Tree trunk instance segmentation is crucial for under-canopy unmanned aerial vehicles(UAVs)to autonomously extract standing tree stem attributes.Using cameras as sensors makes these UAVs compact and lightweight,facili...Tree trunk instance segmentation is crucial for under-canopy unmanned aerial vehicles(UAVs)to autonomously extract standing tree stem attributes.Using cameras as sensors makes these UAVs compact and lightweight,facilitating safe and flexible navigation in dense forests.However,their limited onboard computational power makes real-time,image-based tree trunk segmentation challenging,emphasizing the urgent need for lightweight and efficient segmentation models.In this study,we present RT-Trunk,a model specifically designed for real-time tree trunk instance segmentation in complex forest environments.To ensure real-time performance,we selected SparseInst as the base framework.We incorporated ConvNeXt-T as the backbone to enhance feature extraction for tree trunks,thereby improving segmentation accuracy.We further integrate the lightweight convolutional block attention module(CBAM),enabling the model to focus on tree trunk features while suppressing irrelevant information,which leads to additional gains in segmentation accuracy.To enable RT-Trunk to operate effectively under diverse complex forest environments,we constructed a comprehensive dataset for training and testing by combining self-collected data with multiple public datasets covering different locations,seasons,weather conditions,tree species,and levels of forest clutter.Com-pared with the other tree trunk segmentation methods,the RT-Trunk method achieved an average precision of 91.4%and the fastest inference speed of 32.9 frames per second.Overall,the proposed RT-Trunk provides superior trunk segmentation performance that balances speed and accu-racy,making it a promising solution for supporting under-canopy UAVs in the autonomous extraction of standing tree stem attributes.The code for this work is available at https://github.com/NEFU CVRG/RT Trunk.展开更多
In this work, the potential of natural and pretreated palm tree trunk (PTT) as agents for adsorption of an organic dye, 2,6-dichlorophenolindophenol (2,6-DCPIP) from aqueous solutions was probed. Natural and acetic ac...In this work, the potential of natural and pretreated palm tree trunk (PTT) as agents for adsorption of an organic dye, 2,6-dichlorophenolindophenol (2,6-DCPIP) from aqueous solutions was probed. Natural and acetic acid treated PTT were characterized by Fourier transform infrared (FT-IR) spectroscopy and by the point of zero charge (pzc). The biosorption of 2,6-DCPIP was investigated in batch mode using natural and treated PTT. This study was achieved by highlighting several parameters such as the contact time, biosorbents dosage, the initial concentration of 2,6-DCPIP, the pH of the solution, the ionic strength and the interfering ions. The results showed that 2,6-DCPIP was successfully adsorbed from aqueous solutions by natural and treated PTT. The equilibrium was attained after 40 minutes for treated PTT and 20 minutes for natural PTT. The maximum capacity of adsorption was obtained at pH = 2. The adsorption isotherms were investigated and it was found that the experimental data were best described by the Dubinin-Radushkevich isotherm for the natural PTT (R2 = 0.979) and by the Temkin isotherm for the treated PTT (R2 = 0.976). The maximum adsorption capacities determined by Langmuir isotherm were found as 108.932 and 157.233 μmol·g–1 for natural and treated PTT, respectively. The adsorption kinetics was analyzed and was best described by the pseudo-second order model (R2 ≥ 0.998). The diffusion mechanism was studied and the result showed that external mass transfer is the main rate controlling step. The desorption of 2,6-DCPIP is favorable in alkaline medium.展开更多
针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干...针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干,去除非树干目标,提高树干检测精度。首先,设置环形感兴趣区域(Region of interest,ROI),采用地面拟合算法移除地面点云,消除果园目标点云之间的连通性;其次,设置矩形ROI,采用基于密度的带噪声空间聚类(Density-based spatial clustering of applications with noise,DBSCAN)算法对非地面点云进行x Oy平面聚类,根据Li DAR测量分辨率和果园目标参数设置DBSCAN算法超参数,将非地面点云分割为若干目标簇;然后,从全局和局部2个尺度提取目标簇的几何和强度特征,用这些特征描述树干与其他果园目标间的差异;最后,采用训练好的树干检测器融合特征,将目标簇划分为树干与非树干2个类别,输出树干簇。树干检测步骤采用随机森林(Random forest,RF)算法进行离线特征选择与融合,使用树干和非树干训练样本,基于基尼指数(Gini index,GI)改变量评价特征重要性,从初始特征中选择22个鉴别力较强的特征,再融合这些特征生成树干检测器。实验场景为标准化种植核桃园,共采集1317帧点云数据,从中分割12213个目标簇,其中,树冠、杂草、支撑杆、围栏、土坡、农具、行人等非树干目标占比58.04%。按照帧比例1∶4将目标簇随机划分为训练集和测试集,测试集树干检测精确率为99.16%、召回率为99.21%、F1分数为99.19%,树干层级检测平均帧耗时85.25 ms。本文方法能对复杂果园场景快速、精准地检测出树干,满足果园行间导航对树干检测的准确性和实时性要求。展开更多
