Digital aerial photograph(DAP)data is processed based on Structure from Motion(Sf M)algorithm and regional net adjustment method to generate digital surface discrete point clouds similar to Light Detection and Ranging...Digital aerial photograph(DAP)data is processed based on Structure from Motion(Sf M)algorithm and regional net adjustment method to generate digital surface discrete point clouds similar to Light Detection and Ranging(LiDAR)and digital orthophoto mosaic(DOM)similar to optical remote sensing image.In this study,we obtained highresolution images of mature forests of Chinese fir by unmanned aerial vehicle(UAV)flying through crossroute flight,and then reconstructed the threedimensional point clouds in the UAV aerial area by SfM technique.The point cloud segmentation(PCS)algorithm was used for the individual tree segmentation,and the F-score of the three sample plots were 0.91,0.94,and 0.94,respectively.Individual tree biomass modeling was conducted using 155 mature Chinese fir forests which were correctly segmented.The relative root mean squared error(rRMSE)values of random forest(RF),bagged tree(BT)and support vector regression(SVR)were 34.48%,35.74%and 40.93%,respectively.Our study demonstrated that DAP point clouds had great potential to extract forest vertical parameters and could be applied successfully in individual tree segmentation and individual tree biomass modeling.展开更多
Terrestrial laser scanning(TLS)accurately captures tree structural information and provides prerequisites for treescale estimations of forest biophysical attributes.Quantifying tree-scale attributes from TLS point clo...Terrestrial laser scanning(TLS)accurately captures tree structural information and provides prerequisites for treescale estimations of forest biophysical attributes.Quantifying tree-scale attributes from TLS point clouds requires segmentation,yet the occlusion effects severely affect the accuracy of automated individual tree segmentation.In this study,we proposed a novel method using ellipsoid directional searching and point compensation algorithms to alleviate occlusion effects.Firstly,region growing and point compensation algorithms are used to determine the location of tree roots.Secondly,the neighbor points are extracted within an ellipsoid neighborhood to mitigate occlusion effects compared with k-nearest neighbor(KNN).Thirdly,neighbor points are uniformly subsampled by the directional searching algorithm based on the Fibonacci principle in multiple spatial directions to reduce memory consumption.Finally,a graph describing connectivity between a point and its neighbors is constructed,and it is utilized to complete individual tree segmentation based on the shortest path algorithm.The proposed method was evaluated on a public TLS dataset comprising six forest plots with three complexity categories in Evo,Finland,and it reached the highest mean accuracy of 77.5%,higher than previous studies on tree detection.We also extracted and validated the tree structure attributes using manual segmentation reference values.The RMSE,RMSE%,bias,and bias%of tree height,crown base height,crown projection area,crown surface area,and crown volume were used to evaluate the segmentation accuracy,respectively.Overall,the proposed method avoids many inherent limitations of current methods and can accurately map canopy structures in occluded complex forest stands.展开更多
As an important tropical cash crop,rubber trees play a key role in the rubber industry and ecosystem.However,a significant challenge in precision agriculture and refined management of rubber plantation lies in the lim...As an important tropical cash crop,rubber trees play a key role in the rubber industry and ecosystem.However,a significant challenge in precision agriculture and refined management of rubber plantation lies in the limitations of traditional point cloud segmentation methods,which struggle to accurately extract structural parameters and capture the spatial layout of individual rubber trees.Therefore,we propose an optimized dual-channel clustering method for the UAV LiDAR-based Rubber Tree Point Cloud Segmentation Network(RsegNet)for improved assessment of rubber tree architecture and traits.Firstly,we designed a cosine feature extraction network,termed CosineU-Net,to address the branch-and-leaf overlap problem by calculating the cosine similarity of the spatial and positional features of each point,leveraging deep learning approaches to improve feature representation.Secondly,we constructed a dual-channel clustering module reducing prediction error in rubber tree point cloud data,integrating multi-class association and background classification to tackle background interference.The cluster identification and separation accuracy in high-dimensional data processing is enhanced through a dy-namic clustering optimization algorithm.In our self-built dataset and across five regions of the FOR-instance forest dataset,RsegNet achieved the best performance compared to five state-of-the-art networks,reaching an F-score of 86.1%.This method calculated structural attributes including height,crown diameter,and volume for rubber trees in three areas under different environments in Danzhou City,Hainan Province,providing robust support for precise monitoring,plantation management,and health assessment.展开更多
