Large-scale Mapping Research Articles

A Method for Cropland Layer Extraction in Complex Scenes Integrating Edge Features and Semantic Segmentation

Cultivated land is crucial for food production and security. In complex environments like mountainous regions, the fragmented nature of the cultivated land complicates rapid and accurate information acquisition. Deep learning has become essential for extracting cultivated land but faces challenges such as edge detail loss and limited adaptability. This study introduces a novel approach that combines geographical zonal stratification with the temporal characteristics of medium-resolution remote sensing images for identifying cultivated land. The methodology involves geographically zoning and stratifying the study area, and then integrating semantic segmentation and edge detection to analyze remote sensing images and generate initial extraction results. These results are refined through post-processing with medium-resolution imagery classification to produce a detailed map of the cultivated land distribution. The method achieved an overall extraction accuracy of 95.07% in Tongnan District, with specific accuracies of 92.49% for flat cultivated land, 96.18% for terraced cultivated land, 93.80% for sloping cultivated land, and 78.83% for forest intercrop land. The results indicate that, compared to traditional methods, this approach is faster and more accurate, reducing both false positives and omissions. This paper presents a new methodological framework for large-scale cropland mapping in complex scenarios, offering valuable insights for subsequent cropland extraction in challenging environments.

A 3D visible space index for evaluating urban openness based on the digital urban model

The evaluation of urban open spaces plays an important role in landscape design, urban management and public security. However, few three-dimensional openness approaches with high accuracy and applicability to multiple data models have been developed. A method has been developed to measure the openness of an arbitrary location in an urban space accurately. This method is based mainly on the geometric subdivision of 3D space. First, a complete visual sphere was constructed with the viewpoint as the centre. The visual sphere was subsequently uniformly subdivided by multiple lines of sight at certain horizontal and vertical angle intervals, generating multiple discrete visual difference elements (VDEs). Finally, the specific visible volumes in each VDE were calculated separately to accumulate the all-visible volumes. The visible space index (VSI) was defined as the ratio of all visible space volumes to the visual sphere. The results indicate that the proposed method can accurately calculate the volume of visible space at any location, and the corresponding VSI reflects the difference of visible space in urban environments under different terrain conditions. The proposed method is expected to provide technical support for large-scale urban openness mapping, consequently contributing to the unified evaluation of urban space.

A Second Look at Label Density in Large-Scale Online Maps

A Second Look at Label Density in Large-Scale Online Maps

A New Precise Point Positioning with Ambiguity Resolution (PPP-AR) Approach for Ground Control Point Positioning for Photogrammetric Generation with Unmanned Aerial Vehicles

Unmanned aerial vehicles (UAVs) are now widely preferred systems that are capable of rapid mapping and generating topographic models with relatively high positional accuracy. Since the integrated GNSS receivers of UAVs do not allow for sufficiently accurate outcomes either horizontally or vertically, a conventional method is to use ground control points (GCPs) to perform bundle block adjustment (BBA) of the outcomes. Since the number of GCPs to be installed limits the process in UAV operations, there is an important research question whether the precise point positioning (PPP) method can be an alternative when the real-time kinematic (RTK), network RTK, and post-process kinematic (PPK) techniques cannot be used to measure GCPs. This study introduces a novel approach using precise point positioning with ambiguity resolution (PPP-AR) for ground control point (GCP) positioning in UAV photogrammetry. For this purpose, the results are evaluated by comparing the horizontal and vertical coordinates obtained from the 24 h GNSS sessions of six calibration pillars in the field and the horizontal length differences obtained by electronic distance measurement (EDM). Bartlett’s test is applied to statistically determine the accuracy of the results. The results indicate that the coordinates obtained from a two-hour PPP-AR session show no significant difference from those acquired in a 30 min session, demonstrating PPP-AR to be a viable alternative for GCP positioning. Therefore, the PPP technique can be used for the BBA of GCPs to be established for UAVs in large-scale map generation. However, the number of GCPs to be selected should be four or more, which should be homogeneously distributed over the study area.

