Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of different rubber tree clones, PR107, CATAS 7-20-59, and CATAS 8-7-9, were taken as the study subjects. Through data collection using ground-based mobile light detection and ranging (LiDAR), a voxelisation method based on the scanned tree trunk data was proposed, and deep images (i.e., images normally used for deep learning) were generated through frontal and lateral projection transform of point clouds in each voxel with a length of 8 m and a width of 3 m. These images provided the training and testing samples for the faster region-based convolutional neural network (Faster R-CNN) of deep learning. Consequently, the Faster R-CNN combined with the generated training samples comprising 802 deep images with pre-marked trunk locations was trained to automatically recognize the trunk locations in the testing samples, which comprised 359 deep images. Finally, the point clouds for the lower parts of each trunk were extracted through back-projection transform from the recognized trunk locations in the testing samples and used as the seed points for the region’s growing algorithm to accomplish individual rubber tree crown segmentation. Compared with the visual inspection results, the recognition rate of our method reached 100% for the deep images of the testing samples when the images contained one or two trunks or the trunk information was slightly occluded by leaves. For the complicated cases, i.e., multiple trunks or overlapping trunks in one deep image or a trunk appearing in two adjacent deep images, the recognition accuracy of our method was greater than 90%. Our work represents a new method that combines a deep learning framework with point cloud processing for individual rubber tree crown segmentation based on ground-based mobile LiDAR scanned data.

[1]  Wuming Zhang,et al.  An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation , 2016, Remote. Sens..

[2]  M. Maltamo,et al.  ADAPTIVE METHODS FOR INDIVIDUAL TREE DETECTION ON AIRBORNE LASER BASED CANOPY HEIGHT MODEL , 2004 .

[3]  Ming Cheng,et al.  Tree Classification in Complex Forest Point Clouds Based on Deep Learning , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Fuquan Zhang,et al.  Piecewise Linear Regression Based on Plane Clustering , 2019, IEEE Access.

[5]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Zhixiang Wu,et al.  Seasonal changes impact soil bacterial communities in a rubber plantation on Hainan Island, China. , 2018, The Science of the total environment.

[7]  Bangqian Chen,et al.  Simulation of multi-platform LiDAR for assessing total leaf area in tree crowns , 2019, Agricultural and Forest Meteorology.

[8]  Bangqian Chen,et al.  Estimation of rubber stand age in typhoon and chilling injury afflicted area with Landsat TM data: A case study in Hainan Island, China , 2012 .

[9]  Guan Gui,et al.  Deep Learning Based Improved Classification System for Designing Tomato Harvesting Robot , 2018, IEEE Access.

[10]  Q. Guo,et al.  A bottom-up approach to segment individual deciduous trees using leaf-off lidar point cloud data , 2014 .

[11]  Clément Mallet,et al.  Detection, segmentation and localization of individual trees from mms point cloud data , 2016 .

[12]  B. Žalik,et al.  An efficient approach to 3D single tree-crown delineation in LiDAR data , 2015 .

[13]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[14]  M. Wimmer,et al.  ffi cient Tree Modeling from Airborne LiDAR Point Clouds , 2017 .

[15]  Éric Gaussier,et al.  A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation , 2005, ECIR.

[16]  Tony P. Pridmore,et al.  Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping , 2016 .

[17]  Chien-Shun Lo,et al.  A Multi-level Morphological Active Contour Algorithm for Delineating Tree Crowns in Mountainous Forest , 2011 .

[18]  Lin Cao,et al.  A Novel Approach for Retrieving Tree Leaf Area from Ground-Based LiDAR , 2016, Remote. Sens..

[19]  Woo-Kyun Lee,et al.  Estimating Crown Variables of Individual Trees Using Airborne and Terrestrial Laser Scanners , 2011, Remote. Sens..

[20]  Zhongke Feng,et al.  Applicability of personal laser scanning in forestry inventory , 2019, PloS one.

[21]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  Michela Bertolotto,et al.  Octree-based region growing for point cloud segmentation , 2015 .

[24]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Taghi M. Khoshgoftaar,et al.  A survey of transfer learning , 2016, Journal of Big Data.

[26]  Xusheng Lei,et al.  Intelligent fault detection of high voltage line based on the Faster R-CNN , 2019, Measurement.

[27]  Mikko Inkinen,et al.  A segmentation-based method to retrieve stem volume estimates from 3-D tree height models produced by laser scanners , 2001, IEEE Trans. Geosci. Remote. Sens..

