Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Leiguang Wang has a total of 173 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • AFF-Net: Adaptive Frequency-Domain Fusion in a Dual-Stream Transformer With Wavelet-Assisted Alignment for Remote Sensing Image Segmentation

    by Qingyang Ren, Tiancheng Ma, Leiguang Wang, Chen Zheng

    Remote sensing semantic segmentation is essential for geoscientific analysis. Recently, although multimodal image fusion has achieved notable improvements over single-image approaches, existing methods still suffer from insufficient utilization of the observed information, especially the alignment and fusion of multimodal details information. To address above issues, a novel adaptive frequency-domain fusion network (AFF-Net) is proposed in this letter to achieve effective fusion of visible images and DSM data through a Frequency-Domain Fusion (FDF) module, and enhance the recognition capability of target boundaries via a Semantic-Guided Detail Alignment (SDA) strategy. Specifically, the FDF module conducts an adaptive frequency-wise alignment and fusion scheme between visible images and DSM by decomposing them into low and high frequency subbands, enabling the model to capture more fine-grained complementary information across various frequency domains, rather than coarse-grained fusion in the spatial domain. The SDA strategy further restores high-frequency boundary details while suppressing noise, enabling precise object delineation. AFF-Net was evaluated on the ISPRS Vaihingen and Potsdam datasets, achieving mIoU scores of 84.87%, 87.11%, as well as mF1 scores of 91.61% and 92.93%, respectively. These results show better performances over state-of-the-art methods and verify the effectiveness and superiority of the proposed method. The code is available at https://github.com/lanmao-create/AFF-Net.

  • Open Access

    An Improved Framework for Forest Fire Severity Assessment in Mountainous Areas Based on the dNBR Index: A Case Study from Central Yunnan, China

    by Li Han, Yun Liu, Qiuhua Wang, Tengteng Long, Ning Lu, Leiguang Wang, Weiheng Xu

    Forest fires pose a considerable threat to the security of ecosystems and human society, rendering accurate assessments of fire severity critical for ecological recovery and effective fire management. The differenced Normalized Burn Ratio (dNBR) has been employed to evaluate forest fire severity; however, it presents notable uncertainties owing to variations in data sources, temporal phases, and environmental factors. To address these challenges, this study analyzed 10 forest fires occurring between 2006 and 2023 in central Yunnan Province, China. First, a rapid sampling method utilizing very high-resolution imagery was developed to assess the performance of dNBR classification under varying conditions. Second, the study identified the optimal post-fire observation window and compared classification thresholds and accuracy between Landsat and Sentinel-2 imagery in assessing fire severity. Finally, the research explored the impacts of topographic correction and pre-fire vegetation differences on classification outcomes. The findings revealed the following: (1) Imagery captured in the spring of the fire year, characterized by minimal vegetation interference, demonstrated the highest classification stability and superior capability for identifying high-severity burns. (2) Landsat outperformed Sentinel-2 in regional accuracy (0.92 vs. 0.87), and direct threshold transfer between sensors resulted in a 39% underestimation of high-severity areas, underscoring the necessity for sensor-specific calibration. (3) Topographic correction provided limited practical benefits, merely yielding a marginal improvement in accuracy (+1.44%) with the SCS+C model in steep terrain, and was generally unnecessary. (4) The influence of pre-fire vegetation was discovered to be threshold-dependent: dNBR performed reliably in forests with pre-fire NDVI > 0.5, while adjusted approaches were solely recommended for sparse or heterogeneous vegetation. Overall, this study establishes a systematic framework for optimizing dNBR-based severity assessment, enhancing its accuracy and operational utility in forest fire management.

