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
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
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
This paper proposes an improved method to segment tree image based on color and texture feature and amends the segmented result by mathematical morphology. The crown and trunk of one tree have been successfully segmen...This paper proposes an improved method to segment tree image based on color and texture feature and amends the segmented result by mathematical morphology. The crown and trunk of one tree have been successfully segmented and the experimental result is deemed effective. The authors conclude that building a standard data base for a range of species, featuring color and texture is a necessary condition and constitutes the essential groundwork for tree image segmentation in order to insure its quality.展开更多
航空激光测距技术的发展推动了森林资源调查的技术革新。利用机载激光雷达(Light Detection and Ranging,LiDAR)数据能够精确测量森林结构。结合地面调查样本,LiDAR数据可在大范围内实现高分辨率的森林资源评估。文章以东北地区中8个样...航空激光测距技术的发展推动了森林资源调查的技术革新。利用机载激光雷达(Light Detection and Ranging,LiDAR)数据能够精确测量森林结构。结合地面调查样本,LiDAR数据可在大范围内实现高分辨率的森林资源评估。文章以东北地区中8个样地作为研究对象,使用机载激光雷达点云数据实现对样地内单木林业信息的检核与更新。首先,基于剖面旋转算法,实现样地区域的单木分割。考虑到林业参数与树种的相关性,建立树种与分割树冠几何形态之间的对应关系,实现基于LiDAR数据的树种识别。在已知树种类别的基础上,提取样地内单木树高、冠幅、胸径、地上生物量和蓄积量等森林参数,实现林业参数的检核与更新。实验结果显示,树冠分割F 1分数超过95%,树种识别准确率超过90%,树高、东西冠幅、南北冠幅、胸径、地上生物量及蓄积量的决定系数R^(2)分别为89.3%、75.7%、69.4%、84.0%、89.6%和89.1%。结果表明:激光雷达调查方法实用性强且可以广泛应用于大范围林业精确调查中。展开更多
针对森林资源精准监测的需求,探索背包激光雷达(Light Detection and Ranging,LiDAR)在生产实践中的森林结构参数提取能力,以浙江建德林场为研究区,基于野外调查采集的8块样地背包LiDAR数据,提出一种改进的K-means分层聚类算法进行单木...针对森林资源精准监测的需求,探索背包激光雷达(Light Detection and Ranging,LiDAR)在生产实践中的森林结构参数提取能力,以浙江建德林场为研究区,基于野外调查采集的8块样地背包LiDAR数据,提出一种改进的K-means分层聚类算法进行单木分割,从分割后的单木点云中分别提取胸径、树高、冠幅、树冠投影面积、树冠体积、间隙率等6个单木结构参数,并计算56个点云分层高度特征,利用随机森林方法,构建单木材积估测模型并估测样地蓄积量。结果表明:改进的K-means分层聚类算法综合分割精度F的平均值为0.87,胸径的提取精度为91.26%,树高的提取精度为85.77%;仅用6个单木结构参数作为输入特征变量的单木材积估测模型,模型拟合结果的决定系数(R^(2))为0.89,均方根误差(RMSE)为0.053 m^(3);采用Person相关系数和随机森林特征重要性筛选单木结构参数和分层高度特征后,得到最终的单木材积估测模型,模型拟合结果的R^(2)为0.93,RMSE为0.041 m^(3);利用最优估测模型估算每个样地的蓄积量,平均精度为94.20%。研究结果表明,提出的改进的K-means分层聚类算法能够有效分割单木点云,随机森林方法可以较好地估测单木材积和样地蓄积量,为背包激光雷达在森林资源参数提取方面提供重要的参考价值。展开更多
