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
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
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
Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect i...Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect images, we used convex optimization(CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity(SSIM) results between original image and defect image were calculated to evaluate the performance of segmentation with different convex optimization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree(CART) classifier. The average accuracy of the classifier is 94.1% with four types of defects on Xylosma congestum wood plate surface: pinhole, crack,live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adaptability and high classification accuracy.展开更多
Small storage space for photographs in formal documents is increasingly necessary in today＇s needs for huge amounts of data communication and storage. Traditional compression algorithms do not sufficiently utilize th...Small storage space for photographs in formal documents is increasingly necessary in today＇s needs for huge amounts of data communication and storage. Traditional compression algorithms do not sufficiently utilize the distinctness of formal photographs. That is, the object is an image of the human head, and the background is in unicolor. Therefore, the compression is of low efficiency and the image after compression is still space-consuming. This paper presents an image compression algorithm based on object segmentation for practical high-efficiency applications. To achieve high coding efficiency, shape-adaptive discrete wavelet transforms are used to transformation arbitrarily shaped objects. The areas of the human head and its background are compressed separately to reduce the coding redundancy of the background. Two methods, lossless image contour coding based on differential chain, and modified set partitioning in hierarchical trees （SPIHT） algorithm of arbitrary shape, are discussed in detail. The results of experiments show that when bit per pixel （bpp）is equal to 0.078, peak signal-to-noise ratio （PSNR） of reconstructed photograph will exceed the standard of SPIHT by nearly 4dB.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
Attribute reduction is an important process in rough set theory.Finding minimum attribute reduction has been proven to help the user-oriented make better knowledge discovery in some cases.In this paper,an efficient mi...Attribute reduction is an important process in rough set theory.Finding minimum attribute reduction has been proven to help the user-oriented make better knowledge discovery in some cases.In this paper,an efficient minimum attribute reduction algorithm is proposed based on the multilevel evolutionary tree with self-adaptive subpopulations.A model of multilevel evolutionary tree with self-adaptive subpopulations is constructed,and interacting attribute sets are better decomposed into subsets by the self-adaptive mechanism of elitist populations.Moreover it can self-adapt the subpopulation sizes according to the historical performance record so that interacting attribute decision variables are captured into the same grouped subpopulation,which will be extended to better performance in both quality of solution and competitive computation complexity for minimum attribute reduction.The conducted experiments show the proposed algorithm is better on both efficiency and accuracy of minimum attribute reduction than some representative algorithms.Finally the proposed algorithm is applied to magnetic resonance image(MRI)segmentation,and its stronger applicability is further demonstrated by the effective and robust segmentation results.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
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.
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supported by the Fund of Forestry 948project(2015-4-52)the Fundamental Research Funds for the Central Universities(2572017DB05)the Natural Science Foundation of Heilongjiang Province(C2017005)
文摘Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect images, we used convex optimization(CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity(SSIM) results between original image and defect image were calculated to evaluate the performance of segmentation with different convex optimization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree(CART) classifier. The average accuracy of the classifier is 94.1% with four types of defects on Xylosma congestum wood plate surface: pinhole, crack,live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adaptability and high classification accuracy.
基金This work was supported by National Natural Science Foundation of China (No.60372066)
文摘Small storage space for photographs in formal documents is increasingly necessary in today＇s needs for huge amounts of data communication and storage. Traditional compression algorithms do not sufficiently utilize the distinctness of formal photographs. That is, the object is an image of the human head, and the background is in unicolor. Therefore, the compression is of low efficiency and the image after compression is still space-consuming. This paper presents an image compression algorithm based on object segmentation for practical high-efficiency applications. To achieve high coding efficiency, shape-adaptive discrete wavelet transforms are used to transformation arbitrarily shaped objects. The areas of the human head and its background are compressed separately to reduce the coding redundancy of the background. Two methods, lossless image contour coding based on differential chain, and modified set partitioning in hierarchical trees （SPIHT） algorithm of arbitrary shape, are discussed in detail. The results of experiments show that when bit per pixel （bpp）is equal to 0.078, peak signal-to-noise ratio （PSNR） of reconstructed photograph will exceed the standard of SPIHT by nearly 4dB.
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。
基金Supported by the National Natural Science Foundation of China(61139002,61171132)the Natural Science Foundation of Jiangsu Education Department(12KJB520013)+2 种基金the Fundamental Research Funds for the Central Universitiesthe Funding of Jiangsu Innovation Program for Graduate Education(CXZZ110219)the Open Project Program of State Key Lab for Novel Software Technology in Nanjing University(KFKT2012B28)
文摘Attribute reduction is an important process in rough set theory.Finding minimum attribute reduction has been proven to help the user-oriented make better knowledge discovery in some cases.In this paper,an efficient minimum attribute reduction algorithm is proposed based on the multilevel evolutionary tree with self-adaptive subpopulations.A model of multilevel evolutionary tree with self-adaptive subpopulations is constructed,and interacting attribute sets are better decomposed into subsets by the self-adaptive mechanism of elitist populations.Moreover it can self-adapt the subpopulation sizes according to the historical performance record so that interacting attribute decision variables are captured into the same grouped subpopulation,which will be extended to better performance in both quality of solution and competitive computation complexity for minimum attribute reduction.The conducted experiments show the proposed algorithm is better on both efficiency and accuracy of minimum attribute reduction than some representative algorithms.Finally the proposed algorithm is applied to magnetic resonance image(MRI)segmentation,and its stronger applicability is further demonstrated by the effective and robust segmentation results.
