Accuracy Assessment of Deep Learning Based Classification of LiDAR and UAV Points Clouds for DTM Creation and Flood Risk Mapping

Digital elevation model (DEM) has been frequently used for the reduction and management of flood risk. Various classification methods have been developed to extract DEM from point clouds. However, the accuracy and computational efficiency need to be improved. The objectives of this study were as follows: (1) to determine the suitability of a new method to produce DEM from unmanned aerial vehicle (UAV) and light detection and ranging (LiDAR) data, using a raw point cloud classification and ground point filtering based on deep learning and neural networks (NN); (2) to test the convenience of rebalancing datasets for point cloud classification; (3) to evaluate the effect of the land cover class on the algorithm performance and the elevation accuracy; and (4) to assess the usability of the LiDAR and UAV structure from motion (SfM) DEM in flood risk mapping. In this paper, a new method of raw point cloud classification and ground point filtering based on deep learning using NN is proposed and tested on LiDAR and UAV data. The NN was trained on approximately 6 million points from which local and global geometric features and intensity data were extracted. Pixel-by-pixel accuracy assessment and visual inspection confirmed that filtering point clouds based on deep learning using NN is an appropriate technique for ground classification and producing DEM, as for the test and validation areas, both ground and non-ground classes achieved high recall (>0.70) and high precision values (>0.85), which showed that the two classes were well handled by the model. The type of method used for balancing the original dataset did not have a significant influence in the algorithm accuracy, and it was suggested not to use any of them unless the distribution of the generated and real data set will remain the same. Furthermore, the comparisons between true data and LiDAR and a UAV structure from motion (UAV SfM) point clouds were analyzed, as well as the derived DEM. The root mean square error (RMSE) and the mean average error (MAE) of the DEM were 0.25 m and 0.05 m, respectively, for LiDAR data, and 0.59 m and –0.28 m, respectively, for UAV data. For all land cover classes, the UAV DEM overestimated the elevation, whereas the LIDAR DEM underestimated it. The accuracy was not significantly different in the LiDAR DEM for the different vegetation classes, while for the UAV DEM, the RMSE increased with the height of the vegetation class. The comparison of the inundation areas derived from true LiDAR and UAV data for different water levels showed that in all cases, the largest differences were obtained for the lowest water level tested, while they performed best for very high water levels. Overall, the approach presented in this work produced DEM from LiDAR and UAV data with the required accuracy for flood mapping according to European Flood Directive standards. Although LiDAR is the recommended technology for point cloud acquisition, a suitable alternative is also UAV SfM in hilly areas.

[1]  D. Lague,et al.  Accurate 3D comparison of complex topography with terrestrial laser scanner: Application to the Rangitikei canyon (N-Z) , 2013, 1302.1183.

[2]  Taskin Kavzoglu,et al.  Increasing the accuracy of neural network classification using refined training data , 2009, Environ. Model. Softw..

[3]  George Vosselman,et al.  Ground and Multi-Class Classification of Airborne Laser Scanner Point Clouds Using Fully Convolutional Networks , 2018, Remote. Sens..

[4]  N. Pfeifer,et al.  Neighborhood systems for airborne laser data , 2005 .

[5]  Parisa Kordjamshidi,et al.  Deep Convolutional Neural Network for Flood Extent Mapping Using Unmanned Aerial Vehicles Data , 2019, Sensors.

[6]  M. Westoby,et al.  ‘Structure-from-Motion’ photogrammetry: A low-cost, effective tool for geoscience applications , 2012 .

[7]  Arko Lucieer,et al.  An Automated Technique for Generating Georectified Mosaics from Ultra-High Resolution Unmanned Aerial Vehicle (UAV) Imagery, Based on Structure from Motion (SfM) Point Clouds , 2012, Remote. Sens..

[8]  Venkatesh Merwade,et al.  Incorporating the effect of DEM resolution and accuracy for improved flood inundation mapping , 2015 .

[9]  Seungsoo Lee,et al.  Hyper-resolution 1D-2D urban flood modelling using LiDAR data and hybrid parallelization , 2018, Environ. Model. Softw..

[10]  Dingtao Shen,et al.  A Quantitative Flood-Related Building Damage Evaluation Method Using Airborne LiDAR Data and 2-D Hydraulic Model , 2019, Water.

[11]  Gary Thompson,et al.  Challenges and Opportunities for UAV-Based Digital Elevation Model Generation for Flood-Risk Management: A Case of Princeville, North Carolina , 2018, Sensors.

[12]  P.-E. Mellander,et al.  Defining optimal DEM resolutions and point densities for modelling hydrologically sensitive areas in agricultural catchments dominated by microtopography , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[13]  Heidar Rastiveis,et al.  Extraction of ground points from LiDAR data based on slope and progressive window thresholding (SPWT) , 2018 .

[14]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[15]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[16]  Carlos Castillo,et al.  Image-based surface reconstruction in geomorphometry - merits, limits and developments , 2016 .

[17]  Andrew K. C. Wong,et al.  Classification of Imbalanced Data: a Review , 2009, Int. J. Pattern Recognit. Artif. Intell..

[18]  Xiangyun Hu,et al.  Deep-Learning-Based Classification for DTM Extraction from ALS Point Cloud , 2016, Remote. Sens..

[19]  Guy J.-P. Schumann,et al.  Rapid Mapping of Small-Scale River-Floodplain Environments Using UAV SfM Supports Classical Theory , 2019, Remote. Sens..

[20]  Miro Govedarica,et al.  Flood risk assessment based on LiDAR and UAV points clouds and DEM , 2018, Remote Sensing.

[21]  Mark W. Smith,et al.  Structure from motion photogrammetry in physical geography , 2016 .

[22]  Adam Salach,et al.  Accuracy Assessment of Point Clouds from LiDAR and Dense Image Matching Acquired Using the UAV Platform for DTM Creation , 2018, ISPRS Int. J. Geo Inf..

[23]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.