In this work we determine the physical and mechanical properties of local composites reinforced with papaya trunk fibers (FTP) on one hand and particles of the hulls of the kernels of the garlic (PCNFA) in the other h...In this work we determine the physical and mechanical properties of local composites reinforced with papaya trunk fibers (FTP) on one hand and particles of the hulls of the kernels of the garlic (PCNFA) in the other hand. The samples are produced according to BSI 2782 standards;by combining fibers and untreated to polyester matrix following the contact molding method. We notice that the long fibers of papaya trunks improve the tensile/compression characteristics of composites by 45.44% compared to pure polyester;while the short fibers improve the flexural strength of composites by 62.30% compared to pure polyester. Furthermore, adding fibers decreases the density of the final composite material and the rate of water absorption increases with the size of the fibers. As regards composite materials with particle reinforcement from the cores of the winged fruits, the particle size (fine ≤ 800 μm and large ≤ 1.6 mm) has no influence on the Young’s modulus and on the rate of water absorption. On the other hand, fine particles improve the flexural strength of composite materials by 53.08% compared to pure polyester;fine particles increase the density by 19% compared to the density of pure polyester.展开更多
To determine the age of oil-tea camellia trees, regression equations including Logistic, Mitscherlich, Gompertz, Korf, and Richards were used to calculate accumulative growth rate using basal trunk disc and investigat...To determine the age of oil-tea camellia trees, regression equations including Logistic, Mitscherlich, Gompertz, Korf, and Richards were used to calculate accumulative growth rate using basal trunk disc and investigate the relations between the age of oil-tea camellia trees and their growth rate of secondary trunk. The Gompertz equation Y=71.296 1exp （-3.874 4exp （-0.006 4t）） was the most optimal equation to simulate the accumulative growth rate of basal trunk disc. This equation could be used to estimate the age of oil-tea camellia trees that grow under similar environmental conditions. The Korf equation Y=576.900 1exp （-4.153 0x -0.314 2 ） was the best equation to describe the relation between the age and growth rate of different secondary trunks. With the adjustment coefficient and average growth of different secondary trunk discs, it is possible to predict the age of ancient oil-tea camellia trees that grow under similar environmental conditions. In addition, taking three or more discs from the same diameter group and calculating their average growth rate could lead to more accurate results. For trees that grow in different areas, environmental conditions should be carefully considered when using the above two equations to predict the age of ancient oil-tea camellia trees.展开更多
基金supported in part by the National Natural Science Foundation of China(No.31470714 and 61701105).
文摘Tree trunk instance segmentation is crucial for under-canopy unmanned aerial vehicles(UAVs)to autonomously extract standing tree stem attributes.Using cameras as sensors makes these UAVs compact and lightweight,facilitating safe and flexible navigation in dense forests.However,their limited onboard computational power makes real-time,image-based tree trunk segmentation challenging,emphasizing the urgent need for lightweight and efficient segmentation models.In this study,we present RT-Trunk,a model specifically designed for real-time tree trunk instance segmentation in complex forest environments.To ensure real-time performance,we selected SparseInst as the base framework.We incorporated ConvNeXt-T as the backbone to enhance feature extraction for tree trunks,thereby improving segmentation accuracy.We further integrate the lightweight convolutional block attention module(CBAM),enabling the model to focus on tree trunk features while suppressing irrelevant information,which leads to additional gains in segmentation accuracy.To enable RT-Trunk to operate effectively under diverse complex forest environments,we constructed a comprehensive dataset for training and testing by combining self-collected data with multiple public datasets covering different locations,seasons,weather conditions,tree species,and levels of forest clutter.Com-pared with the other tree trunk segmentation methods,the RT-Trunk method achieved an average precision of 91.4%and the fastest inference speed of 32.9 frames per second.Overall,the proposed RT-Trunk provides superior trunk segmentation performance that balances speed and accu-racy,making it a promising solution for supporting under-canopy UAVs in the autonomous extraction of standing tree stem attributes.The code for this work is available at https://github.com/NEFU CVRG/RT Trunk.
