Search Results (44)

As an important input parameter of the ecological network, the accuracy and detail with which forest cover is extracted directly constrain the accuracy of forest ecological network construction. The development of medium- and high-resolution remote sensing technology has provided an opportunity to obtain accurate and high-resolution forest coverage data. As forests have diverse contours and complex scenes on remote sensing images, a model of them will be disturbed by the natural distribution characteristics of complex forests, which in turn will affect the extraction accuracy. In this study, we first constructed a rather large, complex, diverse, and scene-rich forest extraction dataset based on Sentinel-2 multispectral images, comprising 20,962 labeled images with a spatial resolution of 10 m, in a manually and accurately labeled manner. At the same time, this paper proposes the Dynamic Large Kernel Segformer and conducts forest extraction experiments in Liaoning Province, China. We then used forest coverage as an input parameter and classified the forest landscape patterns in the study area using a landscape spatial pattern characterization method, based on which a forest ecological network was constructed. The results show that the Dynamic Large Kernel Segformer obtains 80.58% IoU, 89.29% precision, 88.63% recall, and a 88.96% F1 Score in extraction accuracy, which is 4.02% higher than that of the Segformer network, and achieves large-scale forest extraction in the study area. The forest area in Liaoning Province increased during the 5-year period from 2019 to 2023. With respect to the overall spatial pattern change, the Core area of Liaoning Province saw an increase in 2019–2023, and the overall quality of the forest landscape improved. Finally, we constructed the forest ecological network for Liaoning Province in 2023, which consists of ecological sources, ecological nodes, and ecological corridors based on circuit theory. This method can be used to extract large areas of forest based on remote sensing images, which is helpful for constructing forest ecological networks and achieving coordinated regional, ecological, and economic development. Full article

The escalating impacts and occurrence of wildfires threaten the public, economies, and global ecosystems. Physiologically declining or dead trees are a great portion of the fires because these trees are prone to higher ignition and have lower moisture content. To prevent wildfires, hazardous vegetation needs to be removed, and the vegetation should be identified early on. This work proposes a real-time fire risk tree detection framework using UAV images, which is based on lightweight object detection. The model uses the MobileNetV3-Small spine, which is optimized for edge deployment, combined with an SSD head. This configuration results in a highly optimized and fast UAV-based inference pipeline. The dataset used in this study comprises over 3000 annotated RGB UAV images of trees in healthy, partially dead, and fully dead conditions, collected from mixed real-world forest scenes and public drone imagery repositories. Thorough evaluation shows that the proposed model outperforms conventional SSD and recent YOLOs on Precision (94.1%), Recall (93.7%), mAP (90.7%), F1 (91.0%) while being light-weight (8.7 MB) and fast (62.5 FPS on Jetson Xavier NX). These findings strongly support the model’s effectiveness for large-scale continuous forest monitoring to detect health degradations and mitigate wildfire risks proactively. The framework UAV-based environmental monitoring systems differentiates itself by incorporating a balance between detection accuracy, speed, and resource efficiency as fundamental principles. Full article

Efficient and accurate acquisition of tree distribution and three-dimensional geometric information in forest scenes, along with three-dimensional reconstructions of entire forest environments, hold significant application value in precision forestry and forestry digital twins. However, due to complex vegetation structures, fine geometric details, and severe occlusions in forest environments, existing methods—whether vision-based or LiDAR-based—still face challenges such as high data acquisition costs, feature extraction difficulties, and limited reconstruction accuracy. This study focuses on reconstructing tree distribution and extracting key individual tree parameters, and it proposes a forest 3D reconstruction framework based on high-resolution remote sensing images. Firstly, an optimized Mask R-CNN model was employed to segment individual tree crowns and extract distribution information. Then, a Tree Parameter and Reconstruction Network (TPRN) was constructed to directly estimate key structural parameters (height, DBH etc.) from crown images and generate tree 3D models. Subsequently, the 3D forest scene could be reconstructed by combining the distribution information and tree 3D models. In addition, to address the data scarcity, a hybrid training strategy integrating virtual and real data was proposed for crown segmentation and individual tree parameter estimation. Experimental results demonstrated that the proposed method could reconstruct an entire forest scene within seconds while accurately preserving tree distribution and individual tree attributes. In two real-world plots, the tree counting accuracy exceeded 90%, with an average tree localization error under 0.2 m. The TPRN achieved parameter extraction accuracies of 92.7% and 96% for tree height, and 95.4% and 94.1% for DBH. Furthermore, the generated individual tree models achieved average Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores of 11.24 and 0.53, respectively, validating the quality of the reconstruction. This approach enables fast and effective large-scale forest scene reconstruction using only a single remote sensing image as input, demonstrating significant potential for applications in both dynamic forest resource monitoring and forestry-oriented digital twin systems. Full article