  • Open Access

    Slope–Wind Coupling Effects on Fire Behavior and Emission Dynamics During Prescribed Burning in Mountainous Yunnan Pine Forests

    by Tengteng Long, Yun Liu, Xiaohui Pu, Zhi Li, Shun Li, Qiuhua Wang, Li Han, Ning Lu, Leiguang Wang, Weiheng Xu

    Prescribed burning is important for reducing wildfire risk and regulating fuel loads, but its implementation in mountainous forests is strongly influenced by the coupled effects of the wind field and topography, making it difficult to control. This study focuses on Yunnan pine (Pinus yunnanensis) forests in southwestern China. A three-dimensional Fire Dynamics Simulator (FDS) combined with measured fuel characteristics was used to simulate 21 slope (0–35°) and wind speed (0–2 m s−1) combinations to quantitatively analyze the fire spread, flame structure, and gaseous emission characteristics during downslope prescribed burning. The local fire spread rate (ROS), evaluated along three lateral lines (Y = 2.5, 5.0, and 7.5 m), exhibits a non-monotonic dependence on slope over the tested range, with a minimum near 30° and a modest rebound at 35°. A downslope wind of 1 m s−1 promotes near-surface heating and accelerates spread, whereas a stronger wind of 2 m s−1 lifts flames away from the fuel bed and suppresses combustion. Thermal field analysis reveals that peak temperature decreases with increasing slope and that a late-stage secondary heating episode occurs at 35°. CO2 emissions are significantly positively correlated with fuel consumption, reaching a peak of 717.5 kg under a 35° slope and no-wind conditions. CO emissions, as an indicator of combustion efficiency, reach their highest value of 2.23 kg at a 35° slope and a wind speed of 1 m s−1, indicating that their trend is not entirely consistent with the ROS and temperature and that there is a certain degree of decoupling. The interaction between slope and wind speed transforms fire behavior from a cooperative to a competitive mechanism, and the topography–wind field coupling provides differentiated control over the combustion intensity and completeness. This study provides a scientific basis for the safe implementation of mountain burning programs and for regional carbon emission assessments.

  • Open Access

    Terrain-Aware Self-Supervised Representation Learning for Tree Species Mapping in Mountainous Regions Under Limited Field Samples

    by Li He, Leiguang Wang, Liang Hong, Qinling Dai, Wei Gu, Xingyue Du, Mingqi Yang, Juanjuan Liu, Yaoming Feng

    Accurate tree species mapping is critical for forest inventory, biodiversity assessment, and ecosystem management. In mountainous regions, terrain-induced radiometric non-stationarity and limited field access often produce scarce, clustered, and environmentally biased samples, limiting model generalization. To address this issue, this study proposes a terrain-aware self-supervised representation learning framework for tree species classification under small-sample conditions. The framework integrates terrain information into representation learning and adopts a hybrid contrastive–generative self-supervised strategy to learn discriminative and terrain-robust features from large volumes of unlabeled multi-source remote sensing data. These learned representations are subsequently combined with limited field samples to produce regional-scale tree species maps. Experiments conducted across Yunnan Province, China, using Sentinel-1, Sentinel-2 and Landsat time-series data show that the proposed framework substantially improvesa class separability and classification robustness in complex mountainous environments. The framework achieves an overall accuracy of 75.8%, significantly outperforming conventional feature engineering (38.3–40.6%) and supervised deep learning models (37.3–47.8%). Species with relatively homogeneous structure and strong ecological niche dependence can be accurately mapped with limited training samples, whereas structurally complex forest communities require broader environmental sample coverage. Overall, the results highlight the potential of terrain-aware self-supervised representation learning as a scalable and data-efficient paradigm for forest mapping in mountainous and environmentally heterogeneous regions.


