High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning

This study presents a novel workflow for automated Digital Terrain Model (DTM) extraction from Airborne LiDAR point clouds based on a convolutional neural network (CNN), considering a transfer learning approach. The workflow consists of three parts: feature image generation, transfer learning using ResNet, and interpolation. First, each point is transformed into a featured image based on its elevation differences with neighboring points. Then, the feature images are classified into ground and non-ground using ImageNet pretrained ResNet models. The ground points are extracted by remapping each feature image to its corresponding points. Last, the extracted ground points are interpolated to generate a continuous elevation surface. We compared the proposed workflow with two traditional filters, namely the Progressive Morphological Filter (PMF) and the Progressive Triangulated Irregular Network Densification (PTD). Our results show that the proposed workflow establishes an advantageous DTM extraction accuracy with yields of only 0.52%, 4.84%, and 2.43% for Type I, Type II, and the total error, respectively. In comparison, Type I, Type II, and the total error for PMF are 7.82%, 11.60%, and 9.48% and for PTD 1.55%, 5.37%, and 3.22%, respectively. The root means square error (RMSE) for the 1 m resolution interpolated DTM is only 7.3 cm. Moreover, we conducted a qualitative analysis to investigate the reliability and limitations of the proposed workflow.

[1]  Norbert Pfeifer,et al.  Automatic Roof Plane Detection and Analysis in Airborne Lidar Point Clouds for Solar Potential Assessment , 2009, Sensors.

[2]  Wuming Zhang,et al.  An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation , 2016, Remote. Sens..

[3]  Xianyu Yu,et al.  An Improved Morphological Algorithm for Filtering Airborne LiDAR Point Cloud Based on Multi-Level Kriging Interpolation , 2016, Remote. Sens..

[4]  Shuanggen Jin,et al.  Automatic DTM extraction from airborne LiDAR based on expectation-maximization , 2019, Optics & Laser Technology.

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

[6]  Huan Wang,et al.  A Point Cloud Filtering Approach to Generating DTMs for Steep Mountainous Areas and Adjacent Residential Areas , 2016, Remote. Sens..

[7]  Yong Li,et al.  A gradient-constrained morphological filtering algorithm for airborne LiDAR , 2013 .

[8]  Xiangguo Lin,et al.  Filtering airborne LiDAR data by embedding smoothness-constrained segmentation in progressive TIN densification , 2013 .

[9]  Norbert Pfeifer,et al.  A Comprehensive Automated 3D Approach for Building Extraction, Reconstruction, and Regularization from Airborne Laser Scanning Point Clouds , 2008, Sensors.

[10]  Wanshou Jiang,et al.  Segmentation and Multi-Scale Convolutional Neural Network-Based Classification of Airborne Laser Scanner Data , 2018, Sensors.

[11]  Yong Li,et al.  An Improved Top-Hat Filter with Sloped Brim for Extracting Ground Points from Airborne Lidar Point Clouds , 2014, Remote. Sens..

[12]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[13]  Bingbo Gao,et al.  State-of-the-Art: DTM Generation Using Airborne LIDAR Data , 2017, Sensors.

[14]  Michael F. Hutchinson,et al.  Recent Progress in the ANUDEM Elevation Gridding Procedure , 2011 .

[15]  Airborne LiDAR for DEM generation: some critical issues , 2008 .

[16]  Xiang Li,et al.  Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[17]  Norbert Pfeifer,et al.  Classification of ALS Point Clouds Using End-to-End Deep Learning , 2019, PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science.

[18]  Ruibin Zhao,et al.  Classifying airborne LiDAR point clouds via deep features learned by a multi-scale convolutional neural network , 2018, Int. J. Geogr. Inf. Sci..

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

[20]  Francisco F. Rivera,et al.  Fast Ground Filtering of Airborne LiDAR Data Based on Iterative Scan-Line Spline Interpolation , 2019, Remote. Sens..

[21]  Saied Pirasteh,et al.  Developing an algorithm for automated geometric analysis and classification of landslides incorporating LiDAR-derived DEM , 2018, Environmental Earth Sciences.

[22]  Haiyan Guan,et al.  DEM generation from lidar data in wooded mountain areas by cross-section-plane analysis , 2014 .

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

[24]  Lingjing Wang,et al.  DANCE-NET: Density-aware convolution networks with context encoding for airborne LiDAR point cloud classification , 2020 .

[25]  George Vosselman,et al.  A deep learning approach to DTM extraction from imagery using rule-based training labels , 2018 .

[26]  Wenzhong Shi,et al.  Morphologically iterative triangular irregular network for airborne LiDAR filtering , 2020 .

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

[28]  Gui-Song Xia,et al.  A geometry-attentional network for ALS point cloud classification , 2020 .