A novel transferable individual tree crown delineation model based on Fishing Net Dragging and boundary classification

Abstract This study provides a novel approach to individual tree crown delineation (ITCD) using airborne Light Detection and Ranging (LiDAR) data in dense natural forests using two main steps: crown boundary refinement based on a proposed Fishing Net Dragging (FiND) method, and segment merging based on boundary classification. FiND starts with approximate tree crown boundaries derived using a traditional watershed method with Gaussian filtering and refines these boundaries using an algorithm that mimics how a fisherman drags a fishing net. Random forest machine learning is then used to classify boundary segments into two classes: boundaries between trees and boundaries between branches that belong to a single tree. Three groups of LiDAR-derived features—two from the pseudo waveform generated along with crown boundaries and one from a canopy height model (CHM)—were used in the classification. The proposed ITCD approach was tested using LiDAR data collected over a mountainous region in the Adirondack Park, NY, USA. Overall accuracy of boundary classification was 82.4%. Features derived from the CHM were generally more important in the classification than the features extracted from the pseudo waveform. A comprehensive accuracy assessment scheme for ITCD was also introduced by considering both area of crown overlap and crown centroids. Accuracy assessment using this new scheme shows the proposed ITCD achieved 74% and 78% as overall accuracy, respectively, for deciduous and mixed forest.

[1]  C. Gleason,et al.  A Review of Remote Sensing of Forest Biomass and Biofuel: Options for Small-Area Applications , 2011 .

[2]  Tomas Brandtberg,et al.  Individual tree-based species classification in high spatial resolution aerial images of forests using fuzzy sets , 2002, Fuzzy Sets Syst..

[3]  Jungho Im,et al.  Forest Biomass and Carbon Stock Quantification Using Airborne LiDAR Data: A Case Study Over Huntington Wildlife Forest in the Adirondack Park , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  Jungho Im,et al.  A Fusion Approach for Tree Crown Delineation from Lidar Data , 2012 .

[5]  Randolph H. Wynne,et al.  Estimating plot-level tree heights with lidar : local filtering with a canopy-height based variable window size , 2002 .

[6]  Borja Velázquez-Martí,et al.  Estimation of wood volume and height of olive tree plantations using airborne discrete-return LiDAR data , 2014 .

[7]  Stephen V. Stehman,et al.  Agent-based region growing for individual tree crown delineation from airborne laser scanning (ALS) data , 2015 .

[8]  S. Ha,et al.  Machine learning approaches to coastal water quality monitoring using GOCI satellite data , 2014 .

[9]  P. Gong,et al.  Isolating individual trees in a savanna woodland using small footprint lidar data , 2006 .

[10]  Barbara Koch,et al.  Investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[11]  D. Leckie,et al.  Detection and assessment of trees with Phellinus weirii (laminated root rot) using high resolution multi-spectral imagery , 2004 .

[12]  Jari P. Kaipio,et al.  Bayesian Approach to Tree Detection Based on Airborne Laser Scanning Data , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Jocelyn Chanussot,et al.  On the use of binary partition trees for the tree crown segmentation of tropical rainforest hyperspectral images , 2015 .

[14]  E. Næsset,et al.  Single Tree Segmentation Using Airborne Laser Scanner Data in a Structurally Heterogeneous Spruce Forest , 2006 .

[15]  Jungho Im,et al.  Remote Sensing-based House Value Estimation Using an Optimized Regional Regression Model , 2013 .

[16]  J. Reitberger,et al.  3D segmentation of single trees exploiting full waveform LIDAR data , 2009 .

[17]  Liviu Theodor Ene,et al.  Comparative testing of single-tree detection algorithms under different types of forest , 2011 .

[18]  Ben Gorte,et al.  A new method for individual tree measurement from airborne LiDAR , 2009 .

[19]  K. O. Niemann,et al.  Local Maximum Filtering for the Extraction of Tree Locations and Basal Area from High Spatial Resolution Imagery , 2000 .

[20]  Aaron E. Maxwell,et al.  Comparison of NAIP orthophotography and RapidEye satellite imagery for mapping of mining and mine reclamation , 2014 .

[21]  K. Itten,et al.  LIDAR-based geometric reconstruction of boreal type forest stands at single tree level for forest and wildland fire management , 2004 .

[22]  C. Burnett,et al.  A multi-scale segmentation/object relationship modelling methodology for landscape analysis , 2003 .

[23]  S. Popescu,et al.  Seeing the Trees in the Forest: Using Lidar and Multispectral Data Fusion with Local Filtering and Variable Window Size for Estimating Tree Height , 2004 .

[24]  M. Vastaranta,et al.  Predicting individual tree attributes from airborne laser point clouds based on the random forests technique , 2011 .

[25]  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..

