Combining Orientation Symmetry and LM Cues for the Detection of Citrus Trees in Orchards From a Digital Surface Model

This letter proposes a new approach for the automated detection of citrus trees from a single digital surface model (DSM) input. The new approach combines orientation symmetry information and local maxima cues in a probabilistic manner. Experiments are performed on eight test DSMs generated from unmanned aerial vehicle (UAV) images, and the results reveal that the new approach is capable of detecting citrus trees with a high success (overall <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula>-score of 92.5%). The performance of our approach is also compared with leading approaches from the literature and from our own previous work and provided superior or comparable results.

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

[2]  Mathias Schardt,et al.  Single tree detection in very high resolution remote sensing data , 2007 .

[3]  Hao Li,et al.  Regions of Interest Detection in Panchromatic Remote Sensing Images Based on Multiscale Feature Fusion , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  Donald A. Falk,et al.  Application of Metabolic Scaling Theory to reduce error in local maxima tree segmentation from aerial LiDAR , 2014 .

[6]  Moncef Gabbouj,et al.  Automated tree detection and density calculation using unmanned aerial vehicles , 2016, 2016 Visual Communications and Image Processing (VCIP).

[7]  Michele Dalponte,et al.  Delineation of Individual Tree Crowns from ALS and Hyperspectral data: a comparison among four methods , 2015 .

[8]  Lorenzo Bruzzone,et al.  A Hierarchical Approach to Three-Dimensional Segmentation of LiDAR Data at Single-Tree Level in a Multilayered Forest , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Asli Ozdarici-Ok,et al.  Automatic detection and delineation of citrus trees from VHR satellite imagery , 2015 .

[10]  Jungho Im,et al.  A novel transferable individual tree crown delineation model based on Fishing Net Dragging and boundary classification , 2015 .

[11]  Michael A. Lefsky,et al.  Review of studies on tree species classification from remotely sensed data , 2016 .

[12]  Arko Lucieer,et al.  Evaluating Tree Detection and Segmentation Routines on Very High Resolution UAV LiDAR Data , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Ali Ozgun Ok,et al.  DETECTION OF CITRUS TREES FROM UAV DSMS , 2017 .

[14]  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 .

[15]  Zhen Zhen,et al.  Trends in Automatic Individual Tree Crown Detection and Delineation - Evolution of LiDAR Data , 2016, Remote. Sens..

[16]  Huadong Guo,et al.  Individual Tree Delineation in Windbreaks Using Airborne-Laser-Scanning Data and Unmanned Aerial Vehicle Stereo Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[17]  Zhen Zhen,et al.  Impact of Tree-Oriented Growth Order in Marker-Controlled Region Growing for Individual Tree Crown Delineation Using Airborne Laser Scanner (ALS) Data , 2014, Remote. Sens..

[18]  P. Gong,et al.  Detection of individual trees and estimation of tree height using LiDAR data , 2007, Journal of Forest Research.

[19]  Jeffrey P. Walker,et al.  Analysis of full-waveform LiDAR data for classification of an orange orchard scene , 2013 .

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

[21]  Christian Heipke,et al.  Automatic extraction and delineation of single trees from remote sensing data , 2007, Machine Vision and Applications.

[22]  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..

[23]  Asli Ozdarici-Ok,et al.  2-D delineation of individual citrus trees from UAV-based dense photogrammetric surface models , 2018, Int. J. Digit. Earth.

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

[25]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..

[26]  Eero P. Simoncelli,et al.  Differentiation of discrete multidimensional signals , 2004, IEEE Transactions on Image Processing.