Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Automatic acquisition of the canopy volume parameters of the Citrus reticulate Blanco cv. Shatangju tree is of great significance to precision management of the orchard. This research combined the point cloud deep learning algorithm with the volume calculation algorithm to segment the canopy of the Citrus reticulate Blanco cv. Shatangju trees. The 3D (Three-Dimensional) point cloud model of a Citrus reticulate Blanco cv. Shatangju orchard was generated using UAV tilt photogrammetry images. The segmentation effects of three deep learning models, PointNet++, MinkowskiNet and FPConv, on Shatangju trees and the ground were compared. The following three volume algorithms: convex hull by slices, voxel-based method and 3D convex hull were applied to calculate the volume of Shatangju trees. Model accuracy was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The results show that the overall accuracy of the MinkowskiNet model (94.57%) is higher than the other two models, which indicates the best segmentation effect. The 3D convex hull algorithm received the highest R2 (0.8215) and the lowest RMSE (0.3186 m3) for the canopy volume calculation, which best reflects the real volume of Citrus reticulate Blanco cv. Shatangju trees. The proposed method is capable of rapid and automatic acquisition for the canopy volume of Citrus reticulate Blanco cv. Shatangju trees.

[1]  Liang Cheng,et al.  A Concave Hull Methodology for Calculating the Crown Volume of Individual Trees Based on Vehicle-Borne LiDAR Data , 2019, Remote. Sens..

[2]  Adrianna Barbasiewicz,et al.  The analysis of the accuracy of spatial models using photogrammetric software: Agisoft Photoscan and Pix4D , 2018 .

[3]  S. Gülci The determination of some stand parameters using SfM-based spatial 3D point cloud in forestry studies: an analysis of data production in pure coniferous young forest stands , 2019, Environmental Monitoring and Assessment.

[4]  Washington Yotto Ochieng,et al.  A New Faulty GNSS Measurement Detection and Exclusion Algorithm for Urban Vehicle Positioning , 2021, Remote. Sens..

[5]  John K. Schueller,et al.  A comparison of approaches for citrus canopy profile generation using ultrasonic and Leddar® sensors , 2019, Comput. Electron. Agric..

[6]  Junhwa Chi,et al.  An Optimal Image-Selection Algorithm for Large-Scale Stereoscopic Mapping of UAV Images , 2021, Remote. Sens..

[7]  Ewelina Rupnik,et al.  Simulation and Analysis of Photogrammetric UAV Image Blocks - Influence of Camera Calibration Error , 2019, Remote. Sens..

[8]  Lukasz Chechlinski,et al.  3D Object Recognition with Ensemble Learning - A Study of Point Cloud-Based Deep Learning Models , 2019, ISVC.

[9]  J. Niemeyer,et al.  Contextual classification of lidar data and building object detection in urban areas , 2014 .

[10]  Yuan Meng,et al.  Measurement and calculation of crown projection area and crown volume of individual trees based on 3D laser-scanned point-cloud data , 2017 .

[11]  Weixin Huang,et al.  Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process , 2021, Remote. Sens..

[12]  Christopher W. Bater,et al.  Automatic Delineation and Height Measurement of Regenerating Conifer Crowns under Leaf-Off Conditions Using UAV Imagery , 2020, Remote. Sens..

[13]  Jianping Wu,et al.  A Voxel-Based Method for Automated Identification and Morphological Parameters Estimation of Individual Street Trees from Mobile Laser Scanning Data , 2013, Remote. Sens..

[14]  Soohyeon Kim,et al.  A Study on Point Cloud Generation Method from UAV Image Using Incremental Bundle Adjustment and Stereo Image Matching Technique , 2018 .

[15]  Aboelmagd Noureldin,et al.  LiDAR/RISS/GNSS Dynamic Integration for Land Vehicle Robust Positioning in Challenging GNSS Environments , 2020, Remote. Sens..

[16]  Stuart R. Phinn,et al.  Detection of Banana Plants Using Multi-Temporal Multispectral UAV Imagery , 2021, Remote. Sens..

[17]  Yanming Chen,et al.  Building Point Detection from Vehicle-Borne LiDAR Data Based on Voxel Group and Horizontal Hollow Analysis , 2016, Remote. Sens..