The pre-training and fine-tuning paradigm has significantly advanced satellite remote sensing applications. However, its potential remains largely underexplored for airborne laser scanning (ALS), a key technology in domains such as forest management and urban planning. In this study, we address this gap by constructing a large-scale ALS point cloud dataset and evaluating its effectiveness in downstream applications. We first propose a simple, generalizable framework for dataset construction, designed to maximize land cover and terrain diversity while allowing flexible control over dataset size. We instantiate this framework using ALS, land cover, and terrain data collected across the contiguous United States, resulting in a dataset geographically covering 17,000 + ${\mathrm{km}}^2$ (184 billion points) with diverse land cover and terrain types included. As a baseline self-supervised learning model, we adopt BEV-MAE, a state-of-the-art masked autoencoder for 3D outdoor point clouds, and pre-train it on the constructed dataset. The resulting models are fine-tuned for several downstream tasks, including tree species classification, terrain scene recognition, and point cloud semantic segmentation. Our results show that pre-trained models consistently outperform their counterparts trained from scratch across all downstream tasks, demonstrating the strong transferability of the learned representations. Additionally, we find that scaling the dataset using the proposed framework leads to consistent performance improvements, whereas datasets constructed via random sampling fail to achieve comparable gains. Full article

Forest anomalies (e.g., pests, deforestation, and fires) are increasingly frequent phenomena on Earth’s surface. Rapid detection of these anomalies is crucial for sustainable forest management and development. On-orbit remote sensing detection of multi-type forest anomalies using single-temporal images is one of the most promising methods for achieving it. Nevertheless, existing forest anomaly detection methods rely on time series image analysis or are designed to detect a single type of forest anomaly. In this study, a Forest Anomaly Comprehensive Index (FACI) is proposed to detect multi-type forest anomalies using single-temporal Sentinel-2 images. First, the spectral characteristics of different forest anomaly events were analyzed to obtain potential band combinations. Then, the formulation of FACI was determined using imagery simulated by the LargE-Scale remote sensing data and image Simulation framework over heterogeneous 3D scenes (LESS) model. The thresholds for FACI for different anomalies were determined using the interquartile method and 90 in situ survey samples. The accuracy of FACI was quantitatively assessed using an additional 90 in situ survey samples. Evaluation results indicated that the overall accuracy of FACI in detecting the three forest anomalies was 88.3%, with a Kappa coefficient of 0.84. The overall accuracy of existing indices (NDVI, NDWI, SAVI, BSI, and TAI) is below 80%, with Kappa coefficients less than 0.7. In the end, a case study in Ji’an, Jiangxi Province, confirmed the ability of FACI to detect different stages of pest infection, as well as deforestation and forest fires, using single-temporal satellite images. The FACI provides a promising method for the on-orbit satellite detection of multi-type forest anomalies in the future. Full article