Copying-lineages of portolan chart metrics and implications of their pre-medieval origin

ABSTRACT Seven portolan charts and atlases (including the anonymous Rex Tholomeus chart) made between 1311 and 1538 were cartometrically analysed. The findings indicate that their geometry was not improved chronologically and that the accuracy of Pietro Vesconte's charts (1311–13) was never surpassed. Portolan charts and atlases appear to be mosaics composed of subsections, each with variable metrics and accuracy levels that are, on average, twice as great in comparison to their Mediterranean and Black Sea areas (as a whole), and it is highly unlikely that they are genuine late medieval products, which is also supported by historical evidence. Their anticlockwise tilts fit well with the tilt of the Gibraltar-Antioch line on modern maps that closely approximate Ptolemy I and Ptolemy II projections centred near Gibraltar and with their meridian tilts for areas around Genoa. If late medieval Italian cartographers had acquired a collection of maps or charts from before the Middle Ages, it is theoretically feasible that they could have achieved the typical geometry of portolan charts by graphically combining their manuscript copies of large-scale regional maps in Mercator or Mercator-like projection, using a small-scale map in conic or pseudoconic projection (on which the convergence of meridians is displayed) as a template.

Large-Scale Mapping of Complex Forest Typologies Using Multispectral Imagery and Low-Density Airborne LiDAR: A Case Study in Pinsapo Fir Forests

Climate change increases the vulnerability of relict forests. To address this problem, regional Forest Services require silvicultural and conservation actions to designate specific forest management alternatives. In this context, the main objective of this study was to develop a methodology to map complex Abies pinsapo forest typologies using multispectral and low-density airborne LiDAR data and machine learning. Stand density, species composition and cover were used to identify seven forest typologies. Random forest resulted as the more accurate model (OA = 0.62; Kappa = 0.43) to classify those types based on multispectral and LiDAR data, although showing a moderate model performance. Classification performance showed great differences between forest types with better results for the uneven-aged stands compared to the even-aged and two-aged stands. The developed typology was applied to supply local forest managers with more accurate forest maps that can be used to improve forest management plans. The typology proposed is easy to apply in forest management practices since it only uses as input the diameter at breast height, tree density and specific composition. The study demonstrated the potential of low-density LiDAR data combined with spectral information from high-resolution orthophotos to predict the structural characteristics of complex forest typologies.

A new transferable deep learning approach for crop mapping

ABSTRACT Accurate crop mapping provides important information for government decision-making and agricultural management. Recent advancements in deep learning have significantly enhanced the capabilities of remote sensing-based crop mapping. In this study, we developed a new deep learning approach, DSH, which comprises three modules, DeepLabV3+ (D), channel self-attention (S), and histogram matching (H). The DeepLabV3+ module learns the spatial distribution of crops in the spatial and spectral dimensions. The channel self-attention module was used to enhance the weights of the important features. The histogram-matching module addresses the domain gap between the training and testing images and enhances the transferability of the DSH. In addition, the input data of the DSH are monthly synthesized Sentinel-2 data, thus relaxing the data collection requirements. The performance of the DSH was evaluated and benchmarked against HRNetV2, DeepLabV3+, and random forest (RF) at eight sites in the U.S. China, and France with different farming structures, climate conditions, and landscape complexities. Temporal transfer revealed that the classification performance of DSH improved as the growth season progressed, peaked in the peak growth season (August), and then declined at each study site. The DSH model trained during the peak growth season demonstrated superior temporal transferability. Spatial transfer experiments demonstrated that transferring DSH to sites with similar planting structures achieved higher precision than full spatial transfers. Spatiotemporal transfer experiments conducted at eight sites over three years (2020–2022) demonstrated an average overall accuracy (OA) of 88.1% for DSH, highlighting the importance of similar planting structures for effective spatiotemporal transfer. DSH outperformed HRNetV2, DeepLabV3+, and RF in OA, producer’s accuracy, and user’s accuracy at all eight study sites. Notably, DSH exhibited comparable performance during both the peak and full growth seasons, with an average OA of 93.9%. The classification accuracy of test images after histogram matching remained stable from 2020 to 2022, whereas the accuracy of raw test images fluctuated annually. This indicates that histogram matching is effective in improving the transferability of DSH. Embedding the channel self-attention module into the position of the high-level features had a more significant impact on improving DSH’s performance than other configurations. Visualizing features from the channel self-attention and high-level layers revealed that integrating the channel self-attention module with DeepLabV3+‘s high-level features significantly improved crop mapping by enhancing relevant semantic information. Overall, DSH exhibits robust spatiotemporal generalizability and requires minimal input data, making it suitable for large-scale crop mapping.