[18]  J. Phattaralerphong,et al.  A method for 3D reconstruction of tree crown volume from photographs: assessment with 3D-digitized plants. , 2005, Tree physiology.

[19]  M. Weiss,et al.  Remote sensing for agricultural applications: A meta-review , 2020 .

[20]  Yutang Wang,et al.  Classification of Street Tree Species Using UAV Tilt Photogrammetry , 2021, Remote. Sens..

[21]  Yasutaka Nakata,et al.  Observation of Diurnal Ground Surface Changes Due to Freeze-Thaw Action by Real-Time Kinematic Unmanned Aerial Vehicle , 2021, Remote. Sens..

[22]  Patrick E. Clark,et al.  Aboveground Total and Green Biomass of Dryland Shrub Derived from Terrestrial Laser Scanning , 2014 .

[23]  Qamar-uz- Zaman,et al.  Performance of an Ultrasonic Tree Volume Measurement System in Commercial Citrus Groves , 2005, Precision Agriculture.

[24]  A. Hovi,et al.  Estimation of tree crown volume from airborne lidar data using computational geometry , 2013 .

[25]  Borja Velázquez-Martí,et al.  Different methodologies for calculating crown volumes of Platanus hispanica trees using terrestrial laser scanner and a comparison with classical dendrometric measurements , 2013 .

[26]  Yi Li,et al.  Building segmentation and outline extraction from UAV image-derived point clouds by a line growing algorithm , 2017, Int. J. Digit. Earth.

[27]  Diego André Sant’Ana,et al.  Semantic Segmentation of Tree-Canopy in Urban Environment with Pixel-Wise Deep Learning , 2021, Remote. Sens..

[28]  Feng Zhongke An estimation of tree canopy biomass based on 3D laser scanning imaging system. , 2007 .

[29]  José Marcato Junior,et al.  Benchmarking Anchor-Based and Anchor-Free State-of-the-Art Deep Learning Methods for Individual Tree Detection in RGB High-Resolution Images , 2021, Remote. Sens..

[30]  Eric Chaumette,et al.  Precision-Aided Partial Ambiguity Resolution Scheme for Instantaneous RTK Positioning , 2021, Remote. Sens..

[31]  Sebastian Egli,et al.  CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations , 2020, Remote. Sens..

[32]  W. M. Miller,et al.  Investigation of Laser and Ultrasonic Ranging Sensors for Measurements of Citrus Canopy Volume , 2002 .

[33]  Marco Amati,et al.  Individual Tree Canopy Parameters Estimation Using UAV-Based Photogrammetric and LiDAR Point Clouds in an Urban Park , 2021, Remote. Sens..

[34]  Francisco R. Feito-Higueruela,et al.  Automatic Grapevine Trunk Detection on UAV-Based Point Cloud , 2020, Remote. Sens..

[35]  Brad M. Potts,et al.  From Drones to Phenotype: Using UAV-LiDAR to Detect Species and Provenance Variation in Tree Productivity and Structure , 2020, Remote. Sens..

[36]  Clément Mallet,et al.  Individual tree segmentation over large areas using airborne LiDAR point cloud and very high resolution optical imagery , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[37]  Arko Lucieer,et al.  Development of a UAV-LiDAR System with Application to Forest Inventory , 2012, Remote. Sens..

[38]  R. C. Derksen,et al.  A HISTORY OF AIR-BLAST SPRAYER DEVELOPMENT AND FUTURE PROSPECTS , 2008 .

[39]  Ilkka Pölönen,et al.  Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks , 2020, Remote. Sens..

[40]  Linhai Jing,et al.  A New Individual Tree Species Recognition Method Based on a Convolutional Neural Network and High-Spatial Resolution Remote Sensing Imagery , 2021, Remote. Sens..

[41]  Qingwu Hu,et al.  A Novel Tree Height Extraction Approach for Individual Trees by Combining TLS and UAV Image-Based Point Cloud Integration , 2019, Forests.

[42]  S. Popescu,et al.  A voxel-based lidar method for estimating crown base height for deciduous and pine trees , 2008 .

[43]  Lin Li,et al.  A dual growing method for the automatic extraction of individual trees from mobile laser scanning data , 2016 .