Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning
Abstract
:1. Introduction
2. Feature Extraction for FWL
3. Methodology of LiDAR Point Clouds Classification
3.1. Construction of WSVM Model
3.2. Parameter Optimization
3.3. WSVM Ensemble
3.4. Implementation of the Proposed Method
- Step 1: Acquire FWL data and filter noise in the data.
- Step 2: Decompose full-waveform LiDAR data and extract the features displayed in Table 1.
- Step 3: Use bootstrap sampling to generate sub-datasets and assign them to each base classifier.
- Step 4: Train base classifiers with the parameters of each particle in the population.
- Step 6: Update global optimal accuracy and corresponding parameters.
- Step 6.1:
- Compare the classification accuracy of the particles in the current generation with the global optimal accuracy.
- Step 6.2:
- Determine whether to update the global optimal accuracy and the corresponding parameters on the basis of comparison result.
- Step 6.3:
- Return to Step 4 until the number of iterations has reached the maximum value.
- Step 7: Save the parameters achieved by the global optimal accuracy of each base classifier according to Steps 4–6, and take them as the parameters of each classifier.
- Step 8: Each base classifier predicts the labels of data with their parameters.
- Step 9: Output the final results with majority voting.
4. Experimental Results and Discussion
4.1. Experimental Platform and Data Information
4.2. Classification Results for Point Clouds
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Magiera, J. Can Satellite Remote Sensing Be Applied in Geological Mapping in Tropics? E3S Web Conf. 2018, 35, 1–9. [Google Scholar] [CrossRef]
- Maltezos, E.; Doulamis, A.; Doulamis, N. Building Extraction From LiDAR Data Applying Deep Convolutional Neural Networks. IEEE Geosci. Remote Sens. Lett. 2018, 16, 155–159. [Google Scholar] [CrossRef]
- Ekhtari, N.; Glennie, C.; Fernandez-Diaz, J.C. Classification of Airborne Multispectral LiDAR Point Clouds for Land Cover Mapping. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018, 11, 2068–2078. [Google Scholar] [CrossRef]
- Elaksher, A.F. Fusion of Hyperspectral Images and LiDAR-based Dems for Coastal Mapping. Opt. Lasers Eng. 2008, 46, 493–498. [Google Scholar] [CrossRef]
- Bork, E.W.; Su, J.G. Integrating LIDAR Data and Multispectral Imagery for Enhanced Classification of Rangeland Vegetation: A Meta Analysis. Remote Sens. Environ. 2007, 111, 11–24. [Google Scholar] [CrossRef]
- Campos-Taberner, M.; Romero-Soriano, A.; Gatta, C.; Camps-Valls, G.; Lagrange, A.; Saux, B.L.; Beaupère, A.; Boulch, A.; Chan-Hon-Tong, A.; Herbin, S.; et al. Processing of extremely high-resolution LiDAR and RGB data: Outcome of the 2015 IEEE GRSS Data Fusion Contest–Part A: 2-D Contest. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 5547–5559. [Google Scholar] [CrossRef]
- Langer, H.; Falsaperla, S.; Masotti, M.; Campanini, R.; Spampinato, S.; Messina, A. Synopsis of Supervised and Unsupervised Pattern Classification Techniques Applied to Volcanic Tremor Data at Mt Etna, Italy. Geophys. J. Int. 2009, 178, 1132–1144. [Google Scholar] [CrossRef]
- Chehataa, N.; Davidb, N.; Bretar, F. LiDAR Data Classification Using Hierarchical K-means Clustering. In Proceedings of the ISPRS Congress, Beijing, China, 3–11 July 2008; pp. 325–330. [Google Scholar]
- Hou, T.; Liu, J.; Liu, Y. Algorithmic Clustering of LiDAR Point Cloud Data for Textural Damage Identifications of Structural Elements. Measurement 2017, 108, 77–90. [Google Scholar] [CrossRef]
- Gu, Z.; Cao, S.; Sanchez-Azofeifa, G.A. Using LiDAR Waveform Metrics to Describe and Identify Successional Stages of Tropical dry forests. Int. J. Appl. Earth Obs. Geoinf. 2018, 73, 482–492. [Google Scholar] [CrossRef]
- Vo, A.; Linh, T.; Laefer, D.F.; Tiede, D.; Oleire-Oltmanns, S.; Baraldi, A.; Shimoni, M.; Moser, G.; Tuia, D. Processing of Extremely High Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest—Part B: 3-D Contest. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2015, 9, 5560–5575. [Google Scholar] [CrossRef]