As large-scale and intensive fattening pig farming has become mainstream, the increase in farm size has led to more severe issues related to the hierarchy within pig groups. Due to genetic differences among individual fattening pigs, those that grow faster enjoy a higher social rank. Larger pigs with greater aggression continuously acquire more resources, further restricting the survival space of weaker pigs. Therefore, fattening pigs must be grouped rationally, and the management of weaker pigs must be enhanced. This study, considering current fattening pig farming needs and actual production environments, designed and implemented an intelligent sorting system based on weight estimation. The main hardware structure of the partitioning equipment includes a collection channel, partitioning channel, and gantry-style collection equipment. Experimental data were collected, and the original scene point cloud was preprocessed to extract the back point cloud of fattening pigs. Based on the morphological characteristics of the fattening pigs, the back point cloud segmentation method was used to automatically extract key features such as hip width, hip height, shoulder width, shoulder height, and body length. The segmentation algorithm first calculates the centroid of the point cloud and the eigenvectors of the covariance matrix to reconstruct the point cloud coordinate system. Then, based on the variation characteristics and geometric shape of the consecutive horizontal slices of the point cloud, hip width and shoulder width slices are extracted, and the related features are calculated. Weight estimation was performed using Random Forest, Multilayer perceptron (MLP), linear regression based on the least squares method, and ridge regression models, with parameter tuning using Bayesian optimization. The mean squared error, mean absolute error, and mean relative error were used as evaluation metrics to assess the model’s performance. Finally, the classification capability was evaluated using the median and average weights of the fattening pigs as partitioning standards. The experimental results show that the system’s average relative error in weight estimation is approximately 2.90%, and the total time for the partitioning process is less than 15 s, which meets the needs of practical production. Full article

Individual tree data could offer potential uses for both forestry and landscape visualization but has not yet been realized on a large scale. Relying on 5 points/m² Finnish national laser scanning, we present the design and implementation of a system for producing, storing, distributing, querying, and viewing individual tree data, both in a web browser and in a game engine-mediated interactive 3D visualization, “virtual forest”. In our experiment, 3896 km² of airborne laser scanning point clouds were processed for individual tree detection, resulting in over 100 million trees detected, but the developed technical infrastructure allows for containing 10+ billion trees (a rough number of log-sized trees in Finland) to be visualized in the same system. About 92% of trees wider than 20 cm in diameter at breast height (corresponding to industrial log-size trees) were detected using national laser scanning data. Obtained relative RMSE for height, diameter, volume, and biomass (stored above-ground carbon) at individual tree levels were 4.5%, 16.9%, 30.2%, and 29.0%, respectively. The obtained RMSE and bias are low enough for operational forestry and add value over current area-based inventories. By combining the single-tree data with open GIS datasets, a 3D virtual forest was produced automatically. A comparison against georeferenced panoramic images was performed to assess the verisimilitude of the virtual scenes, with the best results obtained from sparse grown forests on sites with clear landmarks. Both the online viewer and 3D virtual forest can be used for improved decision-making in multifunctional forestry. Based on the work, individual tree inventory is expected to become operational in Finland in 2026 as part of the third national laser scanning program. Full article

The utilization of radiative transfer models for interpreting remotely sensed data to evaluate forest disturbances is a cost-effective approach. However, the current radiative transfer modeling approaches are either too abstract (e.g., 1D models) or too complex (detailed 3D models). This study introduces a novel multilayer heterogeneous 3D radiative transfer framework with medium complexity, termed MART3D, for characterizing forest disturbances. MART3D generates 3D canopy structures accounting for the within-crown clumping by clustering leaves, which is modeled as a turbid medium, around branches, applicable for forests of medium complexity, such as temperate forests. It then automatically generates a multilayer forest with grass, shrub and several layers of trees using statistical parameters, such as the leaf area index and fraction of canopy cover. By employing the ray-tracing module within the well-established LargE-Scale remote sensing data and image Simulation model (LESS) as the computation backend, MART3D achieves a high accuracy (RMSE = 0.0022 and 0.018 for red and Near-Infrared bands) in terms of the bidirectional reflectance factor (BRF) over two RAMI forest scenes, even though the individual structures of MART3D are generated solely from statistical parameters. Furthermore, we demonstrated the versatility and user-friendliness of MART3D by evaluating the band selection strategy for computing the normalized burn ratio (NBR) to assess the composite burn index over a forest fire scene. The proposed MART3D is a flexible and easy-to-use tool for studying the remote sensing response under varying vegetation conditions. Full article