单木分割在森林结构分析、林木参数提取以及森林生物量反演中具有重要作用。激光雷达(Light Detection and Ranging,LiDAR)作为一种低成本、高效率的数据源,为森林单木分割研究提供了坚实的数据基础。目前的单木分割研究主要集中在结构...单木分割在森林结构分析、林木参数提取以及森林生物量反演中具有重要作用。激光雷达(Light Detection and Ranging,LiDAR)作为一种低成本、高效率的数据源,为森林单木分割研究提供了坚实的数据基础。目前的单木分割研究主要集中在结构较为简单的森林区域,通常通过考虑点云之间的空间关系,制定合适的判别准则来实现单木的分割。然而,针对结构复杂的森林,现有的单木分割算法研究相对较少。提出了一种融合核密度估计、数字表面模型和K-means聚类等方法的单木分割算法。研究结果表明:以甘肃省甘南藏族自治区为研究区,对西北云杉林进行单木分割时,该方法能够显著提高人工云杉林与天然云杉林的分割精度。与传统的K-means聚类单木分割算法相比,该方法的整体棵数查全率分别提高了32%和15%,查准率分别提高了51%和27%,分别达到了83%和89%的查全率,以及92%和55%的查准率。这一方法为机载LiDAR在森林生态应用中的进一步应用提供了新的技术支持,特别为复杂林型结构中的单木分割问题提供了一种高效、简便的解决方案。展开更多
红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区...红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区茅尾海红树林保护区为研究区,利用无人机载和手持式LiDAR获取的点云数据,提出了一种红树冠层下部约束聚类分割方法,对木榄、红海榄、桐花树等不同类型红树的单木分割以及树高、冠幅的进行提取,并与传统单木分割算法进行了对比和分析。结果表明:本文提出的结合空地LiDAR数据的单木分割算法,在不同类型红树单木分割中均取得了较高的单木检出率,与传统的冠层高度模型分割法相比较,单木检出率提升了13.4%—26.7%。其次,有效提高了红树树高的提取精度。3种红树树高参数提取值与实测值之间的R2提高了1.8%—42.2%,RMSE降低了3.4%—55.3%。此外,由于红树冠幅分割结果存在提取值偏小的规律,本研究将能够表征红树冠层交叠密集程度的点云密度变量作为修正因子,经修正后的RMSE降低了45.25%—53.33%。因此,本文提出的联合空地LiDAR的红树林单木生长参数提取方法,可以实现精确的红树单木点云分割并有效提升红树生长参数提取精度,为红树林生物量估算及碳汇能力评估提供了技术和数据支撑。展开更多
随着森林资源管理逐步迈向精准化与数字化,无人机技术为智能化与自动化的森林资源样地调查提供了一种解决方案。然而,当前树冠分割边界刻画不够精细、单木材积估测精度较低的问题仍然突出,同时高精度激光雷达数据的获取成本较高,限制了...随着森林资源管理逐步迈向精准化与数字化,无人机技术为智能化与自动化的森林资源样地调查提供了一种解决方案。然而,当前树冠分割边界刻画不够精细、单木材积估测精度较低的问题仍然突出,同时高精度激光雷达数据的获取成本较高,限制了其在实际应用中的广泛推广。为提高单木材积估测的精度与效率,克服现有方法中树冠分割不精细和高精度激光雷达数据成本高的问题,该研究提出了一种基于树冠精准分割和多源特征融合的无人机单木估测方法。在此方法中,基于YOLOv11算法,结合引入ScaleEdgeExtractor(SEE)、DilatedFusion(DF)、C2BRA和GatedFPN等模块,增强了树冠边界的感知能力和多尺度特征表达能力,并构建了高精度树冠分割网络CrownSeg。在此基础上,基于树冠形态、光谱及纹理特征的多维特征融合策略,结合递进特征组合方法和加权集成学习模型构建了单木材积估测模型。结果表明,CrownSeg树冠分割算法提升了树冠边界的刻画精度,交并比(intersection over union,IoU)阈值为0.5时的平均精度(AP50)达到94.9%,较基准模型提升1.5个百分点;IoU阈值从0.5到0.95区间的平均精度(AP50-95)达到66.2%,较基准模型提升3.8个百分点。此外,多源特征融合有效强化了单木材积的预测能力,最终加权集成模型表现优异,其决定系数(R^(2))达到0.921 5,平均绝对误差(MAE)为0.0228 m^(3),平均绝对百分比误差(MAPE)为17.00%,均优于单一模型,展现出良好的模型稳定性和泛化能力,可为无人机遥感技术在精准林业中的应用提供技术参考。展开更多
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 (Grant No. 30271079) and Graduate Cultivation Foundation of Beijing Forestry University
文摘This paper proposes an improved method to segment tree image based on color and texture feature and amends the segmented result by mathematical morphology. The crown and trunk of one tree have been successfully segmented and the experimental result is deemed effective. The authors conclude that building a standard data base for a range of species, featuring color and texture is a necessary condition and constitutes the essential groundwork for tree image segmentation in order to insure its quality.