- Ni, H.; Lin, X.; Zhang, J. Classification of ALS Point Cloud with Improved Point Cloud Segmentation and Random Forests. Remote Sens. 2017, 9, 288. [Google Scholar] [CrossRef]
- Qiao, J.; Liu, X.; Zhang, Y.H. Land Cover Classification Using LiDAR Height Texture and ANNs. J. Remote Sens. 2011, 15, 539–553. [Google Scholar]
- Penner, M.; Pitt, D.G.; Woods, M.E. Parametric vs. Nonparametric LiDAR Models for Operational Forest Inventory In Boreal Ontario. Can. J. Remote Sens. 2013, 39, 426–443. [Google Scholar]
- Mallet, C.; Bretar, F. Full-waveform topographic LiDAR: State-of-the-art. ISPRS J. Photogramm. Remote Sens. 2009, 64, 1–16. [Google Scholar] [CrossRef]
- Wang, J.; Li, C.; Tang, L.; Zhou, M.; Li, J.M. A Comparison of Two Different Approaches of Point Cloud Classification Based on Full-waveform LIDAR Data. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2012, 39, 179–182. [Google Scholar] [CrossRef]
- Guo, L.; Chehata, N.; Mallet, C.; Boukir, S. Relevance of Airborne Lidar and Multispectral Image Data for Urban Scene Classification Using Random Forests. ISPRS J. Photogramm. Remote Sens. 2011, 66, 56–66. [Google Scholar] [CrossRef]
- Höfle, B.; Hollaus, M.; Hagenauer, J. Urban Vegetation Detection Using Radiometrically Calibrated Small-footprint Full-waveform Airborne LiDAR Data. ISPRS J. Photogramm. Remote Sens. 2012, 67, 134–147. [Google Scholar] [CrossRef]
- Mallet, C.; Bretar, F.; Roux, M.; Soergel, U.; Heipke, C. Relevance Assessment of Full-waveform Lidar Data for Urban Area Classification. ISPRS J. Photogramm. Remote Sens. 2011, 66, 71–84. [Google Scholar] [CrossRef]
- Maxwell, A.E.; Warner, T.A.; Fang, F. Implementation of Machine-learning Classification in Remote Sensing: An Applied Review. Int. J. Remote Sens. 2018, 39, 2784–2817. [Google Scholar] [CrossRef]
- Phu, V.N.; Chau, V.T.N.; Tran, V.T.N. SVM for English Semantic Classification in Parallel Environment. Int. J. Speech Technol. 2017, 20, 487–508. [Google Scholar] [CrossRef]
- Sukawattanavijit, C.; Jie, C.; Zhang, H. GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing Data. IEEE Geosci. Remote Sens. Lett. 2017, 14, 284–288. [Google Scholar] [CrossRef]
- Santos, P.; Villa, L.F.; Reñones, A.; Bustillo, A.; Maudes, J. An SVM-Based Solution for Fault Detection in Wind Turbines. Sensors 2015, 15, 5627–5648. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Dihkan, M.; Guneroglu, N.; Karsli, F.; Guneroglu, A. Remote Sensing of Tea Plantations Using An SVM Classifier and Pattern-based Accuracy Assessment Technique. Int. J. Remote Sens. 2013, 34, 8549–8565. [Google Scholar] [CrossRef]
- Seifi, M.R.; Ghassemian, H. A Probabilistic SVM Approach for Hyperspectral Image Classification Using Spectral and Texture Features. Int. J. Remote Sens. 2017, 38, 4265–4284. [Google Scholar] [CrossRef]
- Zhou, M.; Li, C.; Ma, L.; Guan, H.C. Land Cover Classification from Full-waveform LiDAR Data Based on Support Vector Machines. In Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, ISPRS Congress, Prague, Czech Republic, 12–19 July 2016; pp. 447–452. [Google Scholar]
- Tseng, Y.; Wang, C.; Chu, H.J.; Hung, Y.C. Waveform-based Point Cloud Classification in Land-cover Identification. Int. J. Appl. Earth Obs. Geoinf. 2015, 34, 78–88. [Google Scholar] [CrossRef]
- Kedzierski, M.; Fryskowska, A. Terrestrial and Aerial Laser Scanning Data Integration Using Wavelet Analysis for the Purpose of 3D Building Modeling. Sensors 2014, 14, 12070–12092. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Krawczyk, B.; Minku, L.L.; Gama, J.; Stefanowski, J.; Woźniak, M. Ensemble Learning for Data Stream Analysis: A Survey. Inf. Fusion 2017, 37, 132–156. [Google Scholar] [CrossRef]
- Dou, P.; Chen, Y. Remote Sensing Imagery Classification Using AdaBoost with A Weight Vector. Remote Sens. Lett. 2017, 8, 733–742. [Google Scholar] [CrossRef]