Background. With the advancement of “digital forestry” and “intelligent forestry”, point cloud data have emerged as a powerful tool for accurately capturing three-dimensional forest scenes. It enables the creation and presentation of digital forest systems, facilitates the monitoring of dynamic changes such as forest growth and logging processes, and facilitates the evaluation of forest resource fluctuations. However, forestry point cloud data are characterized by its large volume and the need for time-consuming and labor-intensive manual processing. Deep learning, with its exceptional learning capabilities, holds tremendous potential for processing forestry environment point cloud data. This potential is attributed to the availability of accurately annotated forestry point cloud data and the development of deep learning models specifically designed for forestry applications. Nonetheless, in practical scenarios, conventional direct annotation methods prove to be inefficient and time-consuming due to the complex terrain, dense foliage occlusion, and uneven sparsity of forestry point clouds. Furthermore, directly applying deep learning frameworks to forestry point clouds results in subpar accuracy and performance due to the large size, occlusion, sparsity, and unstructured nature of these scenes. Therefore, the proposal of accurately annotated forestry point cloud datasets and the establishment of semantic segmentation methods tailored for forestry environments hold paramount importance. Methods. A point cloud data annotation method based on single-tree positioning to enhance annotation efficiency was proposed and challenges such as occlusions and sparse distribution in forestry environments were addressed. This method facilitated the construction of a forestry point cloud semantic segmentation dataset, consisting of 1259 scenes and 214.4 billion points, encompassing four distinct categories. The pointDMM framework was introduced, a semantic segmentation framework specifically designed for forestry point clouds. The proposed method first integrates tree features using the DMM module and constructs key segmentation graphs utilizing energy segmentation functions. Subsequently, the cutpursuit algorithm is employed to solve the graph and achieve the pre-segmentation of semantics. The locally extracted forestry point cloud features from the pre-segmentation are comprehensively inputted into the network. Feature fusion is performed using the MLP method of multi-layer features, and ultimately, the point cloud is segmented using the lightweight PointNet. Result. Remarkable segmentation results are demonstrated on the DMM dataset, achieving an accuracy rate of 93% on a large-scale forest environment point cloud dataset known as DMM-3. Compared to other algorithms, the proposed method improves the accuracy of standing tree recognition by 21%. This method exhibits significant advantages in extracting feature information from artificially planted forest point clouds obtained from TLS. It establishes a solid foundation for the automation, intelligence, and informatization of forestry, thereby possessing substantial scientific significance. Full article

Background: The development of laser measurement techniques is of great significance in forestry monitoring and park management in smart cities. It provides many conveniences for improving landscape planning efficiency and strengthening digital construction. However, capturing 3D point clouds in large-scale landscape environments is a complex task that generates massive amounts of unstructured data with characteristics such as randomness, rotational invariance, sparsity, and serious barriers. Methods: To improve the processing efficiency of intelligent devices for massive point clouds, we propose a novel deep learning neural network based on a multi-feature aggregation strategy. This network is designed to divide 3D laser point clouds in complex large-scale scenarios. Firstly, we utilize multiple terrestrial laser sensors to collect a large amount of data in open scenes such as parks, streets, and forests in urban environments. These data are integrated into a practical database called DMSdataset, which contains different information variables, densities, and dimensions. Then, an automatic block integrated with a multi-feature extractor is constructed to pre-process the unstructured point cloud data and standardize the datasets. Finally, a novel semantic segmentation framework called PointDMS is designed using 3D convolutional deep networks. PointDMS achieves a better segmentation performance of point clouds with a lightweight parameter structure. Here, “D” stands for deep network, “M” stands for multi-feature, and “S” stands for segmentation. Results: Extensive experiments on self-built datasets show that the proposed PointDMS achieves similar or better performance in point cloud segmentation compared to other methods. The overall identification accuracy of the proposed model is up to 93.5%, which is a 14% increase. Particularly for living wood objects, the average identification accuracy is up to 88.7%, which is, at least, an 8.2% increase. These results effectively prove that PointDMS is beneficial for 3D point cloud processing, division, and mining applications in urban forest environments. It demonstrates good robustness and generalization. Full article