[28]  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..

[29]  Kang Jiang,et al.  Rubber Tree Crown Segmentation and Property Retrieval Using Ground-Based Mobile LiDAR after Natural Disturbances , 2019, Remote. Sens..

[30]  Lei Wang,et al.  3D Point Cloud Analysis and Classification in Large-Scale Scene Based on Deep Learning , 2019, IEEE Access.

[31]  Linhai Jing,et al.  An individual tree crown delineation method based on multi-scale segmentation of imagery , 2012 .

[32]  Yi Lin,et al.  Three-level frame and RD-schematic algorithm for automatic detection of individual trees from MLS point clouds , 2012 .

[33]  Z. Shi,et al.  A robust method to estimate foliar phosphorus of rubber trees with hyperspectral reflectance , 2018, Industrial Crops and Products.

[34]  George C. Hurtt,et al.  An efficient, multi-layered crown delineation algorithm for mapping individual tree structure across multiple ecosystems , 2014 .

[35]  Bin Chen,et al.  Plane-Gaussian artificial neural network , 2011, Neural Computing and Applications.

[36]  Shang Gao,et al.  Deep Learning: Individual Maize Segmentation From Terrestrial Lidar Data Using Faster R-CNN and Regional Growth Algorithms , 2018, Front. Plant Sci..

[37]  Peng Du,et al.  A Fast Face Recognition System Based on Deep Learning , 2018, 2018 11th International Symposium on Computational Intelligence and Design (ISCID).

[38]  Maggi Kelly,et al.  A New Method for Segmenting Individual Trees from the Lidar Point Cloud , 2012 .

[39]  J. Holmgren,et al.  Estimation of stem attributes using a combination of terrestrial and airborne laser scanning , 2012, European Journal of Forest Research.

[40]  Wei Chen,et al.  Adaptive Mean Shift-Based Identification of Individual Trees Using Airborne LiDAR Data , 2017, Remote. Sens..

[41]  Michael Wimmer,et al.  Efficient tree modeling from airborne LiDAR point clouds , 2017, Comput. Graph..

[42]  Sangjun Kim,et al.  Fast Pedestrian Detection in Surveillance Video Based on Soft Target Training of Shallow Random Forest , 2019, IEEE Access.

[43]  Lin Cao,et al.  Extraction of Leaf Biophysical Attributes Based on a Computer Graphic-based Algorithm Using Terrestrial Laser Scanning Data , 2018, Remote. Sens..

[44]  Reza Ehsani,et al.  Detection of citrus fruit and tree trunks in natural environments using a multi-elliptical boundary model , 2018, Comput. Ind..

[45]  Yinghai Ke,et al.  A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing , 2011 .

[46]  Bin Wu,et al.  Individual tree crown delineation using localized contour tree method and airborne LiDAR data in coniferous forests , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[47]  Leonard Barolli,et al.  A Vegetable Category Recognition System Using Deep Neural Network , 2016, 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS).

[48]  Liang Zhang,et al.  A Deep Neural Network With Spatial Pooling (DNNSP) for 3-D Point Cloud Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[49]  Wei An,et al.  Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval , 2019, IEEE Transactions on Multimedia.

[50]  Fuquan Zhang,et al.  Infinite norm large margin classifier , 2019, Int. J. Mach. Learn. Cybern..

[51]  Yun Wu,et al.  A model for fine-grained vehicle classification based on deep learning , 2017, Neurocomputing.

[52]  Philippe Giguère,et al.  Mapping forests using an unmanned ground vehicle with 3D LiDAR and graph-SLAM , 2018, Comput. Electron. Agric..

[53]  Johan Holmgren,et al.  Tree Stem and Height Measurements using Terrestrial Laser Scanning and the RANSAC Algorithm , 2014, Remote. Sens..

[54]  Yanming Chen,et al.  Segmentation of Individual Trees From TLS and MLS Data , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[55]  Chunhua Hu,et al.  A 3D Point Cloud Filtering Method for Leaves Based on Manifold Distance and Normal Estimation , 2019, Remote. Sens..

[56]  Bisheng Yang,et al.  A new method for 3D individual tree extraction using multispectral airborne LiDAR point clouds , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[57]  Rama Rao Nidamanuri,et al.  Individual tree detection from airborne laser scanning data based on supervoxels and local convexity , 2019, Remote Sensing Applications: Society and Environment.