- Waske, B.; Van, L.S.; Benediktsson, J.A.; Rabe, A.; Hostert, P. Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data. IEEE Trans. Geosci. Remote Sens. 2010, 48, 2880–2889. [Google Scholar] [CrossRef] [Green Version]
- Sun, J.; Fujita, H.; Chen, P.; Li, H. Dynamic Financial Distress Prediction with Concept Drift Based on Time Weighting Combined with Adaboost Support Vector Machine Ensemble. Knowl. Based Syst. 2017, 120, 4–14. [Google Scholar] [CrossRef]
- Yu, L.; Yue, W.; Wang, S.; Lai, K.K. Support Vector Machine Based Multiagent Ensemble Learning for Credit Risk Evaluation. Expert Syst. Appl. 2010, 37, 1351–1360. [Google Scholar] [CrossRef]
- Lai, X.; Zheng, M. A Denoising Method for LiDAR Full-Waveform Data. Math. Probl. Eng. 2015, 2015, 164318. [Google Scholar] [CrossRef]
- Lai, X.; Qin, N.N.; Han, X.S.; Wang, J.H.; Hou, W.G. Iterative Decomposition Method for Small Foot-print LiDAR Waveform. J. Infrared Millim. Waves 2013, 32, 319–324. [Google Scholar] [CrossRef]
- Wang, M.; Wan, Y.; Ye, Z.; Lai, X.D. Remote Sensing Image Classification Based on the Optimal Support Vector Machine and Modified Binary Coded Ant Colony Optimization Algorithm. Inf. Sci. 2017, 402, 50–68. [Google Scholar] [CrossRef]
- Tharwat, A. Parameter Investigation of Support Vector Machine Classifier with Kernel Functions. Knowl. Inf. Syst. 2019, 3, 1–34. [Google Scholar] [CrossRef]
- Xie, Z.P.; Chen, D.S.; Chen, S.C.; Qiao, L.S.; Yang, B. A Tight Support Kernel for Support Vector Machine. In Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, Hong Kong, China, 30–31 August 2008; pp. 460–464. [Google Scholar]
- Wang, A.; Zhao, Y.; Hou, Y.T.; Li, Y.L. A Novel Construction of SVM Compound Kernel Function. In Proceedings of the International Conference on Logistics Systems and Intelligent Management (ICLSIM), Harbin, China, 9–10 January 2010; pp. 1462–1465. [Google Scholar]
- Zhang, L.; Zhou, W.; Jiao, L. Wavelet Support Vector Machine. IEEE Trans. Syst. Man Cybern. 2004, 34, 34–39. [Google Scholar] [CrossRef]
- Xia, C.; Zhang, M.; Cao, J. A Hybrid Application of Soft Computing Methods with Wavelet SVM and Neural Network to Electric Power Load Forecasting. J. Electr. Syst. Inf. Technol. 2018, 5, 681–696. [Google Scholar] [CrossRef]
- García, P.J.; García-Gonzalo, E.; Alonso, J.R.; Muñiz, C.D. A Hybrid Wavelet Kernel SVM-based Method Using Artificial Bee Colony Algorithm for Predicting the Cyanotoxin Content from Experimental Cyanobacteria Concentrations in the Trasona Reservoir (Northern Spain). J. Comput. Appl. Math. 2017, 309, 587–602. [Google Scholar] [CrossRef]
- Liu, Z.; Cui, Y.; Li, W. A Classification Method for Complex Power Quality Disturbances Using EEMD and Rank Wavelet SVM. IEEE Trans. Smart Grid 2017, 6, 1678–1685. [Google Scholar] [CrossRef]
- Tang, B.; Song, T.; Li, F.; Deng, L. Fault Diagnosis for A Wind Turbine Transmission System Based on Manifold Learning and Shannon Wavelet Support Vector Machine. Renew. Eng. 2014, 62, 1–9. [Google Scholar] [CrossRef]
- Wang, P.; Gan, X.; Yao, D. Anomaly Intrusion Detection Based on Support Vector Machine with Mexico Hat Wavelet Kernel Function. Appl. Mech. Mater. 2014, 687, 3897–3900. [Google Scholar] [CrossRef]
- Domenico, C.; Alessandro, P. Spectrum-compatible Accelerograms with Harmonic Wavelets. Comput. Struct. 2015, 147, 26–35. [Google Scholar]
- Yang, G. License Plate Character Recognition Based on Wavelet Kernel LS-SVM. In Proceedings of the International Conference on Computer Research and Development, Shanghai, China, 11–13 March 2011; pp. 222–226. [Google Scholar]
- Wu, D.; Gu, X.; Guo, Q. A New Scheme of Automatic Modulation Classification Using Wavelet and WSVM. In Proceedings of the International Conference on Mobile Technology, Guangzhou, China, 15–17 November 2005. [Google Scholar]
- Eberhart, R.; Kennedy, J. A New Optimizer Using Particle Swarm Theory. In Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 4–6 October 1995; pp. 39–43. [Google Scholar]