Accurate individual tree detection by unmanned aerial vehicles (UAVs) is a critical technique for smart forest management and serves as the foundation for evaluating ecological functions. Existing object detection and segmentation methods, on the other hand, have reduced accuracy when detecting and segmenting individual trees in complicated urban forest landscapes, as well as poor mask segmentation quality. This study proposes a novel Mask-CSP-attention-coupled network (MCAN) based on the Mask R-CNN algorithm. MCAN uses the Cross Stage Partial Net (CSPNet) framework with the Sigmoid Linear Unit (SiLU) activation function in the backbone network to form a new Cross Stage Partial Residual Net (CSPResNet) and employs a convolutional block attention module (CBAM) mechanism to the feature pyramid network (FPN) for feature fusion and multiscale segmentation to further improve the feature extraction ability of the model, enhance its detail information detection ability, and improve its individual tree detection accuracy. In this study, aerial photography of the study area was conducted by UAVs, and the acquired images were used to produce a dataset for training and validation. The method was compared with the Mask Region-based Convolutional Neural Network (Mask R-CNN), Faster Region-based Convolutional Neural Network (Faster R-CNN), and You Only Look Once v5 (YOLOv5) on the test set. In addition, four scenes—namely, a dense forest distribution, building forest intersection, street trees, and active plaza vegetation—were set up, and the improved segmentation network was used to perform individual tree segmentation on these scenes to test the large-scale segmentation ability of the model. MCAN’s average precision (AP) value for individual tree identification is 92.40%, which is 3.7%, 3.84%, and 12.53% better than that of Mask R-CNN, Faster R-CNN, and YOLOv5, respectively. In comparison to Mask R-CNN, the segmentation AP value is 97.70%, an increase of 8.9%. The segmentation network’s precision for the four scenes in multi-scene segmentation ranges from 95.55% to 92.33%, showing that the proposed network performs high-precision segmentation in many contexts. Full article

Modeling large-scale scenarios of diversity in real forests is a hot topic in forestry research. At present, there is a common problem of simple and poor model scalability in large-scale forest scenes. Forest growth is often carried out using a holistic scaling approach, which does not reflect the diversity of trees in nature. To solve this problem, we propose a method for constructing large-scale forest scenes based on forest hierarchical models, which can improve the dynamic visual effect of large-scale forest landscape polymorphism. In this study, we constructed tree hierarchical models of corresponding sizes using the detail attribute data of 29 subplots in the Shanxia Experimental Forest Farm in Jiangxi Province. The growth values of trees of different ages were calculated according to the hierarchical growth model of trees, and the growth dynamic simulation of large-scale forest scenes constructed by the integrated model and hierarchical model was carried out using three-dimensional visualization technology. The results indicated that the runtime frame rate of the scene constructed by the hierarchical model was 30.63 fps and the frame rate after growth was 29.68 fps, which met the operational requirements. Compared with the traditional integrated model, the fluctuation value of the frame rate of the hierarchical model was 0.036 less than that of the integrated model, and the scene ran stably. The positive feedback rate of personnel evaluation reached 95%. In this study, the main conclusion is that our proposed method achieves polymorphism in large-scale forest scene construction and ensures the stability of large-scale scene operation. Full article

Existing 3D city reconstruction via oblique photography can only produce surface models, lacking semantic information about the urban environment and the ability to incorporate all individual buildings. Here, we propose a method for the semantic segmentation of 3D model data from oblique photography and for building monomer construction and implementation. Mesh data were converted into and mapped as point sets clustered to form superpoint sets via rough geometric segmentation, facilitating subsequent feature extractions. In the local neighborhood computation of semantic segmentation, a neighborhood search method based on geodesic distances, improved the rationality of the neighborhood. In addition, feature information was retained via the superpoint sets. Considering the practical requirements of large-scale 3D datasets, this study offers a robust and efficient segmentation method that combines traditional random forest and Markov random field models to segment 3D scene semantics. To address the need for modeling individual and unique buildings, our methodology utilized 3D mesh data of buildings as a data source for specific contour extraction. Model monomer construction and building contour extractions were based on mesh model slices and assessments of geometric similarity, which allowed the simultaneous and automatic achievement of these two processes. Full article

