Search Results (359)

Grassland classification via remote sensing is essential for ecosystem monitoring and precision management, yet conventional satellite-based approaches are fundamentally constrained by coarse spatial resolution. To overcome this limitation, we harness high-resolution UAV multi-sensor data, integrating multi-scale image fusion with deep learning to achieve fine-scale grassland classification that satellites cannot provide. First, four categories of UAV data, including RGB, multispectral, thermal infrared, and LiDAR point cloud, were collected, and a fused image tensor consisting of 10 channels (NDVI, VCI, CHM, etc.) was constructed through orthorectification and resampling. For feature-level fusion, four deep fusion networks were designed. Among them, the MultiScale Pyramid Fusion Network, utilizing a pyramid pooling module, effectively integrated spectral and structural features, achieving optimal performance in all six image fusion evaluation metrics, including information entropy (6.84), spatial frequency (15.56), and mean gradient (12.54). Subsequently, training and validation datasets were constructed by integrating visual interpretation samples. Four backbone networks, including UNet++, DeepLabV3+, PSPNet, and FPN, were employed, and attention modules (SE, ECA, and CBAM) were introduced separately to form 12 model combinations. Results indicated that the UNet++ network combined with the SE attention module achieved the best segmentation performance on the validation set, with a mean Intersection over Union (mIoU) of 77.68%, overall accuracy (OA) of 86.98%, F1-score of 81.48%, and Kappa coefficient of 0.82. In the categories of Leymus chinensis and Puccinellia distans, producer’s accuracy (PA)/user’s accuracy (UA) reached 86.46%/82.30% and 82.40%/77.68%, respectively. Whole-image prediction validated the model’s coherent identification capability for patch boundaries. In conclusion, this study provides a systematic approach for integrating multi-source UAV remote sensing data and intelligent grassland interpretation, offering technical support for grassland ecological monitoring and resource assessment. Full article

Comprehensive evaluation of suburban landscape perception is essential for improving environmental quality and fostering integrated urban–rural development. Despite its importance, limited research has systematically extracted local visual features and analyzed influencing factors in suburban landscapes using multi-source data and machine learning. This study investigated Chongming District, a suburban area of Shanghai. Using Baidu Street View 360° panoramic images, local visual features were extracted through semantic segmentation of street view imagery, spatial multi-clustering, and random forest classification. A geographic detector model was employed to explore the relationships between landscape characteristics and their driving factors. The findings of the study indicate (1) significant spatial variations in the green visibility, sky openness, building density, road width, facility diversity, and enclosure integrity; (2) an intertwined spatial pattern of blue, green, and gray spaces; (3) the emergence of natural environment dimension factors as the primary drivers influencing the spatial configuration. In the suburban industrial dimension, the interaction between the GDP and commercial vitality exhibits the highest level of synergy. Based on these findings, targeted strategies are proposed to enhance the distinctive landscape features of Chongming Island. This research framework and methodology are specifically applied to Chongming District as a case study. Future studies should consider modifying the algorithms and index systems to better reflect other study areas, thereby ensuring the validity and precision of the results. Full article

The fusion of multi-source remote sensing data has emerged as a critical technical approach to enhancing the accuracy of ground object classification. The synergistic integration of hyperspectral images and light detection and ranging data can significantly improve the capability of identifying ground objects in complex environments. However, modeling the correlation between their heterogeneous features remains a key technical challenge. Conventional methods often result in feature redundancy due to simple concatenation, making it difficult to effectively exploit the complementary information across modalities. To address this issue, this paper proposes a cross-modal cross-attention Transformer network for the classification of hyperspectral images combined with light detection and ranging data. The proposed method aims to effectively integrate the complementary characteristics of hyperspectral images and light detection and ranging data. Specifically, it employs a two-level pyramid architecture to extract multi-scale features at the shallow level, thereby overcoming the redundancy limitations associated with traditional stacking-based fusion approaches. Furthermore, an innovative cross-attention mechanism is introduced within the Transformer encoder to dynamically capture the semantic correlations between the spectral features of hyperspectral images and the elevation information from light detection and ranging data. This enables effective feature alignment and enhancement through the adaptive allocation of attention weights. Extensive experiments conducted on three publicly available datasets demonstrate that the proposed method exhibits notable advantages over existing state-of-the-art approaches. Full article