The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)...The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)point cloud data.We proposed the Nyström-based spectral clustering(NSC)algorithm to decrease the computational burden.This novel NSC method showed accurate and rapid in individual tree segmentation using point cloud data.The K-nearest neighbour-based sampling(KNNS)was proposed for the Nyström approximation of voxels to improve the efficiency.The NSC algorithm showed good performance for 32 plots in China and Europe.The overall matching rate and extraction rate of proposed algorithm reached 69%and 103%.For all trees located by Global Navigation Satellite System(GNSS)calibrated tape-measures,the tree height regression of the matching results showed an value of 0.88 and a relative root mean square error(RMSE)of 5.97%.For all trees located by GNSS calibrated total-station measures,the values were 0.89 and 4.49%.The method also showed good performance in a benchmark dataset with an improvement of 7%for the average matching rate.The results demonstrate that the proposed NSC algorithm provides an accurate individual tree segmentation and parameter estimation using airborne LiDAR point cloud data.展开更多
Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating t...Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating the adoption of advanced,automated approaches for improved forest conservation and management.This study explores the application of deep learning-based object detection techniques for individual tree detection in RGB satellite imagery.A dataset of 3157 images was collected and divided into training(2528),validation(495),and testing(134)sets.To enhance model robustness and generalization,data augmentation was applied to the training part of the dataset.Various YOLO-based models,including YOLOv8,YOLOv9,YOLOv10,YOLOv11,and YOLOv12,were evaluated using different hyperparameters and optimization techniques,such as stochastic gradient descent(SGD)and auto-optimization.These models were assessed in terms of detection accuracy and the number of detected trees.The highest-performing model,YOLOv12m,achieved a mean average precision(mAP@50)of 0.908,mAP@50:95 of 0.581,recall of 0.851,precision of 0.852,and an F1-score of 0.847.The results demonstrate that YOLO-based object detection offers a highly efficient,scalable,and accurate solution for individual tree detection in satellite imagery,facilitating improved forest inventory,monitoring,and ecosystem management.This study underscores the potential of AI-driven tree detection to enhance environmental sustainability and support data-driven decision-making in forestry.展开更多
Rubber products have become an important strategic resource in the global economy.However,individual rubber tree segmentation in plantation environments remains challenging due to canopy background interfer-ence and s...Rubber products have become an important strategic resource in the global economy.However,individual rubber tree segmentation in plantation environments remains challenging due to canopy background interfer-ence and significant morphological variations among trees.To address these issues,we propose a high-precision segmentation network,TM-WSNet(Spatial Geometry Enhanced Hybrid Feature Extraction Module-Wavelet Grid Feature Fusion Encoder Segmentation Network).First,we introduce SGTramba,a hybrid feature extraction module combining Grouped Transformer and Mamba architectures,designed to reduce confusion between tree crown boundaries and surrounding vegetation or background elements.Second,we propose the WGMS encoder,which enhances structural feature recognition by applying wavelet-based spatial grid downsampling and mul-tiscale feature fusion,effectively handling variations in canopy shape and tree height.Third,a scale optimization algorithm(SCPO)is developed to adaptively search for the optimal learning rate,addressing uneven learning across different resolution scales.We evaluate TM-WSNet on a self-constructed dataset(RubberTree)and two public datasets(ShapeNetPart and ForestSemantic),where it consistently achieves high segmentation accuracy and robustness.In practical field tests,our method accurately predicts key rubber tree parameters—height,crown width,and diameter at breast height with coefficients of determination(R^(2))of 1.00,0.99,and 0.89,respectively.These results demonstrate TM-WSNet's strong potential for supporting precision rubber yield estimation and health monitoring in complex plantation environments.展开更多
We address the 1-line minimum Steiner tree of line segments(1L-MStT-LS)problem.Specifically,given a set S of n disjoint line segments in R^(2),we are asked to find the location of a line l and a set E_(l) of necessary...We address the 1-line minimum Steiner tree of line segments(1L-MStT-LS)problem.Specifically,given a set S of n disjoint line segments in R^(2),we are asked to find the location of a line l and a set E_(l) of necessary line segments(i.e.,edges)such that a graph consisting of all line segments in S ∪ E_(l) plus this line l,denoted by T_(l)=(S,l,E_(l)),becomes a Steiner tree,the objective is to minimize total length of edges in E_(l) among all such Steiner trees.Similarly,we are asked to find a set E_(0) of necessary edges such that a graph consisting of all line segments in S ∪ E_(0),denoted by T_(S)=(S,E_(0)),becomes a Steiner tree,the objective is to minimize total length of edges in E_(0) among all such Steiner trees,we refer to this new problem as the minimum Steiner tree of line segments(MStT-LS)problem.In addition,when two endpoints of each edge in Eo need to be located on two different line segments in S,respectively,we refer to that problem as the minimum spanning tree of line segments(MST-LS)problem.We obtain three main results:(1)Using technique of Voronoi diagram of line segments,we design an exact algorithm in time O(n log n)to solve the MST-LS problem;(2)we show that the algorithm designed in(1)is a 1.214-approximation algorithm to solve the MStT-LS problem;(3)using the combination of the algorithm designed in(1)as a subroutine for many times,a technique of finding linear facility location and a key lemma proved by techniques of computational geometry,we present a 1.214-approximation algorithm in time O(n^(3) log n)to solve the 1L-MStT-LS problem.展开更多