Soil cover on complex glacial terrain and challenges for large-scale soil mapping using the World Reference Base (WRB) classification system

In conditions of complex glacial topography, large-scale soil mapping (1:10 000) according to the World reference base for soil resources (WRB) 2022 classification faces significant challenges. High diversity of reference soil groups (RSG) and qualifiers can be found in a small area, and this diversity is not related to the influence of a single but rather to a set of soil-forming factors. As a part of the study, the classification of soils on postglacial landscape was conducted using the WRB 2022 classification system. The analysis was focused on examining relationships between RSG and qualifiers, and also with type of geological deposits, location on the terrain, human activities (drainage of agricultural land, soil tillage and erosion). Survey showed that, in a relatively small area, soil cover consisted of WRB RSG such as Luvisols, Retisols, Regosols, Stagnosols, Gleysols Phaeozems, Planosols, Podzols, Histosols and Anthrosols, with the respective sets of qualifiers. Soils corresponding to the Anthrosol RSG were formed during the construction of a drainage system by burying the former soil with deeper material and later by translocation of colluvium by soil erosion. In the complex glacial topography, the distribution of RSG and their qualifiers is specific, which poses a number of challenges for soil mapping. The study confirmed the possibility of WRB classification for large-scale mapping of agricultural soils on postglacial landscape at the RSG level. The use of qualifiers for definition of mapping units in similar conditions of complex terrain and geological deposits (when mapping on a scale of 1:10 000) is possible only by increasing sampling density.

Three-dimensional fiber orientation mapping of the human brain at micrometer resolution.

The accurate measurement of three-dimensional (3D) fiber orientation in the brain is crucial for reconstructing fiber pathways and studying their involvement in neurological diseases. Comprehensive reconstruction of axonal tracts and small fascicles requires high-resolution technology beyond the ability of current in vivo imaging (e.g. diffusion magnetic resonance imaging). Optical imaging methods such as polarization-sensitive optical coherence tomography (PS-OCT) and polarization microscopy can quantify fiber orientation at micrometer resolution but have been limited to two-dimensional in-plane orientation or thin slices, preventing the comprehensive study of connectivity in 3D. In this work we present a novel method to quantify volumetric 3D orientation in full angular space with PS-OCT. We measure the polarization contrasts of the brain sample from two illumination angles of 0 and 15 degrees and apply a computational method that yields the 3D optic axis orientation and true birefringence. We further present 3D fiber orientation maps of entire coronal cerebrum sections and brainstem with 10 μm in-plane resolution, revealing unprecedented details of fiber configurations. We envision that our method will open a promising avenue towards large-scale 3D fiber axis mapping in the human brain as well as other complex fibrous tissues at microscopic level.

Automatic road network selection method considering functional semantic features of roads with graph convolutional networks

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people’s needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography.

Solutions to enhance the accuracy of UAV’s images for creating extremely large-scale maps in urban area

Abstract Ho Chi Minh City, the largest urban agglomeration in Vietnam, is at the forefront of enabling the government’s efforts and advocating for smart city initiatives in the coming decades. To facilitate this advancement, the implementation of solutions to support the collection, construction, and updating of spatial databases is crucial. These databases serve as the foundational platform for effective urban management practices. Unmanned Aerial Vehicles (UAVs) have witnessed significant growth across various domains, particularly in spatial data collection. However, challenges arise when acquiring and processing UAV images in urban areas. These challenges include orthomosaic distortion in certain regions, insufficient accuracy for creating extremely large-scale maps (e.g., 1:200 or 1:500), and unclear boundaries between adjacent objects. The objective of this paper is to present flight tests conducted at varying altitudes, with different shooting angles, and varying layouts of Ground Control Points (GCPs), both with and without the UAV’s RTK receiver mode. In order to improve the accuracy of UAV’s images, the results suggest that the precision of orthomosaic, Digital Surface Model (DSM) and point clouds in the context of 3D mapping depends on various factors, including: the determination of the optimal flight altitude, optimizing number of GCPs, selecting an appropriate level of image processing, capturing images from varied angles, and using UAVs with RTK or PPK data acquisition modes to mitigate image distortion.

