Application of Intelligent Interpolation Methods for DTM Generation of Forest Areas Based on LiDAR Data

The increased ability of laser pulses to penetrate the vegetation cover has made LiDAR technology an attractive option for the generation of Digital Terrain Models (DTM) of forest areas. A LiDAR-based DTM generation consists of two phases, filtering and interpolation. This study suggests a combination of a slope-based and a hybrid filter for filtering of raw LiDAR data with innovative interpolation methods including artificial neural network (ANN) and artificial emotional neural network (ENN). Also, the genetic algorithm (GA) is used to improve both polynomial and inverse distance weighting (IDW) interpolation methods. The performance of those intelligent methods was also compared with that of conventional methods such as kriging and radial basis functions (RBF). For practical applicability of the presented method, two LiDAR datasets of forest regions in the Golestan province of Iran were selected, one with dense vegetation cover (Tavar-kuh) and one with reduced cover density (Shastkola-River basin). The results of these studies indicate that the hybrid filter outperforms the slope-based filter. Also the conventional interpolation methods were unable to achieve the accuracies offered by the intelligent methods. The elevation of the result shows that the best DTM reaches a root-mean-square error (RMSE) of 0.09 m for Tavar-kuh and 0.12 m for Shastkola-River basin by hybrid filter with an ENN interpolation.ZusammenfassungAnwendung von intelligenten Interpolationsmethoden zur LiDAR-basierten DTM-Erfassung von Waldgebieten. Die verbesserten Möglichkeiten des Laserscanning zur Durchdringung der Vegetationsdecke hat die LiDAR-Technologie attraktiv für die Erzeugung von Digitalen Geländemodellen (DGM) in Waldgebieten gemacht. Die LiDAR-basierte DGM-Erzeugung erfolgt in zwei Schritten, Filterung und Interpolation. Die Studie empfiehlt eine Kombination eines die Geländeneigung berücksichtigenden und eines hybriden Filters mit innovativen Interpolationsmethoden wie Artificial Neural Network (ANN) und Artificial Emotional Neural Network (ENN). Ergänzend wird der Genetische Algorithmus (GA) verwendet, um sowohl die polynomiale als auch die Inverse Distance Weighting (IDW) Interpolationsmethode zu verbessern. Die Leistungsfähigkeit dieser Methoden wurde der einiger konventioneller Methoden wie Kriging und Radial Basis Functions (RBS) gegenübergestellt. Für den praktischen Teil wurden zwei LiDAR-Datensätze aus Waldgebieten der Provinz Golestan im Iran ausgewählt, und zwar einer mit dichter Vegetationsdecke (Tavar-Kuh) und einer mit offener Vegetation (Tal des Flusses Shastkola). Die Ergebnisse zeigen eine höhere Leitungsfähigkeit des hybriden Filters im Vergleich zum die Geländeneigung berücksichtigen Filters. Auch in Hinblick auf die Genauigkeit sind die vorgestellten den konventionellen Methoden überlegen. Der Root-Mean-Square Höhenfehler liegt nach Anwendung des hybriden Filters in Verbindung mit der Anwendung von ENN bei 0.09 m für Tavar-Kuh und 0,12 m beim Flusstal.

[1]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[2]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[3]  R. Franke.  Scattered data interpolation: tests of some methods , 1982 .

[4]  R. L. Hardy.  Theory and applications of the multiquadric-biharmonic method : 20 years of discovery 1968-1988 , 1990 .

[5]  R. E. Carlson,et al.  The parameter R2 in multiquadric interpolation , 1991 .

[6]  Efraim Turban,et al.  Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real-World Performance , 1992 .

[7]  Maureen Caudill,et al.  Understanding Neural Networks; Computer Explorations , 1992 .

[8]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[9]  K. Kraus,et al.  Determination of terrain models in wooded areas with airborne laser scanner data , 1998 .

[10]  G. Vosselman.  SLOPE BASED FILTERING OF LASER ALTIMETRY DATA , 2000 .

[11]  P. Lohmann,et al.  APPROACHES TO THE FILTERING OF LASER SCANNER DATA , 2000 .

[12]  P. Axelsson.  DEM Generation from Laser Scanner Data Using Adaptive TIN Models , 2000 .

[13]  John P. Wilson,et al.  Terrain analysis : principles and applications , 2000 .

[14]  R. Wack,et al.  DIGITAL TERRAIN MODELS FROM AIRBORNE LASER SCANNER DATA - A GRID BASED APPROACH , 2002 .

[15]  F. Samadzadegan,et al.  AUTOMATIC SURFACE RECONSTRUCTION BASED ON THE FUSION OF FUZZY LOGIC AND ROBUST ESTIMATION TECHNIQUES , 2002 .

[16]  B. Fornberg,et al.  Theoretical and computational aspects of multivariate interpolation with increasingly flat radial basis functions , 2003 .

[17]  Chengcui Zhang,et al.  A progressive morphological filter for removing nonground measurements from airborne LIDAR data , 2003, IEEE Trans. Geosci. Remote. Sens..

[18]  D. Roberts,et al.  Small-footprint lidar estimation of sub-canopy elevation and tree height in a tropical rain forest landscape , 2004 .