[26]  Leila Maria Garcia Fonseca,et al.  Automatic tree crown delineation in tropical forest using hyperspectral data , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[27]  F. Gougeon.  A Crown-Following Approach to the Automatic Delineation of Individual Tree Crowns in High Spatial Resolution Aerial Images , 1995 .

[28]  Lindi J. Quackenbush,et al.  INDIVIDUAL TREE CROWN DETECTION AND DELINEATION FROM HIGH SPATIAL RESOLUTION IMAGERY USING ACTIVE CONTOUR AND HILL-CLIMBING METHODS , 2009 .

[29]  Åsa Persson,et al.  Detecting and measuring individual trees using an airborne laser scanner , 2002 .

[30]  Geoffrey J. Hay,et al.  Multiscale Object-Specific Analysis (MOSA): An Integrative Approach for Multiscale Landscape Analysis , 2004 .

[31]  Jaehoon Jung,et al.  Effects of national forest inventory plot location error on forest carbon stock estimation using k-nearest neighbor algorithm , 2013 .

[32]  Xuan Zhu,et al.  An integrated GIS tool for automatic forest inventory estimates of Pinus radiata from LiDAR data , 2013 .

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

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

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

[36]  Shijun Tang,et al.  Three-dimensional surface reconstruction of tree canopy from lidar point clouds using a region-based level set method , 2013 .

[37]  Jungho Im,et al.  Landfast sea ice monitoring using multisensor fusion in the Antarctic , 2015 .

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

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

[40]  Lindi J. Quackenbush,et al.  FOREST SPECIES CLASSIFICATION AND TREE CROWN DELINEATION USING QUICKBIRD IMAGERY , 2007 .

[41]  Juha Hyyppä,et al.  An International Comparison of Individual Tree Detection and Extraction Using Airborne Laser Scanning , 2012, Remote. Sens..

[42]  John E. Wagner,et al.  Variable selection for hedonic model using machine learning approaches: A case study in Onondaga County, NY , 2012 .

[43]  Fernand Meyer,et al.  Topographic distance and watershed lines , 1994, Signal Process..

[44]  Philip A. Townsend,et al.  A pseudo-waveform technique to assess forest structure using discrete lidar data , 2011 .

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

[46]  Daniel Rivero,et al.  Classification of EEG signals using relative wavelet energy and artificial neural networks , 2009, GEC '09.

[47]  Liviu Theodor Ene,et al.  Single tree detection in heterogeneous boreal forests using airborne laser scanning and area-based stem number estimates , 2012 .

[48]  D. A. Hill,et al.  Combined high-density lidar and multispectral imagery for individual tree crown analysis , 2003 .

[49]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[50]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[51]  I. Hung,et al.  Estimating number of trees, tree height and crown width using Lidar data , 2014 .

[52]  Jian Yang,et al.  A multi-band watershed segmentation method for individual tree crown delineation from high resolution multispectral aerial image , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[53]  Sang Jin Lee,et al.  The extraction of forest CO2 storage capacity using high-resolution airborne lidar data , 2013 .

[54]  Jungho Im,et al.  Characterization of Forest Crops with a Range of Nutrient and Water Treatments Using AISA Hyperspectral Imagery , 2012 .

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

[56]  Lucy Marshall,et al.  Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest , 2013 .

[57]  Markus Hollaus,et al.  A Benchmark of Lidar-Based Single Tree Detection Methods Using Heterogeneous Forest Data from the Alpine Space , 2015 .

[58]  P. Gong,et al.  Individual Tree-Crown Delineation and Treetop Detection in High-Spatial-Resolution Aerial Imagery , 2004 .

[59]  François A. Gougeon,et al.  Individual Tree Crown Image Analysis - A Step Towards Precision Forestry ∗ , 2001 .

[60]  Mats Rudemo,et al.  Automatic estimation of individual tree positions from aerial photos , 1997 .

[61]  N. Coops,et al.  Using airborne and ground-based ranging lidar to measure canopy structure in Australian forests , 2003 .

[62]  Le Wang,et al.  A Multi-scale Approach for Delineating Individual Tree Crowns with Very High Resolution Imagery , 2010 .

[63]  Jungho Im,et al.  Forest biomass estimation from airborne LiDAR data using machine learning approaches , 2012 .

[64]  Maxim J. Goldberg,et al.  Removing noise from music using local trigonometric bases and wavelet packets , 1994 .

[65]  J. Im,et al.  Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest , 2013 .

[66]  J. Rhee,et al.  Relationship between land cover patterns and surface temperature in urban areas , 2014 .

[67]  Bardan Ghimire,et al.  An Evaluation of Bagging, Boosting, and Random Forests for Land-Cover Classification in Cape Cod, Massachusetts, USA , 2012 .