This paper proposes a semi-greedy framework for optimizing multi-joinqueries in shared-nothing systems. The plan generated by the framework com-prises several pipelines, each performing several joins. The framework de...This paper proposes a semi-greedy framework for optimizing multi-joinqueries in shared-nothing systems. The plan generated by the framework com-prises several pipelines, each performing several joins. The framework deter-mines the 'optimal' number of joins to be performed in each pipeline. Thedecisions are made based on the cost estimation of the entire processing plan.Two ekisting optimization algorithms are extended under the framework. Ananalytical model is presented and used to compare the quality of plans producedby each optimization algorithm. Our study shows that the new algorithms out-perform their counterparts that are not extended.展开更多
基金grants from the National Natural Science Foundation of China(No.31870620)the Fundamental Research Funds for the Central Universities(No.PTYX202107)the National Technology Extension Fund of Forestry([2019]06)。
文摘Digital aerial photograph(DAP)data is processed based on Structure from Motion(Sf M)algorithm and regional net adjustment method to generate digital surface discrete point clouds similar to Light Detection and Ranging(LiDAR)and digital orthophoto mosaic(DOM)similar to optical remote sensing image.In this study,we obtained highresolution images of mature forests of Chinese fir by unmanned aerial vehicle(UAV)flying through crossroute flight,and then reconstructed the threedimensional point clouds in the UAV aerial area by SfM technique.The point cloud segmentation(PCS)algorithm was used for the individual tree segmentation,and the F-score of the three sample plots were 0.91,0.94,and 0.94,respectively.Individual tree biomass modeling was conducted using 155 mature Chinese fir forests which were correctly segmented.The relative root mean squared error(rRMSE)values of random forest(RF),bagged tree(BT)and support vector regression(SVR)were 34.48%,35.74%and 40.93%,respectively.Our study demonstrated that DAP point clouds had great potential to extract forest vertical parameters and could be applied successfully in individual tree segmentation and individual tree biomass modeling.
基金supported by the National Natural Science Foundation of China(Nos.32171789,32211530031,12411530088)the National Key Research and Development Program of China(No.2023YFF1303901)+2 种基金the Joint Open Funded Project of State Key Laboratory of Geo-Information Engineering and Key Laboratory of the Ministry of Natural Resources for Surveying and Mapping Science and Geo-spatial Information Technology(2022-02-02)Background Resources Survey in Shennongjia National Park(SNJNP2022001)the Open Project Fund of Hubei Provincial Key Laboratory for Conservation Biology of Shennongjia Snub-nosed Monkeys(SNJGKL2022001).
文摘Terrestrial laser scanning(TLS)accurately captures tree structural information and provides prerequisites for treescale estimations of forest biophysical attributes.Quantifying tree-scale attributes from TLS point clouds requires segmentation,yet the occlusion effects severely affect the accuracy of automated individual tree segmentation.In this study,we proposed a novel method using ellipsoid directional searching and point compensation algorithms to alleviate occlusion effects.Firstly,region growing and point compensation algorithms are used to determine the location of tree roots.Secondly,the neighbor points are extracted within an ellipsoid neighborhood to mitigate occlusion effects compared with k-nearest neighbor(KNN).Thirdly,neighbor points are uniformly subsampled by the directional searching algorithm based on the Fibonacci principle in multiple spatial directions to reduce memory consumption.Finally,a graph describing connectivity between a point and its neighbors is constructed,and it is utilized to complete individual tree segmentation based on the shortest path algorithm.The proposed method was evaluated on a public TLS dataset comprising six forest plots with three complexity categories in Evo,Finland,and it reached the highest mean accuracy of 77.5%,higher than previous studies on tree detection.We also extracted and validated the tree structure attributes using manual segmentation reference values.The RMSE,RMSE%,bias,and bias%of tree height,crown base height,crown projection area,crown surface area,and crown volume were used to evaluate the segmentation accuracy,respectively.Overall,the proposed method avoids many inherent limitations of current methods and can accurately map canopy structures in occluded complex forest stands.