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

[20]  George Vosselman,et al.  Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds , 2004 .

[21]  N. Pfeifer,et al.  SEGMENTATION BASED ROBUST INTERPOLATION - A NEW APPROACH TO LASER DATA FILTERING , 2005 .

[22]  G. Sithole,et al.  Segmentation and classification of airborne laser scanner data , 2005 .

[23]  Hong Wei,et al.  DTM Generation from LIDAR Data using Skewness Balancing , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[24]  P. Gong,et al.  Filtering airborne laser scanning data with morphological methods , 2007 .

[25]  Ali Mansourian,et al.  Rational function optimization using genetic algorithms , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Andrew Thomas Hudak,et al.  A Multiscale Curvature Algorithm for Classifying Discrete Return LiDAR in Forested Environments , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Norbert Pfeifer,et al.  Repetitive interpolation: A robust algorithm for DTM generation from Aerial Laser Scanner Data in forested terrain☆ , 2007 .

[28]  L. Xiaowen,et al.  CLASSIFICATION OF LIDAR POINT CLOUD AND GENERATION OF DTM FROM LIDAR HEIGHT AND INTENSITY DATA IN FORESTED AREA , 2008 .

[29]  H. Asakereh.  KRIGING APPLICATION IN CLIMATIC ELEMENT INTERPOLATION (A CASE STUDY: IRAN PRECIPITATION IN 1996.12.16) , 2008 .

[30]  X. Zhang,et al.  DERIVATION OF DIGITAL TERRAIN MODEL IN FORESTED AREA WITH AIRBORNE LIDAR DATA , 2008 .

[31]  J. Shan,et al.  Topographic laser ranging and scanning : principles and processing , 2008 .

[32]  Michael Höhle,et al.  Accuracy assessment of digital elevation models by means of robust statistical methods , 2009 .

[33]  Kaiguang Zhao,et al.  Ground Filtering Algorithms for Airborne LiDAR Data: A Review of Critical Issues , 2010, Remote. Sens..

[34]  C. Cao,et al.  Estimating biomass of individual trees using point cloud data of airborne LIDAR , 2010 .

[35]  Siti Zaiton Mohd Hashim,et al.  A review of emotional learning and it's utilization in control engineering , 2010, SOCO 2010.

[36]  David J. Harding,et al.  Polarimetric, two-color, photon-counting laser altimeter measurements of forest canopy structure , 2011, International Symposium on Lidar and Radar Mapping Technologies.

[37]  Mohammad Javad Valadan Zoej,et al.  A Novel Filtering Algorithm for Bare-Earth Extraction From Airborne Laser Scanning Data Using an Artificial Neural Network , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[38]  Domen Mongus,et al.  Parameter-free ground filtering of LiDAR data for automatic DTM generation , 2012 .

[39]  Juha Hyyppä,et al.  Advances in Forest Inventory Using Airborne Laser Scanning , 2012, Remote. Sens..

[40]  Thomas Schmickl,et al.  EMANN - a model of emotions in an artificial neural network , 2013, ECAL.

[41]  Almasi S. Maguya,et al.  Adaptive algorithm for large scale dtm interpolation from lidar data for forestry applications in steep forested terrain , 2013 .

[42]  K. Stereńczak,et al.  A two-phase inventory method for calculating standing volume and tree-density of forest stands in central Poland based on airborne laser-scanning data , 2013 .

[43]  Y. Li.  FILTERING AIRBORNE LIDAR DATA BY AN IMPROVED MORPHOLOGICAL METHOD BASED ON MULTI-GRADIENT ANALYSIS , 2013 .

[44]  S. Hagen,et al.  Topographic accuracy assessment of bare earth lidar-derived unstructured meshes , 2013 .

[45]  Ehsan Lotfi,et al.  BRAIN EMOTIONAL LEARNING-BASED PATTERN RECOGNIZER , 2013, Cybern. Syst..

[46]  Louis de Mesnard.  Pollution models and inverse distance weighting: Some critical remarks , 2013, Comput. Geosci..

[47]  Akbar Najafi,et al.  Forest Road Detection Using LiDAR Data , 2014, Journal of Forestry Research.

[48]  Bing Zhang,et al.  Modeling Accumulated Volume of Landslides Using Remote Sensing and DTM Data , 2014, Remote. Sens..

[49]  Ehsan Lotfi,et al.  Practical emotional neural networks , 2014, Neural Networks.

[50]  Hossein Bagheri,et al.  The Assessment of using an Intelligent Algorithm for the Interpolation of Elevation in the DTM Generation Verwendung von Methoden der künstlichen Intelligenz zur Ableitung von Höhenmodellen , 2014 .

[51]  D G Krige,et al.  A statistical approach to some mine valuation and allied problems on the Witwatersrand , 2015 .

[52]  T. Zawila-Niedzwiecki,et al.  Comparison of various algorithms for DTM interpolation from LIDAR data in dense mountain forests , 2016 .

[53]  Martin Isenburg,et al.  Generating spike-free digital surface models using LiDAR raw point clouds: A new approach for forestry applications , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[54]  N. Pfeifer,et al.  LiDAR Data Filtering and DTM Generation , 2017 .