Porosity–permeability characteristics and mineralization–alteration zones of the Maoping germanium-rich lead–zinc deposit in SW China

The Maoping superlarge germanium-rich lead–zinc deposit is a typical nonmagmatic hydrothermal deposit that is structurally controlled in the Sichuan–Yunnan–Guizhou lead–zinc polymetallic metallogenic area. The orebodies are distributed in several formations. This paper is based on large-scale alteration mapping combined with porosity and permeability measurements. We delineated the mineralization–alteration zones of different ore-bearing formations, explored the geological significance of porosity and permeability, and proposed prospecting directions. The research results indicate that during the mineralization period, the ore-forming metal fluids migrated from the deep part of the SSW region to the shallow part of the NNE region along the ore-guiding structure (Maoping Fault). Through the ore distribution structure, depressurization boiling occurred in the open space of the NE-trending interlayered sinistral compressive–torsional faults in several ore-bearing formations, resulting in fluid precipitation and the formation of different brecciated hot-melt dolomite lead–zinc mineralization zones. From the orebody to the wallrock, the C2w Formation and D3zg Formation are divided into four different mineralization–alteration zones. Tectonic activity affects the properties, migration, and precipitation of fluids, thereby controlling the alteration characteristics generated during fluid migration and thus changing the porosity and permeability. The porosity and permeability of strata on the NW flank of the anticline are greater than those of strata on the SE flank. On the NW flank, the greater the degree of mineralization–alteration is, the greater the porosity and permeability are, and the porosity of the orebody is lower than that during dolomitization. Finally, we believe that the NW flank of the anticline is an important area for prospecting. The pyrite + striped altered dolomite zone (Zones II–III) in the C2w limestone and the pyrite + strong dolomite zone (Zones II–III) in the D3zg dolomite are important prospecting indicators.

Spatiotemporal variations and driving factors of farmland soil organic carbon in various landforms of a complex topography

Estimating the spatiotemporal variations and driving factors of farmland soil organic carbon density (SOCD) is of great significance for enhancing soil carbon sequestration capacity. Herein, a large region of complex topography was targeted, which includes hill–mountain, valley–basin, and plain–platform. Based on the massive amounts of sampling data (57,254 measured values) and a large-scale soil map of 1:10,000 (371,976 polygonal patches), the gravity center migration model and gray correlation model were used to quantify the spatiotemporal variations and driving factors of farmland SOCD. The results indicated that the farmland soils in the study area had dual functions of carbon source and sink during 1982–2018, of which 45.50 % and 54.50 % were identified as carbon source and sink, respectively. Specifically, the SOCD for the entire study area, its hill–mountain, and valley–basin increased from 2.79 kg m−2, 2.97 kg m−2, and 3.06 kg m−2 to 2.87 kg m−2, 3.06 kg m−2, and 3.14 kg m−2, respectively, with 0.08 kg m−2 carbon sequestrations and a northeast migration direction for the SOCD gravity center (angle: 21.94°, 23.56°, and 18.82°; distance: 1.56 km, 2.73 km, and 3.20 km). There was a smaller increase of 0.07 kg m−2 in SOCD for the plain–platform from 2.38 kg m−2 (1982) to 2.45 kg m−2 (2018), and the SOCD gravity center migrated to the southwest with an angle of −172.46° and a distance of 1.84 km. Thus, the spatiotemporal variations of farmland SOCD in various landforms varied greatly. Over the past 36 years, SOCD variations were driven by a combination of intrinsic soil factors and external factors such as human disturbance. However, the driving effects of these factors on the landforms of hill–mountain, valley–basin, and plain–platform were quite different in size and order. Therefore, we suggest that topography must be considered when formulating policies to improve soil carbon sequestration, and priority should be given to landform-specific SOCD variation and the factors contributing to them.