文摘航空激光测距技术的发展推动了森林资源调查的技术革新。利用机载激光雷达(Light Detection and Ranging,LiDAR)数据能够精确测量森林结构。结合地面调查样本,LiDAR数据可在大范围内实现高分辨率的森林资源评估。文章以东北地区中8个样地作为研究对象,使用机载激光雷达点云数据实现对样地内单木林业信息的检核与更新。首先,基于剖面旋转算法,实现样地区域的单木分割。考虑到林业参数与树种的相关性,建立树种与分割树冠几何形态之间的对应关系,实现基于LiDAR数据的树种识别。在已知树种类别的基础上,提取样地内单木树高、冠幅、胸径、地上生物量和蓄积量等森林参数,实现林业参数的检核与更新。实验结果显示,树冠分割F 1分数超过95%,树种识别准确率超过90%,树高、东西冠幅、南北冠幅、胸径、地上生物量及蓄积量的决定系数R^(2)分别为89.3%、75.7%、69.4%、84.0%、89.6%和89.1%。结果表明:激光雷达调查方法实用性强且可以广泛应用于大范围林业精确调查中。
文摘单木分割在森林结构分析、林木参数提取以及森林生物量反演中具有重要作用。激光雷达(Light Detection and Ranging,LiDAR)作为一种低成本、高效率的数据源,为森林单木分割研究提供了坚实的数据基础。目前的单木分割研究主要集中在结构较为简单的森林区域,通常通过考虑点云之间的空间关系,制定合适的判别准则来实现单木的分割。然而,针对结构复杂的森林,现有的单木分割算法研究相对较少。提出了一种融合核密度估计、数字表面模型和K-means聚类等方法的单木分割算法。研究结果表明:以甘肃省甘南藏族自治区为研究区,对西北云杉林进行单木分割时,该方法能够显著提高人工云杉林与天然云杉林的分割精度。与传统的K-means聚类单木分割算法相比,该方法的整体棵数查全率分别提高了32%和15%,查准率分别提高了51%和27%,分别达到了83%和89%的查全率,以及92%和55%的查准率。这一方法为机载LiDAR在森林生态应用中的进一步应用提供了新的技术支持,特别为复杂林型结构中的单木分割问题提供了一种高效、简便的解决方案。
文摘红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区茅尾海红树林保护区为研究区,利用无人机载和手持式LiDAR获取的点云数据,提出了一种红树冠层下部约束聚类分割方法,对木榄、红海榄、桐花树等不同类型红树的单木分割以及树高、冠幅的进行提取,并与传统单木分割算法进行了对比和分析。结果表明:本文提出的结合空地LiDAR数据的单木分割算法,在不同类型红树单木分割中均取得了较高的单木检出率,与传统的冠层高度模型分割法相比较,单木检出率提升了13.4%—26.7%。其次,有效提高了红树树高的提取精度。3种红树树高参数提取值与实测值之间的R2提高了1.8%—42.2%,RMSE降低了3.4%—55.3%。此外,由于红树冠幅分割结果存在提取值偏小的规律,本研究将能够表征红树冠层交叠密集程度的点云密度变量作为修正因子,经修正后的RMSE降低了45.25%—53.33%。因此,本文提出的联合空地LiDAR的红树林单木生长参数提取方法,可以实现精确的红树单木点云分割并有效提升红树生长参数提取精度,为红树林生物量估算及碳汇能力评估提供了技术和数据支撑。
文摘随着森林资源管理逐步迈向精准化与数字化,无人机技术为智能化与自动化的森林资源样地调查提供了一种解决方案。然而,当前树冠分割边界刻画不够精细、单木材积估测精度较低的问题仍然突出,同时高精度激光雷达数据的获取成本较高,限制了其在实际应用中的广泛推广。为提高单木材积估测的精度与效率,克服现有方法中树冠分割不精细和高精度激光雷达数据成本高的问题,该研究提出了一种基于树冠精准分割和多源特征融合的无人机单木估测方法。在此方法中,基于YOLOv11算法,结合引入ScaleEdgeExtractor(SEE)、DilatedFusion(DF)、C2BRA和GatedFPN等模块,增强了树冠边界的感知能力和多尺度特征表达能力,并构建了高精度树冠分割网络CrownSeg。在此基础上,基于树冠形态、光谱及纹理特征的多维特征融合策略,结合递进特征组合方法和加权集成学习模型构建了单木材积估测模型。结果表明,CrownSeg树冠分割算法提升了树冠边界的刻画精度,交并比(intersection over union,IoU)阈值为0.5时的平均精度(AP50)达到94.9%,较基准模型提升1.5个百分点;IoU阈值从0.5到0.95区间的平均精度(AP50-95)达到66.2%,较基准模型提升3.8个百分点。此外,多源特征融合有效强化了单木材积的预测能力,最终加权集成模型表现优异,其决定系数(R^(2))达到0.921 5,平均绝对误差(MAE)为0.0228 m^(3),平均绝对百分比误差(MAPE)为17.00%,均优于单一模型,展现出良好的模型稳定性和泛化能力,可为无人机遥感技术在精准林业中的应用提供技术参考。