With industrial transformation and the rise in the 15 min community life circle, optimizing walkability and preserving industrial heritage are key to revitalizing former industrial areas. This study, focusing on Shijingshan District in Beijing, proposes a walkability evaluation framework integrating multi-source big data and street-level perception. Using Points of Interest (POI) classification, which refers to the categorization of key urban amenities, pedestrian network modeling, and street view image data, a Walkability Friendliness Index is developed across four dimensions: accessibility, convenience, diversity, and safety. POI data provide insights into the spatial distribution of essential services, while pedestrian network data, derived from OpenStreetMap, model the walkable road network. Street view image data, processed through semantic segmentation, are used to assess the quality and safety of pedestrian pathways. Results indicate that core communities exhibit higher Walkability Friendliness Index scores due to better connectivity and land use diversity, while older and newly developed areas face challenges such as street discontinuity and service gaps. Accordingly, targeted optimization strategies are proposed: enhancing accessibility by repairing fragmented alleys and improving network connectivity; promoting functional diversity through infill commercial and service facilities; upgrading lighting, greenery, and barrier-free infrastructure to ensure safety; and delineating priority zones and balanced enhancement zones for differentiated improvement. This study presents a replicable technical framework encompassing data acquisition, model evaluation, and strategy development for enhancing walkability, providing valuable insights for the revitalization of industrial districts worldwide. Future research will incorporate virtual reality and subjective user feedback to further enhance the adaptability of the model to dynamic spatiotemporal changes. Full article

Slope stability monitoring in open-pit mining remains a critical challenge for geological hazard prevention, where conventional qualitative methods often fail to address dynamic risks. This study proposes an integrated framework combining empirical modeling (slope classification, hazard assessment, and safety ratings) with multi-source real-time monitoring (synthetic aperture radar, machine vision, and Global Navigation Satellite System) to achieve quantitative stability analysis. The method establishes an initial stability baseline through mechanical modeling (Bishop/Morgenstern–Price methods, safety factors: 1.35–1.75 across five mine zones) and dynamically refines it via 3D terrain displacement tracking (0.02 m to 0.16 m average cumulative displacement, 1 h sampling). Key innovations include the following: (1) a convex hull-displacement dual-criterion algorithm for automated sensitive zone identification, reducing computational costs by ~40%; (2) Ku-band synthetic aperture radar subsurface imaging coupled with a Global Navigation Satellite System and vision for centimeter-scale 3D modeling; and (3) a closed-loop feedback mechanism between empirical and real-time data. Field validation at a 140 m high phosphate mine slope demonstrated robust performance under extreme conditions. The framework advances slope risk management by enabling proactive, data-driven decision-making while maintaining compliance with safety standards. Full article

To address the complex challenge of recognizing mixed handwritten text in practical scenarios such as examination papers and to overcome the limitations of existing methods that typically focus on a single category, this paper proposes MHTR, a Multimodal Handwritten Text Adaptive Recognition algorithm. The framework comprises two key components, a Handwritten Character Classification Module and a Handwritten Text Adaptive Recognition Module, which work in conjunction. The classification module performs fine-grained analysis of the input image, identifying different types of handwritten content such as Chinese characters, digits, and mathematical formula. Based on these results, the recognition module dynamically selects specialized sub-networks tailored to each category, thereby enhancing recognition accuracy. To further reduce errors caused by similar character shapes and diverse handwriting styles, a Context-aware Recognition Optimization Module is introduced. This module captures local semantic and structural information, improving the model’s understanding of character sequences and boosting recognition performance. Recognizing the limitations of existing public handwriting datasets, particularly their lack of diversity in character categories and writing styles, this study constructs a heterogeneous, integrated handwritten text dataset. The dataset combines samples from multiple sources, including Chinese characters, numerals, and mathematical symbols, and features high structural complexity and stylistic variation to better reflect real-world application needs. Experimental results show that MHTR achieves a recognition accuracy of 86.63% on the constructed dataset, significantly outperforming existing methods. Furthermore, the context-aware optimization module demonstrates strong adaptive correction capabilities in various misrecognition scenarios, confirming the effectiveness and practicality of the proposed approach for complex, multi-category handwritten text recognition tasks. Full article

