurement setup with only minor degradation on the object list level. The DNNs PointVoxel-Region-based Convolutional Neural Network (PV-RCNN) and Sparsely Embedded Convolutional Detection (SECOND) both only show a reduction in object detection of less than 5% with a reduced resolution of up to 32 factors, for an increase in distance of 4 factors, and with a Gaussian noise up to $\mu =0$ and $\sigma =0.07$. In addition, both networks require an unshaded height of approx. 0.5 m from a detected person’s head downwards to ensure good people detection performance without special training for these cases. The results obtained, such as shadowing information, are transferred to a software program to determine the minimum number of sensors and their orientation based on the mounting height of the sensor, the sensor parameters, and the ground area under consideration, both for detection at the point cloud level and object detection level. Full article

With its fast advancements, cloud computing opens many opportunities for research in various applications from the robotics field. In our paper, we further explore the prospect of integrating Cloud AI object recognition services into an industrial robotics sorting task. Starting from our previously implemented solution on a digital twin, we are now putting our proposed architecture to the test in the real world, on an industrial robot, where factors such as illumination, shadows, different colors, and textures of the materials influence the performance of the vision system. We compare the results of our suggested method with those from an industrial machine vision software, indicating promising performance and opening additional application perspectives in the robotics field, simultaneously with the continuous improvement of Cloud and AI technology. Full article

The accurate extraction of mountainous cropland from remote sensing images remains challenging due to its fragmented plots, irregular shapes, and the terrain-induced shadows. To address this, we propose a deep learning framework, SE-ResUNet, that integrates Squeeze-and-Excitation (SE) modules into ResUNet to enhance feature representation. Leveraging Sentinel-1/2 imagery and DEM data, we fuse vegetation indices (NDVI/EVI), terrain features (Slope/TRI), and SAR polarization characteristics into 3-channel inputs, optimizing the network’s discriminative capacity. Comparative experiments on network architectures, feature combinations, and terrain conditions demonstrated the superiority of our approach. The results showed the following: (1) feature fusion (NDVI + TerrainIndex + SAR) had the best performance (OA: 97.11%; F1-score: 96.41%; IoU: 93.06%), significantly reducing shadow/cloud interference. (2) SE-ResUNet outperformed ResUNet by 3.53% for OA and 8.09% for IoU, emphasizing its ability to recalibrate channel-wise features and refine edge details. (3) The model exhibited robustness across diverse slopes/aspects (OA > 93.5%), mitigating terrain-induced misclassifications. This study provides a scalable solution for mountainous cropland mapping, supporting precision agriculture and sustainable land management. Full article