The technology of remote sensing-assisted tree species classification is increasingly developing, but the rapid refinement of tree species classification on a large scale is still challenging. As one of the treasures of ecological resources in China, Arxan has 80% forest cover, and tree species classification surveys guarantee ecological environment management and sustainable development. In this study, we identified tree species in three samples within the Arxan Duraer Forestry Zone based on the spectral, textural, and topographic features of unmanned aerial vehicle (UAV) multispectral remote sensing imagery and light detection and ranging (LiDAR) point cloud data as classification variables to distinguish among birch, larch, and nonforest areas. The best extracted classification variables were combined to compare the accuracy of the random forest (RF), support vector machine (SVM), and classification and regression tree (CART) methodologies for classifying species into three sample strips in the Arxan Duraer Forestry Zone. Furthermore, the effect on the overall classification results of adding a canopy height model (CHM) was investigated based on spectral and texture feature classification combined with field measurement data to improve the accuracy. The results showed that the overall accuracy of the RF was 79%, and the kappa coefficient was 0.63. After adding the CHM extracted from the point cloud data, the overall accuracy was improved by 7%, and the kappa coefficient increased to 0.75. The overall accuracy of the CART model was 78%, and the kappa coefficient was 0.63; the overall accuracy of the SVM was 81%, and the kappa coefficient was 0.67; and the overall accuracy of the RF was 86%, and the kappa coefficient was 0.75. To verify whether the above results can be applied to a large area, Google Earth Engine was used to write code to extract the features required for classification from Sentinel-2 multispectral and radar topographic data (create equivalent conditions), and six tree species and one nonforest in the study area were classified using RF, with an overall accuracy of 0.98, and a kappa coefficient of 0.97. In this paper, we mainly integrate active and passive remote sensing data for forest surveying and add vertical data to a two-dimensional image to form a three-dimensional scene. The main goal of the research is not only to find schemes to improve the accuracy of tree species classification, but also to apply the results to large-scale areas. This is necessary to improve the time-consuming and labor-intensive traditional forest survey methods and to ensure the accuracy and reliability of survey data. Full article

Operational weather satellites, dating back to 1970s, currently provide the best basis for climatological investigations, such as an analysis of changes in the cloud cover. Because clouds are highly dynamic in time, temporally high-resolution data from the geostationary orbit are preferred in order to take variations in the diurnal cycles into account. For such studies, a consistent dataset in space and time is mandatory, but not yet available. Ground-based point measurements of various cloud parameters, such as ceiling, visibility, and cloud type are often sparsely spread and inconsistent, making it difficult to derive reliable spatio-temporal information over large areas. The Meteosat program has generally provided suitable data from over Europe since 1977, but different spatial, spectral, and radiometric resolution of the instruments of the individual satellites, including early-years calibration uncertainties, makes harmonization necessary to finally derive a time series applicable to any kind of climatological study. In this study, a machine learning-based approach has been employed to generate a long-term consistent dataset with high spatio-temporal resolution and extensive coverage over Europe by the harmonization of Meteosat First Generation (MFG) and Meteosat Second Generation (MSG) satellite datasets (1991–2020). A random forest (RF) regressor is trained on the overlap period (2004–2006), where datasets of both satellite generation (MFG and MSG) are available to predict MFG Water Vapour (WV) and Infrared (IR) channels brightness temperature (BT) values based on MSG channels. The aim of the study is to synthesize MFG MVIRI data from MSG SEVIRI to generate a consistent MFG time series. The results indicate a good match of MFG synthesized data with the original MFG data with a mean absolute error of 0.7 K for the WV model and 1.6 K for the IR model, and an out-of-bag (OOB) R² score of 0.98 for both the models. Based on the trained models, the MFG scenes are synthesized from the MSG scenes for the years from 2006 to 2020. The long-term homogeneity of the generated time series is analyzed. The harmonized dataset will be applied to generate a continuous time series on fog and low stratus (FLS) occurrence for a climatological time scale of 30 years. Full article