The present-day issues related to the cotton-growing industry, namely yield estimation, pest effect, and growth phase diagnostics, call for integrated, scalable monitoring solutions. This write-up reveals Cotton Multitask Learning (CMTL), a transformer-driven multitask framework that launches three major agronomic tasks from UAV pictures at one go: boll detection, pest damage segmentation, and phenological stage classification. CMTL does not change separate pipelines, but rather merges these goals using a Cross-Level Multi-Granular Encoder (CLMGE) and a Multitask Self-Distilled Attention Fusion (MSDAF) module that both allow mutual learning across tasks and still keep their specific features. The biologically guided Stage Consistency Loss is the part of the architecture of the network that enables the system to carry out growth stage transitions that occur in reality. We executed CMTL on a tri-source UAV dataset that fused over 2100 labeled images from public and private collections, representing a variety of crop stages and conditions. The model showed its virtues state-of-the-art baselines in all the tasks: setting 0.913 mAP for boll detection, 0.832 IoU for pest segmentation, and 0.936 accuracy for growth stage classification. Additionally, it runs at the fastest speed of performance on edge devices such as NVIDIA Jetson Xavier NX (Manufactured in Shanghai, China), which makes it ideal for deployment. These outcomes evoke CMTL’s promise as a single and productive instrument of aerial crop intelligence in precision cotton agriculture. Full article

The classification of submarine topography and geomorphology is essential for marine resource exploitation and ocean engineering, with wide-ranging implications in marine geology, disaster assessment, resource exploration, and autonomous underwater navigation. Submarine landscapes are highly complex and diverse. Traditional visual interpretation methods are not only inefficient and subjective but also lack the precision required for high-accuracy classification. While many machine learning and deep learning models have achieved promising results in image classification, limited work has been performed on integrating backscatter and bathymetric data for multi-source processing. Existing approaches often suffer from high computational costs and excessive hyperparameter demands. In this study, we propose a novel approach that integrates pruning-enhanced ConDenseNet with label smoothing regularization to reduce misclassification, strengthen the cross-entropy loss function, and significantly lower model complexity. Our method improves classification accuracy by 2% to 10%, reduces the number of hyperparameters by 50% to 96%, and cuts computation time by 50% to 85.5% compared to state-of-the-art models, including AlexNet, VGG, ResNet, and Vision Transformer. These results demonstrate the effectiveness and efficiency of our model for multi-source submarine topography classification. Full article

In order to address the limitations of the number of label samples in practical accurate classification scenarios and the problems of overfitting and an insufficient generalization ability caused by Few-Shot Learning (FSL) in hyperspectral image classification (HSIC), this paper designs and implements a neural architecture search (NAS) for a few-shot HSI classification method that combines meta learning. Firstly, a multi-source domain learning framework was constructed to integrate heterogeneous natural images and homogeneous remote sensing images to improve the information breadth of few-sample learning, enabling the final network to enhance its generalization ability under limited labeled samples by learning the similarity between different data sources. Secondly, by constructing precise and robust search spaces and deploying different units at different locations, the classification accuracy and model transfer robustness of the final network can be improved. This method fully utilizes spatial texture information and rich category information of multi-source data and transfers the learned meta knowledge to the optimal architecture for HSIC execution through precise and robust search space design, achieving HSIC tasks with limited samples. Experimental results have shown that our proposed method achieved an overall accuracy (OA) of 98.57%, 78.39%, and 98.74% for classification on the Pavia Center, Indian Pine, and WHU-Hi-LongKou datasets, respectively. It is fully demonstrated that utilizing spatial texture information and rich category information of multi-source data, and through precise and robust search space design, the learned meta knowledge is fully transmitted to the optimal architecture for HSIC, perfectly achieving classification tasks with few-shot samples. Full article

Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. Full article

Multi-source remote sensing spatiotemporal fusion aims to enhance the temporal continuity of high-spatial, low-temporal-resolution images. In recent years, deep learning-based spatiotemporal fusion methods have achieved significant progress in this field. However, existing methods face three major challenges. First, large differences in spatial resolution among heterogeneous remote sensing images hinder the reconstruction of high-quality texture details. Second, most current deep learning-based methods prioritize spatial information while overlooking spectral information. Third, these methods often depend on complex network architectures, resulting in high computational costs. To address the aforementioned challenges, this article proposes a Sparse Fast Transformer fusion method based on Generative Adversarial Network (SFT-GAN). First, the method introduces a multi-scale feature extraction and fusion architecture to capture temporal variation features and spatial detail features across multiple scales. A channel attention mechanism is subsequently designed to integrate these heterogeneous features adaptively. Secondly, two information compensation modules are introduced: detail compensation module, which enhances high-frequency information to improve the fidelity of spatial details; spectral compensation module, which improves spectral fidelity by leveraging the intrinsic spectral correlation of the image. In addition, the proposed sparse fast transformer significantly reduces both the computational and memory complexity of the method. Experimental results on four publicly available benchmark datasets showed that the proposed SFT-GAN achieved the best performance compared with state-of-the-art methods in fusion accuracy while reducing computational cost by approximately 70%. Additional classification experiments further validated the practical effectiveness of SFT-GAN. Overall, this approach presents a new paradigm for balancing accuracy and efficiency in spatiotemporal fusion. Full article

A timely and accurate distribution of crop types and cropping patterns provides a crucial reference for the management of agriculture and food security. However, accurately mapping crop types and cropping patterns in subtropical hilly and mountainous areas often face challenges such as mixed pixels resulted from fragmented patches and difficulty in obtaining optical satellites due to a frequently cloudy and rainy climate. Here we propose a crop type and cropping pattern mapping framework in subtropical hilly and mountainous areas, considering multiple sources of satellites (i.e., Landsat 8/9, Sentinel-2, and Sentinel-1 images and GF 1/2/7). To develop this framework, six types of variables from multi-sources data were applied in a random forest classifier to map major summer crop types (singe-cropped rice and double-cropped rice) and winter crop types (rapeseed). Multi-scale segmentation methods were applied to improve the boundaries of the classified results. The results show the following: (1) Each type of satellite data has at least one variable selected as an important feature for both winter and summer crop type classification. Apart from the endmember variables, the other five extracted variable types are selected by the RF classifier for both winter and summer crop classifications. (2) SAR data can capture the key information of summer crops when optical data is limited, and the addition of SAR data can significantly improve the accuracy as to summer crop types. (3) The overall accuracy (OA) of both summer and winter crop type mapping exceeded 95%, with clear and relatively accurate cropland boundaries. Area evaluation showed a small bias in terms of the classified area of rapeseed, single-cropped rice, and double-cropped rice from statistical records. (4) Further visual examination of the spatial distribution showed a better performance of the classified crop types compared to three existing products. The results suggest that the proposed method has great potential in accurately mapping crop types in a complex subtropical planting environment. Full article

Internet-of-Things (IoT) approaches are continually introducing new sensors into the fields of agriculture and animal welfare. The application of multi-sensor data fusion to these domains remains a complex and open-ended challenge that defies straightforward optimization, often requiring iterative testing and refinement. To respond to this need, we have created a new open-source framework as well as a corresponding Python tool which we call the “Data Fusion Explorer (DFE)”. We demonstrated and evaluated the effectiveness of our proposed framework using four early-stage datasets from diverse disciplines, including animal/environmental tracking, agrarian monitoring, and food quality assessment. This included data across multiple common formats including single, array, and image data, as well as classification or regression and temporal or spatial distributions. We compared various pipeline schemes, such as low-level against mid-level fusion, or the placement of dimensional reduction. Based on their space and time complexities, we then highlighted how these pipelines may be used for different purposes depending on the given problem. As an example, we observed that early feature extraction reduced time and space complexity in agrarian data. Additionally, independent component analysis outperformed principal component analysis slightly in a sweet potato imaging dataset. Lastly, we benchmarked the DFE tool with respect to the Vanilla Python3 packages using our four datasets’ pipelines and observed a significant reduction, usually more than 50%, in coding requirements for users in almost every dataset, suggesting the usefulness of this package for interdisciplinary researchers in the field. Full article