- Wang, D.; Tan, D.; Liu, L. Particle Swarm Optimization Algorithm: An Overview. Soft Comput. 2018, 22, 387–408. [Google Scholar] [CrossRef]
- Li, L.; Hu, Q.; Wu, X.; Yu, D. Exploration of Classification Confidence in Ensemble Learning. Pattern Recognit. 2014, 47, 3120–3131. [Google Scholar] [CrossRef]
- Wang, S.; Mathew, A.; Yan, C.; Li, F.X.; Ma, L.; Lee, J. Empirical Analysis of Support Vector Machine Ensemble Classifiers. Expert Syst. Appl. 2009, 36, 6466–6476. [Google Scholar] [CrossRef]
- Bi, Y. The Impact of Diversity on the Accuracy of Evidential Classifier Ensembles. Int. J. Approx. Reason. 2012, 53, 584–607. [Google Scholar] [CrossRef]
Feature Type | Feature Name | Formula | Explanation |
---|---|---|---|
Geometric | h | / | In general, elevation can effectively distinguish between ground and off-ground points, but, for trees, houses, and hillsides with similar elevations, absolute elevation may not work. |
Z denotes the current point, denotes the average elevation of all points in , and n is the number of points in . High vegetation and the edges of buildings often have a greater height difference. | |||
is the volume of . Generally speaking, of building walls and trees is lower than others. | |||
c | c reflects the shape of the surface of the object, and the canopy usually has a high value. | ||
/ | Deviation angle of a normal vector from the vertical direction, reflecting the flatness of the ground object. | ||
The variance of the vertical angles of 3D points in , reflecting the shape of the ground object. | |||
Waveform | A | / | The value of the natural surface and building is the highest, and that of the asphalt surface and trees is low, thus it can distinguish between vegetation and artificial objects. |
/ | reflects the time that the laser pulse interacts with the ground object. Due to the scattering effect of the canopy on the laser, can distinguish between non-vegetation and vegetation. | ||
u | / | u can be used to calculate the distance between the laser emission location and the target. | |
I | / | I is the amount of energy returned by the laser pulse interacting with the ground objects whose characteristic is similar to A. |
Experimental | Data Area | Total | Training | Testing | Point Cloud |
---|---|---|---|---|---|
Data | Points | Samples | Samples | Density | |
Study Area 1 | 203,833 | 227,078 | 6450 | 5683 | 1.11 |
Study Area 2 | 180,030 | 283,315 | 6489 | 5070 | 1.57 |
Study Area 3 | 131,767 | 226,123 | 6739 | 5399 | 1.72 |
Experimental | Basic | Optimal | RF | ISODATA | Non-Optimization | Proposed |
---|---|---|---|---|---|---|
Data | SVM | WSVM | Method | |||
Study Area 1 | 78.6326 | 123.0621 | 139.9527 | 82.2098 | 69.6642 | 85.0167 |
Study Area 2 | 73.5228 | 111.6443 | 123.8943 | 76.3754 | 66.0029 | 78.4931 |
Study Area 3 | 88.9489 | 130.5389 | 152.0112 | 93.0824 | 77.4131 | 97.0145 |
Experimental | Basic | Optimal Single | RF | ISODATA | Non-Optimization | Proposed |
---|---|---|---|---|---|---|
Data | SVM | WSVMs | Method | |||
Study Area 1 | 66.0743 | 96.5720 | 94.8236 | 55.7943 | 93.4956 | 97.7477 |
Study Area 2 | 55.5702 | 94.5937 | 88.2017 | 77.6837 | 90.3324 | 95.0955 |
Study Area 3 | 66.8505 | 92.1143 | 93.1469 | 75.7884 | 84.4282 | 93.8322 |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lai, X.; Yuan, Y.; Li, Y.; Wang, M. Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning. Sensors 2019, 19, 3191. https://doi.org/10.3390/s19143191
Lai X, Yuan Y, Li Y, Wang M. Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning. Sensors. 2019; 19(14):3191. https://doi.org/10.3390/s19143191
Chicago/Turabian StyleLai, Xudong, Yifei Yuan, Yongxu Li, and Mingwei Wang. 2019. "Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning" Sensors 19, no. 14: 3191. https://doi.org/10.3390/s19143191
APA StyleLai, X., Yuan, Y., Li, Y., & Wang, M. (2019). Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning. Sensors, 19(14), 3191. https://doi.org/10.3390/s19143191