基金This work was supported by the Hainan Province Science and Technology Special Fund(Grant No.ZDYF2025XDNY113)the Central Public-interest Scientific Institution Basal Research Fund(Grant No.1630032022007)+2 种基金the Special Fund for Hainan Excellent Team"Rubber Genetics and Breeding"(Grant No.20210203)the Hunan Provincial Natural Science Foundation Project(Grant No.2025JJ50385)in part by the National Natural Science Foundation of China(Grant No.62276276).
文摘As an important tropical cash crop,rubber trees play a key role in the rubber industry and ecosystem.However,a significant challenge in precision agriculture and refined management of rubber plantation lies in the limitations of traditional point cloud segmentation methods,which struggle to accurately extract structural parameters and capture the spatial layout of individual rubber trees.Therefore,we propose an optimized dual-channel clustering method for the UAV LiDAR-based Rubber Tree Point Cloud Segmentation Network(RsegNet)for improved assessment of rubber tree architecture and traits.Firstly,we designed a cosine feature extraction network,termed CosineU-Net,to address the branch-and-leaf overlap problem by calculating the cosine similarity of the spatial and positional features of each point,leveraging deep learning approaches to improve feature representation.Secondly,we constructed a dual-channel clustering module reducing prediction error in rubber tree point cloud data,integrating multi-class association and background classification to tackle background interference.The cluster identification and separation accuracy in high-dimensional data processing is enhanced through a dy-namic clustering optimization algorithm.In our self-built dataset and across five regions of the FOR-instance forest dataset,RsegNet achieved the best performance compared to five state-of-the-art networks,reaching an F-score of 86.1%.This method calculated structural attributes including height,crown diameter,and volume for rubber trees in three areas under different environments in Danzhou City,Hainan Province,providing robust support for precise monitoring,plantation management,and health assessment.
文摘The spectral clustering method has notable advantages in segmentation.But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging(LiDAR)point cloud data.We proposed the Nyström-based spectral clustering(NSC)algorithm to decrease the computational burden.This novel NSC method showed accurate and rapid in individual tree segmentation using point cloud data.The K-nearest neighbour-based sampling(KNNS)was proposed for the Nyström approximation of voxels to improve the efficiency.The NSC algorithm showed good performance for 32 plots in China and Europe.The overall matching rate and extraction rate of proposed algorithm reached 69%and 103%.For all trees located by Global Navigation Satellite System(GNSS)calibrated tape-measures,the tree height regression of the matching results showed an value of 0.88 and a relative root mean square error(RMSE)of 5.97%.For all trees located by GNSS calibrated total-station measures,the values were 0.89 and 4.49%.The method also showed good performance in a benchmark dataset with an improvement of 7%for the average matching rate.The results demonstrate that the proposed NSC algorithm provides an accurate individual tree segmentation and parameter estimation using airborne LiDAR point cloud data.
基金funding from Horizon Europe Framework Programme(HORIZON),call Teaming for Excellence(HORIZON-WIDERA-2022-ACCESS-01-two-stage)-Creation of the centre of excellence in smart forestry“Forest 4.0”No.101059985funded by the EuropeanUnion under the project FOREST 4.0-“Ekscelencijos centras tvariai miško bioekonomikai vystyti”No.10-042-P-0002.
文摘Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating the adoption of advanced,automated approaches for improved forest conservation and management.This study explores the application of deep learning-based object detection techniques for individual tree detection in RGB satellite imagery.A dataset of 3157 images was collected and divided into training(2528),validation(495),and testing(134)sets.To enhance model robustness and generalization,data augmentation was applied to the training part of the dataset.Various YOLO-based models,including YOLOv8,YOLOv9,YOLOv10,YOLOv11,and YOLOv12,were evaluated using different hyperparameters and optimization techniques,such as stochastic gradient descent(SGD)and auto-optimization.These models were assessed in terms of detection accuracy and the number of detected trees.The highest-performing model,YOLOv12m,achieved a mean average precision(mAP@50)of 0.908,mAP@50:95 of 0.581,recall of 0.851,precision of 0.852,and an F1-score of 0.847.The results demonstrate that YOLO-based object detection offers a highly efficient,scalable,and accurate solution for individual tree detection in satellite imagery,facilitating improved forest inventory,monitoring,and ecosystem management.This study underscores the potential of AI-driven tree detection to enhance environmental sustainability and support data-driven decision-making in forestry.