Exploring optimal features and image analysis methods for crop type classification from the perspective of crop landscape heterogeneity

Agricultural landscape structure (e.g., the shape of fields, crop diversity, and landscape heterogeneity) greatly influences the selection of methods for large-scale crop mapping using remote sensing data. However, in-depth assessments of its impacts on crop mapping remain infrequent in the existing literature. This study investigated the optimal crop identification features and image analysis methods including pixel- and object-based approaches on crop classification, through the integration of spectral and textural features across various quantitative agricultural landscapes. In the experiments, crop fields were initially delineated into four distinct landscapes using the K-means clustering algorithm based on analyzing 13 selected landscape metrics such as PLAND, LSI and SHDI. Both pixel- and object-based approaches were then employed to conduct crop classification was then conducted using 48 selected features including 9 band reflectance, 23 vegetation indices (VIs), and 16 textures) and two image analysis methods. Specifically, five classification schemes for the different combinations of feature datasets and image analysis methods were explored to assess the impacts of crop heterogeneity on crop classification. Results indicated the five landscape metrics (e.g., SPLIT, SHEI, Average distance, etc.) performed best in assessing crop heterogeneity. In general, spectral bands and VIs had a higher contribution in the compositional heterogeneity, while textural features and VIs played a more important role in the configurational heterogeneity. VIs in the object-based approach and texture features in the pixel-based approach can improved crop classification accuracy in configurational landscapes. The findings provide a theoretical basis on selecting optimal features and image analysis methods for crop classification in complex agricultural landscapes.

Engineering geological and geotechnical evaluation of Sathya Sai Prasanthi Nilayam railway tunnel, Andhra Pradesh, India

Detailed engineering geological investigations were carried out for a railway tunnel which was constructed more than two decades ago. 3D engineering geological mapping was carried out using Brunton Compass and Total Station Surveying instruments in 1:100 scale. Coarse-grained pink and grey granite, hornblende-biotite gneiss and dolerite dyke of Archaean age and Lower Proterozoic age were mapped. Rock mass was intersected by sub-horizontal, inclined, and vertical joint sets, which were continuous and persistent, smooth, and planar with thick filling of decomposed and crushed sheared material or with thin coating of clay material. Based on the Q-system, rock mass was classified into different classes. On the basis of large-scale engineering geological mapping and Norwegian Method of Tunnelling, a support system was recommended which includes rock bolt, fibre reinforced shotcrete, grouting and reinforced ribs of sprayed concrete and the same is implemented by the agency. As per the best knowledge of the authors, reinforced ribs of sprayed concrete are first time used for transportation tunnels in India and it will be more effective if it will be compared with ISMB or Lattice Girder.

Mapping off-road tracks and animal paths in protected areas using high-resolution GeoEye-1 panchromatic satellite imagery

ABSTRACT Off-road driving activities are common in many protected areas. This study aimed at applying a curvelet-based approach for the automatic extraction, mapping and separation of off-road tracks and animal paths in Masai Mara National Reserve, Kenya, using high-resolution GeoEye-1 panchromatic satellite imagery (50 cm). A novel hybrid remote sensing-GIS method comprising three main blocks is proposed: (1) extracting the high-contrast curvilinear feature from curvelet magnitudes derived from the finer scale of curvelet coefficient; (2) extracting the low-contrast curvilinear feature from coarser scale curvelets and refine the shape by deformable active contour (Snake), and (3) categorizing the extracted curvilinear feature into vehicle tracks and animal paths by a fuzzy logic inference system. Results from quantification of extraction and categorization performance of the trails were 77.5% for completeness, 89.2% for correctness, and 4.5% for redundancy, with an overall accuracy of 79.5%. Using grid matching, we find a high correlation between off-road vehicle tracks and animal paths in the area (r = 0.75, p < 0.05) indicating co-occurrence of these two types of trails. The proposed approach provides a basis for large-scale mapping and monitoring of off-road tracks and animal paths in the African savanna from space.

A local encryption method for large-scale vector maps based on spatial hierarchical index and 4D hyperchaotic system

With the development of geographic information services, applications based on map data are increasing. Internet and mobile communication technologies have brought great convenience to the distribution, sharing, and acquisition of map data. Unfortunately, it also brings great challenges to protect the security and privacy of confidential map data. Although several encryption algorithms have been developed for map data, most of the existing methods are simple extensions of classical encryption algorithms for text data in cryptography, ignoring special structures and characteristics of geospatial data. Existing methods mainly take the entire map or layers as encryption units, which makes the encryption efficiency for large-scale map data low and limits the ability to perform local and incremental encryption for local areas, making it still challenging to meet the needs of map data in applications, such as autonomous driving. To solve the limitations, a local encryption approach for large-scale vector map data is proposed in this paper considering the structure characteristics of map data. Experiments on map data of different types (including points, lines, and polygons) demonstrate the effectiveness of the proposed method. With local and parallel encryption strategies, the proposed method has higher efficiency compared to available algorithms for large-scale map data.