文摘In this work, the potential of natural and pretreated palm tree trunk (PTT) as agents for adsorption of an organic dye, 2,6-dichlorophenolindophenol (2,6-DCPIP) from aqueous solutions was probed. Natural and acetic acid treated PTT were characterized by Fourier transform infrared (FT-IR) spectroscopy and by the point of zero charge (pzc). The biosorption of 2,6-DCPIP was investigated in batch mode using natural and treated PTT. This study was achieved by highlighting several parameters such as the contact time, biosorbents dosage, the initial concentration of 2,6-DCPIP, the pH of the solution, the ionic strength and the interfering ions. The results showed that 2,6-DCPIP was successfully adsorbed from aqueous solutions by natural and treated PTT. The equilibrium was attained after 40 minutes for treated PTT and 20 minutes for natural PTT. The maximum capacity of adsorption was obtained at pH = 2. The adsorption isotherms were investigated and it was found that the experimental data were best described by the Dubinin-Radushkevich isotherm for the natural PTT (R2 = 0.979) and by the Temkin isotherm for the treated PTT (R2 = 0.976). The maximum adsorption capacities determined by Langmuir isotherm were found as 108.932 and 157.233 μmol·g–1 for natural and treated PTT, respectively. The adsorption kinetics was analyzed and was best described by the pseudo-second order model (R2 ≥ 0.998). The diffusion mechanism was studied and the result showed that external mass transfer is the main rate controlling step. The desorption of 2,6-DCPIP is favorable in alkaline medium.
文摘针对复杂果园环境行间导航树干检测问题,提出一种基于多线激光雷达(Light detection and ranging,Li DAR)的主干形果树树干层级检测方法,使用16线VLP-16型LiDAR采集车辆周围的果园点云数据,通过目标分割和树干检测2个步骤层次化检测树干,去除非树干目标,提高树干检测精度。首先,设置环形感兴趣区域(Region of interest,ROI),采用地面拟合算法移除地面点云,消除果园目标点云之间的连通性;其次,设置矩形ROI,采用基于密度的带噪声空间聚类(Density-based spatial clustering of applications with noise,DBSCAN)算法对非地面点云进行x Oy平面聚类,根据Li DAR测量分辨率和果园目标参数设置DBSCAN算法超参数,将非地面点云分割为若干目标簇;然后,从全局和局部2个尺度提取目标簇的几何和强度特征,用这些特征描述树干与其他果园目标间的差异;最后,采用训练好的树干检测器融合特征,将目标簇划分为树干与非树干2个类别,输出树干簇。树干检测步骤采用随机森林(Random forest,RF)算法进行离线特征选择与融合,使用树干和非树干训练样本,基于基尼指数(Gini index,GI)改变量评价特征重要性,从初始特征中选择22个鉴别力较强的特征,再融合这些特征生成树干检测器。实验场景为标准化种植核桃园,共采集1317帧点云数据,从中分割12213个目标簇,其中,树冠、杂草、支撑杆、围栏、土坡、农具、行人等非树干目标占比58.04%。按照帧比例1∶4将目标簇随机划分为训练集和测试集,测试集树干检测精确率为99.16%、召回率为99.21%、F1分数为99.19%,树干层级检测平均帧耗时85.25 ms。本文方法能对复杂果园场景快速、精准地检测出树干,满足果园行间导航对树干检测的准确性和实时性要求。
文摘In this work we determine the physical and mechanical properties of local composites reinforced with papaya trunk fibers (FTP) on one hand and particles of the hulls of the kernels of the garlic (PCNFA) in the other hand. The samples are produced according to BSI 2782 standards;by combining fibers and untreated to polyester matrix following the contact molding method. We notice that the long fibers of papaya trunks improve the tensile/compression characteristics of composites by 45.44% compared to pure polyester;while the short fibers improve the flexural strength of composites by 62.30% compared to pure polyester. Furthermore, adding fibers decreases the density of the final composite material and the rate of water absorption increases with the size of the fibers. As regards composite materials with particle reinforcement from the cores of the winged fruits, the particle size (fine ≤ 800 μm and large ≤ 1.6 mm) has no influence on the Young’s modulus and on the rate of water absorption. On the other hand, fine particles improve the flexural strength of composite materials by 53.08% compared to pure polyester;fine particles increase the density by 19% compared to the density of pure polyester.
基金Supported by Hunan Forestry Science and Technology Project(XLK201707)
文摘To determine the age of oil-tea camellia trees, regression equations including Logistic, Mitscherlich, Gompertz, Korf, and Richards were used to calculate accumulative growth rate using basal trunk disc and investigate the relations between the age of oil-tea camellia trees and their growth rate of secondary trunk. The Gompertz equation Y=71.296 1exp （-3.874 4exp （-0.006 4t）） was the most optimal equation to simulate the accumulative growth rate of basal trunk disc. This equation could be used to estimate the age of oil-tea camellia trees that grow under similar environmental conditions. The Korf equation Y=576.900 1exp （-4.153 0x -0.314 2 ） was the best equation to describe the relation between the age and growth rate of different secondary trunks. With the adjustment coefficient and average growth of different secondary trunk discs, it is possible to predict the age of ancient oil-tea camellia trees that grow under similar environmental conditions. In addition, taking three or more discs from the same diameter group and calculating their average growth rate could lead to more accurate results. For trees that grow in different areas, environmental conditions should be carefully considered when using the above two equations to predict the age of ancient oil-tea camellia trees.