基金This work was supported by the Hainan Province Science and Technology Special Fund(Grant No.ZDYF2025XDNY113)the Central Public-interest Scientific Institution Basal Research Fund(Grant No.1630032022007)+2 种基金the Special Fund for Hainan Excellent Team“Rubber Genetics and Breeding”(Grant No.20210203)the Hunan Provincial Natural Science Foundation Project(Grant No.2025JJ50385)in part by the National Natural Science Foundation of China(Grant No.62276276).
文摘Rubber products have become an important strategic resource in the global economy.However,individual rubber tree segmentation in plantation environments remains challenging due to canopy background interfer-ence and significant morphological variations among trees.To address these issues,we propose a high-precision segmentation network,TM-WSNet(Spatial Geometry Enhanced Hybrid Feature Extraction Module-Wavelet Grid Feature Fusion Encoder Segmentation Network).First,we introduce SGTramba,a hybrid feature extraction module combining Grouped Transformer and Mamba architectures,designed to reduce confusion between tree crown boundaries and surrounding vegetation or background elements.Second,we propose the WGMS encoder,which enhances structural feature recognition by applying wavelet-based spatial grid downsampling and mul-tiscale feature fusion,effectively handling variations in canopy shape and tree height.Third,a scale optimization algorithm(SCPO)is developed to adaptively search for the optimal learning rate,addressing uneven learning across different resolution scales.We evaluate TM-WSNet on a self-constructed dataset(RubberTree)and two public datasets(ShapeNetPart and ForestSemantic),where it consistently achieves high segmentation accuracy and robustness.In practical field tests,our method accurately predicts key rubber tree parameters—height,crown width,and diameter at breast height with coefficients of determination(R^(2))of 1.00,0.99,and 0.89,respectively.These results demonstrate TM-WSNet's strong potential for supporting precision rubber yield estimation and health monitoring in complex plantation environments.
基金supported by the National Natural Science Foundation of China(Nos.11861075 and 12101593)Project for Innovation Team(Cultivation)of Yunnan Province(No.202005AE160006)+2 种基金Key Project of Yunnan Provincial Science and Technology Department and Yunnan University(No.2018FY001014)Program for Innovative Research Team(in Science and Technology)in Universities of Yunnan Province(No.C176240111009)Jian-Ping Li is also supported by Project of Yunling Scholars Training of Yunnan Province.Su-Ding Liu is also supported by the Graduate Research and Innovation Project of Yunnan University(No.2020Z66).
文摘We address the 1-line minimum Steiner tree of line segments(1L-MStT-LS)problem.Specifically,given a set S of n disjoint line segments in R^(2),we are asked to find the location of a line l and a set E_(l) of necessary line segments(i.e.,edges)such that a graph consisting of all line segments in S ∪ E_(l) plus this line l,denoted by T_(l)=(S,l,E_(l)),becomes a Steiner tree,the objective is to minimize total length of edges in E_(l) among all such Steiner trees.Similarly,we are asked to find a set E_(0) of necessary edges such that a graph consisting of all line segments in S ∪ E_(0),denoted by T_(S)=(S,E_(0)),becomes a Steiner tree,the objective is to minimize total length of edges in E_(0) among all such Steiner trees,we refer to this new problem as the minimum Steiner tree of line segments(MStT-LS)problem.In addition,when two endpoints of each edge in Eo need to be located on two different line segments in S,respectively,we refer to that problem as the minimum spanning tree of line segments(MST-LS)problem.We obtain three main results:(1)Using technique of Voronoi diagram of line segments,we design an exact algorithm in time O(n log n)to solve the MST-LS problem;(2)we show that the algorithm designed in(1)is a 1.214-approximation algorithm to solve the MStT-LS problem;(3)using the combination of the algorithm designed in(1)as a subroutine for many times,a technique of finding linear facility location and a key lemma proved by techniques of computational geometry,we present a 1.214-approximation algorithm in time O(n^(3) log n)to solve the 1L-MStT-LS problem.
文摘This paper proposes a semi-greedy framework for optimizing multi-joinqueries in shared-nothing systems. The plan generated by the framework com-prises several pipelines, each performing several joins. The framework deter-mines the 'optimal' number of joins to be performed in each pipeline. Thedecisions are made based on the cost estimation of the entire processing plan.Two ekisting optimization algorithms are extended under the framework. Ananalytical model is presented and used to compare the quality of plans producedby each optimization algorithm. Our study shows that the new algorithms out-perform their counterparts that are not extended.