A Pathfinding Algorithm for Large-Scale Complex Terrain Environments in the Field

Pathfinding for autonomous vehicles in large-scale complex terrain environments is difficult when aiming to balance efficiency and quality. To solve the problem, this paper proposes Hierarchical Path-Finding A* based on Multi-Scale Rectangle, called RHA*, which achieves efficient pathfinding and high path quality for large-scale unequal-weighted maps. Firstly, the original map grid cells were aggregated into fixed-size clusters. Then, an abstract map was constructed by aggregating equal-weighted clusters into rectangular regions of different sizes and calculating the nodes and edges of the regions in advance. Finally, real-time pathfinding was performed based on the abstract map. The experiment showed that the computation time of real-time pathfinding was reduced by 96.64% compared to A* and 20.38% compared to HPA*. The total cost of the generated path deviated no more than 0.05% compared to A*. The deviation value is reduced by 99.2% compared to HPA*. The generated path can be used for autonomous vehicle traveling in off-road environments.

European beech spring phenological phase prediction with UAV-derived multispectral indices and machine learning regression

Acquiring phenological event data is crucial for studying the impacts of climate change on forest dynamics and assessing the risks associated with the early onset of young leaves. Large-scale mapping of forest phenological timing using Earth observation (EO) data could enhance our understanding of these processes through an added spatial component. However, translating traditional ground-based phenological observations into reliable ground truthing for training and validating EO mapping applications remains challenging. This study explored the feasibility of predicting high-resolution phenological phase data for European beech (Fagus sylvatica) using unoccupied aerial vehicle (UAV)-based multispectral indices and machine learning. Employing a comprehensive feature selection process, we identified the most effective sensors, vegetation indices, training data partitions, and machine learning models for phenological phase prediction. The model that performed best and generalized well across various sites utilized Green Chromatic Coordinate (GCC) and Generalized Additive Model (GAM) boosting. The GCC training data, derived from the radiometrically calibrated visual bands of a multispectral sensor, were predicted using uncalibrated RGB sensor data. The final GCC/GAM boosting model demonstrated capability in predicting phenological phases on unseen datasets within a root mean squared error threshold of 0.5. This research highlights the potential interoperability among common UAV-mounted sensors, particularly the utility of readily available, low-cost RGB sensors. However, considerable limitations were observed with indices that implement the near-infrared band due to oversaturation. Future work will focus on adapting models to better align with the ICP Forests phenological flushing stages.

Large-Scale Land Cover Mapping Framework Based on Prior Product Label Generation: A Case Study of Cambodia

Large-Scale land cover mapping (LLCM) based on deep learning models necessitates a substantial number of high-precision sample datasets. However, the limited availability of such datasets poses challenges in regularly updating land cover products. A commonly referenced method involves utilizing prior products (PPs) as labels to achieve up-to-date land cover mapping. Nonetheless, the accuracy of PPs at the regional level remains uncertain, and the Remote Sensing Image (RSI) corresponding to the product is not publicly accessible. Consequently, the sample dataset constructed through geographic location matching may lack precision. Errors in such datasets are not only due to inherent product discrepancies, and can also arise from temporal and scale disparities between the RSI and PPs. In order to solve the above problems, this paper proposes an LLCM framework for generating labels for use with PPs. The framework consists of three main parts. First, initial generation of labels, in which the collected PPs are integrated based on D-S evidence theory and initial labels are obtained using the generated trust map. Second, for dynamic label correction, a two-stage training method based on initial labels is adopted. The correction model is pretrained in the first stage, then the confidence probability (CP) correction module of the dynamic threshold value and NDVI correction module are introduced in the second stage. The initial labels are iteratively corrected while the model is trained using the joint correction loss, with the corrected labels obtained after training. Finally, the classification model is trained using the corrected labels. Using the proposed land cover mapping framework, this study used PPs to produce a 10 m spatial resolution land cover map of Cambodia in 2020. The overall accuracy of the land cover map was 91.68% and the Kappa value was 0.8808. Based on these results, the proposed mapping framework can effectively use PPs to update medium-resolution large-scale land cover datasets, and provides a powerful solution for label acquisition in LLCM projects.