  • Open Access

    Accurate Detection of Large-Leaf Tea Buds in Mountainous Tea Plantations Based on an Improved YOLO Framework

    by Juxiang He, Er Wang, Yun Liu, Ning Lu, Leiguang Wang, Weiheng Xu

    Tea buds are the key raw material for high-quality tea production, and their accurate perception is essential for intelligent harvesting and quality-oriented management. However, tea bud detection in mountainous large-leaf tea plantations remains challenging because small, densely distributed targets are embedded in complex field environments, significantly limiting the stability and accuracy of existing detection methods. To address these challenges, this study proposes an improved tea bud detection model, termed YOLO-LAR, for mountainous large-leaf tea plantations in Yunnan Province, China, which is developed as an enhanced framework based on the YOLOv11 baseline. YOLO-LAR improves feature representation through multi-scale feature fusion, enabling more effective detection of densely distributed small tea buds. In addition, an optimized downsampling strategy is employed to preserve critical spatial information, and a context-enhanced feature aggregation mechanism is introduced to strengthen robustness under complex backgrounds and illumination variations. The results demonstrate that YOLO-LAR achieves precision, recall, mAP@0.50, and mAP@0.50:0.95 of 0.959, 0.908, 0.961, and 0.814, respectively, outperforming mainstream YOLO-based models, including YOLOv11n, YOLOv10n, and YOLOv8n. These results indicate that YOLO-LAR provides an effective and practical solution for accurate tea bud detection, offering strong technical support for intelligent harvesting and precision management in mountainous tea plantation environments.


  • Geospatial Prior Guided Confused-Class Data Augmentation for Semantic Segmentation of Remote Sensing Images

    by Jingying Li, Guoying Liu, Jiaxuan Li, Tiancheng Ma, Leiguang Wang, Chen Zheng

    Semantic segmentation of high spatial resolution remote sensing images plays a crucial role in diverse applications. Deep learning-based methods have emerged as the dominant approach in this field. However, existing methods face the challenge of effectively using the information in annotated training data, resulting in limited model performance. Data augmentation is a commonly used technique to better reveal the information embedded in the data through appropriate transformations. However, these methods usually fail to account for the unique characteristics of remote sensing images, such as the high spectral similarity among different classes and intra-class variation among distinct objects. This oversight hinders the model’s ability to distinguish between spectrally similar classes, resulting in persistent misclassifications. To address these challenges, we propose a novel geospatial prior guided confused-class data augmentation (GCA) method for semantic segmentation of remote sensing images. By emphasizing the occurrence of confused classes within augmented training data, GCA compels the model to focus on learning discriminative features to improve class separability. GCA consists of three key modules: geospatial prior information extraction module (module G), confused-class similar units detection module (C), and confused-class data augmentation module (module A). Specifically, module G extracts geographic units and their spatial relationships. Module C identifies highly similar units from confused classes that are prone to misclassification. Module A generates challenging training data by emphasizing confused-class similar units under the guidance of geospatial priors. Experiments on the GID and LoveDA datasets demonstrate that the proposed GCA method shows a better performance than state-of-the-art data augmentation methods. The GCA code is publicly available at https://github.com/Jingying-Li/GCA.


  • Remote Sensing Image Semantic Segmentation Utilizing Geographical Element Association Features

    by Ruiqi Yang, Haoyu Fu, Nan Chen, Shilin Tao, Liang Hong, Leiguang Wang, Chen Zheng

    Semantic segmentation of high-resolution remote sensing images remains challenging due to complex spatial structures, fine-grained category variations, and hierarchical semantic dependencies. Existing deep learning models often treat semantic categories as independent, flat labels, which leads to inconsistent predictions across hierarchical levels (e.g., a pixel predicted as Tree but not as Vegetation) and weak generalization in heterogeneous landscapes. To address these issues, we propose HAG Net (Hierarchical Attention Gate Multi-Residual UNet), a novel framework that explicitly models hierarchical semantics and enforces cross-level consistency. First, a multi-residual encoder–decoder backbone with hierarchical attention gates (HAGs) enhances multi-scale representation while filtering irrelevant background noise. Second, a Mixture-of-Head (MoH) attention module enables bidirectional semantic interaction between coarse- and fine-level features, mitigating error propagation caused by unidirectional designs. Third, a Hierarchical Interaction (HI) Loss introduces a dynamic category interaction matrix to adaptively constrain predictions, ensuring consistency across levels. Extensive experiments on two large-scale datasets, GID (5- and 15-class) and Ascend Cup 2020 (8- and 17-class), demonstrate that HAG Net consistently outperforms state-of-the-art methods, including DeepLabv3+, CGGLNet, and MAE-BG. Specifically, HAG Net achieves up to 4.5 % improvement in FWIoU and significantly enhances per-class accuracy for small and structurally complex objects. These results confirm the effectiveness of incorporating hierarchical semantics into segmentation networks and highlight the potential of HAG Net for large-scale land cover mapping, ecological monitoring, and urban planning applications.The source code is available at: https://github.com/yangruiqi-kiki/HAG.


