A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction Based on Unmanned Aerial Vehicle Images

Surveys of windthrown trees, resulting from hurricanes and other types of natural disasters, are an important component of agricultural insurance, forestry statistics, and ecological monitoring. Aerial images are commonly used to determine the total area or number of downed trees, but conventional methods suffer from two primary issues: misclassification of windthrown trees due to the interference from other objects or artifacts, and poor extraction resolution when trunk diameters are small. The objective of this study is to develop a coarse-to-fine extraction technique for individual windthrown trees that reduces the effects of these common flaws. The developed method was tested using UAV imagery collected over rubber plantations on Hainan Island after the Nesat typhoon in China on 19 October 2011. First, a coarse extraction of the affected area was performed by analyzing the image spectrum and textural characteristics. A thinning algorithm was then used to simplify downed trees into skeletal structures. Finally, fine extraction of individual trees was achieved using a line detection algorithm. The completeness of windthrown trees in the study area was 75.7% and the correctness was 92.5%. While similar values have been reported in other studies, they often include constraints, such as tree height. This technique is proposed to be a more feasible extraction algorithm as it is capable of achieving low commission errors across a broad range of tree heights and sizes. As such, it is a viable option for extraction of windthrown trees with a small trunk diameter.

[1]  Markus Hollaus,et al.  Detection of fallen trees in forested areas using small footprint airborne laser scanning data , 2013 .

[2]  Norbert Pfeifer,et al.  COMPARISON OF DISCRETE AND FULL-WAVEFORM ALS FEATURES FOR DEAD WOOD DETECTION , 2013 .

[3]  Markus Hollaus,et al.  Detection of lying tree stems from airborne laser scanning data using a line template matching algorithm , 2013 .

[4]  Jianhua Gong,et al.  UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis , 2015, Remote. Sens..

[5]  Y. R. Chen,et al.  Application of morphological image processing in agriculture. , 1990 .

[6]  S. Cui,et al.  Complex building description and extraction based on Hough transformation and cycle detection , 2012 .

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

[8]  Patrick Hostert,et al.  imageRF - A user-oriented implementation for remote sensing image analysis with Random Forests , 2012, Environ. Model. Softw..

[9]  Lars M. H. Ulander,et al.  Mapping of wind-thrown forests using VHF/UHF SAR images , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[10]  Rafael Grompone von Gioi,et al.  LSD: a Line Segment Detector , 2012, Image Process. Line.

[11]  K. Moffett,et al.  Remote Sens , 2015 .

[12]  Markus Hollaus,et al.  Assessment of Wooded Area Reduction by Airborne Laser Scanning , 2015 .

[13]  Markus Hollaus,et al.  Identification of dead trees using small footprint full-waveform airborne laser scanning data , 2012 .

[14]  Maurizio Santoro,et al.  Mapping of wind-thrown forests using satellite SAR images , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[15]  Johan Holmgren,et al.  Detection of windthrown trees using airborne laser scanning , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Rodney A. Walker,et al.  Towards automatic power line detection for a UAV surveillance system using pulse coupled neural filter and an improved Hough transform , 2009, Machine Vision and Applications.

[17]  Sowmya Selvarajan,et al.  Fusion of LiDAR and aerial imagery for the estimation of downed tree volume using Support Vector Machines classification and region based object fitting , 2011 .

[18]  Mikko T. Niemi,et al.  Extracting Canopy Surface Texture from Airborne Laser Scanning Data for the Supervised and Unsupervised Prediction of Area-Based Forest Characteristics , 2016, Remote. Sens..

[19]  Mustafa Turker,et al.  Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[20]  D. Stow,et al.  THE EFFECT OF TRAINING STRATEGIES ON SUPERVISED CLASSIFICATION AT DIFFERENT SPATIAL RESOLUTIONS , 2002 .

[21]  R. Suzuki,et al.  Unmanned Aerial Survey of Fallen Trees in a Deciduous Broadleaved Forest in Eastern Japan , 2014, PloS one.

[22]  Tim Appelhans,et al.  Improving the accuracy of rainfall rates from optical satellite sensors with machine learning — A random forests-based approach applied to MSG SEVIRI , 2014 .

[23]  Gustau Camps-Valls,et al.  Uncertainty analysis of gross primary production upscaling using Random Forests, remote sensing and eddy covariance data , 2015 .

[24]  Richard Gloaguen,et al.  TecLines: A MATLAB-Based Toolbox for Tectonic Lineament Analysis from Satellite Images and DEMs, Part 2: Line Segments Linking and Merging , 2014, Remote. Sens..

[25]  Arko Lucieer,et al.  Detecting pruning of individual stems using Airborne Laser Scanning data captured from an Unmanned Aerial Vehicle , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Giorgos Mountrakis,et al.  Assessing the impact of training sample selection on accuracy of an urban classification: a case study in Denver, Colorado , 2014 .

[27]  Christian Heipke,et al.  EVALUATION OF AUTOMATIC ROAD EXTRACTION , 2007 .

[28]  Fugui Wang,et al.  Comparison of remote sensing change detection techniques for assessing hurricane damage to forests , 2010, Environmental monitoring and assessment.

[29]  Zhang Dakun,et al.  Notice of RetractionOne Eighth Rule in N-queens Problem Based on Group Theory and Morphological Gene Combinations , 2009, 2009 International Forum on Information Technology and Applications.

[30]  F. Agüera,et al.  Automatic greenhouse delineation from QuickBird and Ikonos satellite images , 2009 .

[31]  Uwe Stilla,et al.  Detection of fallen trees in ALS point clouds using a Normalized Cut approach trained by simulation , 2015 .

[32]  Keinosuke Fukunaga,et al.  Effects of Sample Size in Classifier Design , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Djemel Ziou,et al.  Edge Detection Techniques-An Overview , 1998 .

[34]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[35]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[36]  Per Angelstam,et al.  Dead wood threshold values for the three-toed woodpecker presence in boreal and sub-alpine forest , 2004 .

[37]  Zoltan Szantoi,et al.  International Journal of Applied Earth Observation and Geoinformation a Tool for Rapid Post-hurricane Urban Tree Debris Estimates Using High Resolution Aerial Imagery , 2022 .

[38]  C. Bouget,et al.  The effects of windthrow on forest insect communities: a literature review , 2004 .

[39]  Maggi Kelly,et al.  Object-Based Image Analysis of Downed Logs in Disturbed Forested Landscapes Using Lidar , 2011, Remote. Sens..

[40]  Linlin Xu,et al.  A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1 imagery , 2014 .

[41]  Christopher B. Jones,et al.  A Triangulated Spatial Model for Cartographic Generalisation of Areal Objects , 1995, COSIT.

[42]  Xianjun Hao,et al.  Post-hurricane forest damage assessment using satellite remote sensing , 2010 .

[43]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[44]  Eija Honkavaara,et al.  Automatic Storm Damage Detection in Forests Using High-Altitude Photogrammetric Imagery , 2013, Remote. Sens..

[45]  Jocelyn Chanussot,et al.  Airborne remote sensing of vineyards for the detection of dead vine trees , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..