Fire regime (FR) is a key element in the study of ecosystem dynamics, supporting natural resource management planning by identifying gaps in fire patterns in time and space and planning to assess ecological conditions. Due to the insufficient consideration of integrated characterization factors, especially the insufficient research on fire season types (FST), the current understanding of the spatial heterogeneity of fire patterns in China is still limited, and it is necessary to use FST as a key dimension to classify FR zones more accurately. This study extracted 13 fire characteristic variables based on Moderate Resolution Imaging Spectroradiometer (MODIS) burned area data (MCD64A1), active fire data (MODIS Collection 6), and land cover data (MCD12Q1) from 2001 to 2023. The study systematically analyzed the frequency, intensity, spatial distribution and seasonal characteristics of fires across China. By using data normalization and the k-means clustering algorithm, the study area was divided into five types of FR zones (FR 1–5) with significant differences. The burned areas of the five FR zones account for 67.76%, 13.88%, 4.87%, 12.94%, and 0.55% of the total burned area across the country over the 23-year study period, respectively. Among them, fires in the Northeast China Plain and North China Plain cropland areas (FR 1) exhibit a bimodal distribution, with the peak period concentrated in April and June, respectively; the southern forest and savanna region (FR 2) is dominated by high-frequency, small-scale, unimodal fires, peaking in February; the central grassland region (FR 3) experiences high-intensity, low-frequency fires, with a peak in April; the east central forest region (FR 4) is characterized by low-frequency, high-intensity fires; and the western grassland region (FR 5) experiences low-frequency fires with significant inter-annual fluctuations. Among the five zones, FST consistently ranks within the top five contributors, with contribution rates of 0.39, 0.31, 0.44, 0.27, and 0.55, respectively, confirming that the inclusion of FST is a reasonable and necessary choice when constructing FR zones. By integrating multi-source remote sensing data, this study has established a novel FR classification system that encompasses fire frequency, intensity, and particularly FST. This approach transcends the traditional single-factor classification, demonstrating that seasonal characteristics are indispensable for accurately delineating fire conditions. The resultant zoning system effectively overcomes the limitations of traditional methods, providing a scientific basis for localized fire risk warning and differentiated prevention and control strategies. Full article

Soil salinization poses a significant threat to agricultural productivity, food security, and ecological sustainability in arid and semi-arid regions. Effectively and timely mapping of different degrees of salinized soils is essential for sustainable land management and ecological restoration. Although deep learning (DL) methods have been widely employed for soil salinization extraction from remote sensing (RS) data, the integration of multi-source RS data with DL methods remains challenging due to issues such as limited data availability, speckle noise, geometric distortions, and suboptimal data fusion strategies. This study focuses on the Keriya Oasis, Xinjiang, China, utilizing RS data, including Sentinel-2 multispectral and GF-3 full-polarimetric SAR (PolSAR) images, to conduct soil salinization classification. We propose a Dual-Modal deep learning network for Soil Salinization named DMSSNet, which aims to improve the mapping accuracy of salinization soils by effectively fusing spectral and polarimetric features. DMSSNet incorporates self-attention mechanisms and a Convolutional Block Attention Module (CBAM) within a hierarchical fusion framework, enabling the model to capture both intra-modal and cross-modal dependencies and to improve spatial feature representation. Polarimetric decomposition features and spectral indices are jointly exploited to characterize diverse land surface conditions. Comprehensive field surveys and expert interpretation were employed to construct a high-quality training and validation dataset. Experimental results indicate that DMSSNet achieves an overall accuracy of 92.94%, a Kappa coefficient of 79.12%, and a macro F1-score of 86.52%, positively outperforming conventional DL models (ResUNet, SegNet, DeepLabv3+). The results confirm the superiority of attention-guided dual-branch fusion networks for distinguishing varying degrees of soil salinization across heterogeneous landscapes and highlight the value of integrating Sentinel-2 optical and GF-3 PolSAR data for complex land surface classification tasks. Full article