  • Open Access

    An Adaptive Progressive Recursive Network for Pansharpening

    by Zhipeng Zhao, Yu Liu, Qingwei Tong, Kui Ran, Qinling Dai, ZhiTao Fu, Leiguang Wang

    Pansharpening faces inherent limitations in reconciling spatial enhancement with spectral fidelity due to the fixed interpolation-based upsampling of low-resolution multispectral (LRMS) images. To overcome this, we propose a novel Dense Adaptive Upsampling Module (DAUM) that learns pixel-wise refinement weights to optimize bilinear interpolation, thereby adaptively recovering spatial details without artificial information injection. Building upon this, we introduce ProRecFusionNet (PRFN) with dual core components: (1) a Gradual Fusion Module (GFM) enabling coarse-to-fine alignment of panchromatic (PAN) and upsampled LRMS features via hybrid CNN-Transformer interactions, and (2) a Recursive Fusion Module (RFM) iteratively suppressing artifacts through multi-scale residual optimization. This holistic framework achieves synergistic complementarity of high frequency spatial details (from PAN) and spectral signatures (from LRMS). Extensive experiments on GaoFen-2, QuickBird, and WorldView-II show that PRFN surpasses nine leading methods, with average gains of −0.916 in SAM, −0.849 in ERGAS, and +0.042 in HQNR (vs. the per-dataset mean of nine baselines). This cross-sensor robustness supports large-scale land-cover monitoring. Code: https://github.com/Zhipeng Zhao99/ProRecFusionNet-main.


  • Open Access

    Enhancing Aboveground Biomass Estimation in Rubber Plantations Using UAV Multispectral Data for Satellite Upscaling

    by Hongjian Tan, Weili Kou, Weiheng Xu, Leiguang Wang, Huan Wang, Ning Lu

    The estimation of rubber plantation aboveground biomass (AGB) is crucial for carbon sequestration assessment and management optimization. Unmanned Aerial Vehicles (UAVs) fitted with multispectral sensors present an economical approach for local-scale AGB monitoring. However, the prevailing studies primarily concentrate on spectral characteristics and algorithmic enhancements, failing to incorporate key ecological parameters such as stand age. Moreover, the current approaches remain constrained to local-scale assessments due to the absence of reliable upscaling methodologies from UAV to satellite platforms, limiting their applicability for regional monitoring. Thus, this study aims to establish an improved estimation model for rubber plantation AGB based on UAV multispectral imagery and stand age, develop an upscaling algorithm to bridge the gap between UAV and satellite scales, and ultimately achieve accurate regional-scale monitoring of rubber forest AGB. Combining optimized multispectral features, Landsat-derived stand age, and machine learning techniques yields the most accurate UAV-scale AGB estimates in this study, with performance metrics of R2 = 0.90, an RMSE = 13.24 t/ha, and an MAE = 11.09 t/ha. Notably, the novel ‘UAV-satellite’ upscaling approach proposed in this study enables regional-scale AGB estimation using Sentinel-2 imagery, with remarkable consistency (correlation coefficient of 0.93). The developed framework synergistically combines Landsat-derived stand age data with spectral features, effectively improving rubber plantation AGB estimation accuracy through machine learning and enabling UAVs to replace manual measurements. This cross-scale upscaling framework demonstrates applicability beyond rubber plantation AGB monitoring, while providing novel insights for estimating critical parameters, including regional-scale stock volume and leaf area index, across diverse tree species.