[en] Most deep learning (DL) methods that are not end-to-end use several multi-scale and multi-type hand-crafted features that make the network challenging, more computationally intensive and vulnerable to overfitting. Furthermore, reliance on empirically-based feature dimensionality reduction may lead to misclassification. In contrast, efficient feature management can reduce storage and computational complexities, builds better classifiers, and improves overall performance. Principal Component Analysis (PCA) is a well-known dimension reduction technique that has been used for feature extraction. This paper presents a two-step PCA based feature extraction algorithm that employs a variant of feature-based PointNet (Qi et al., 2017a) for point cloud classification. This paper extends the PointNet framework for use on large-scale aerial LiDAR data, and contributes by (i) developing a new feature extraction algorithm, (ii) exploring the impact of dimensionality reduction in feature extraction, and (iii) introducing a non-end-to-end PointNet variant for per point classification in point clouds. This is demonstrated on aerial laser scanning (ALS) point clouds. The algorithm successfully reduces the dimension of the feature space without sacrificing performance, as benchmarked against the original PointNet algorithm. When tested on the well-known Vaihingen data set, the proposed algorithm achieves an Overall Accuracy (OA) of 74.64% by using 9 input vectors and 14 shape features, whereas with the same 9 input vectors and only 5PCs (principal components built by the 14 shape features) it actually achieves a higher OA of 75.36% which demonstrates the effect of efficient dimensionality reduction.
Disciplines :
Ingénierie, informatique & technologie: Multidisciplinaire, généralités & autres
Auteur, co-auteur :
NURUNNABI, Abdul Awal Md ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
TEFERLE, Felix Norman ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Laefer, Debra; New York University, USA > Center for Urban Science and Progress and Department of Civil and Urban Engineering
Lindenbergh, Roderik; Delft University of Technology, The Netherlands > Geosciences and Remote Sensing, Faculty of Civil Engineering and Geosciences
Hunegnaw, Addisu; University of Luxembourg, Luxembourg > Geodesy and Geospatial Engineering, Faculty of Science, Technology and Medicine
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
A TWO-STEP FEATURE EXTRACTION ALGORITHM: APPLICATION TO DEEP LEARNING FOR POINT CLOUD CLASSIFICATION
Date de publication/diffusion :
mars 2022
Nom de la manifestation :
9th Intl. Workshop 3D-ARCH “3D Virtual Reconstruction and Visualization of Complex Architectures
Lieu de la manifestation :
Mantova, Italie
Date de la manifestation :
from 02-03-2022 to 04-03-2022
Manifestation à portée :
International
Titre de l'ouvrage principal :
A TWO-STEP FEATURE EXTRACTION ALGORITHM: APPLICATION TO DEEP LEARNING FOR POINT CLOUD CLASSIFICATION
AHN: Actueel Hoogtebestand Nederland. Available at: https://app.pdok.nl/ahn3-downloadpage/.
Atik, M. E., Duran, Z., Seker, D. Z., 2021. Machine learning based supervised classification of point clouds using multiscale geometric features. Int. J Geo-Information, 10 (187), 1-23.
Bello, S. A., Yu, S., Wang, C., Adam, J. M., Li, J., 2020. Review: Deep learning on 3D point clouds. Remote Sensing, 12(11), 1729.
Bishop, C. M., 2006. Pattern Recognition and Machine Learning, Springer.
Blomley, R., Jutzi, B., Weinmann, M., 2016. 3D semantic labeling of ALS point clouds by exploiting multi-scale, multi-type neighborhoods for feature extraction. GEOBIA, Solutions and Synergies, 14-16 Sep.
Cabo, C., Ordóñez, C., Sáchez-Lasheras, F., Roca-Pardiñas, J., de Cos-Juez, J., 2019. Multiscale supervised classification of point clouds with urban and forest applications. Sensors, 19(20), 4523.
Cramer, M., 2010. The DGPF-test on digital airborne camera evaluation overview and test design. PFG Photogrammetrie, Fernerkundung, Geoinformation, 73-82.
Goodfellow, I., Yoshua B., Aaron, C., 2016. Deep Learning. MIT press.
Grilli, E., Poux, F., Remondino, F., 2021. Unsupervised object-based clustering in support of supervised point-based 3D point cloud classification. Int. Arch. of the Photogramm. Remote Sens. and Spat. Info. Sci., Vol. XLIII-B2, ISPRS Congress, 5-9 July.
Hastie, T., Tibshirani, R., Friedman, J., 2017. The Elements of Statistical Learning. Springer.
He, K., Zhang, X., Ren, S., Sun., J., 2015. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. IEEE ICCV,1026-1034.
Hsu, P-H., Zhuang, Z-Y., 2020. Incorporating hand-crafted features into deep learning for point cloud classification. Remote Sensing, 12 (3713), 1-28.
Hu, Q., et al., 2020. RandLA-Net: Efficient semantic segmentation of large-scale point clouds. CVPR, 11108-11117.
Hubert, M., Rousseeuw, P. J., Vanden Branden, K., 2005. ROBPCA: a new approach to robust principal component analysis. Technometrics, 47(1), 64-79.
Hubert, M., Rousseeuw, P. J., Verdonck, T., 2012. A deterministic algorithm for robust location and scatter. Journal of Computational and Graphical Statistics, 21(3), 618-637.
Ioffe, S., Szegedy, C., 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. ICML, 448-456.
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K., 2015. Spatial transformer networks. ArXiv :1506.02025.
Jolliffe, I. T., 2002. Principal Component Analysis, Springer, New York.
Jorgensen, P. E., Kang, S., Song, M. S., Tian, F., 2019. Dimension reduction and kernel principal component analysis. arXiv preprint arXiv:1906.06451.
Kotsiantis, S., 2011. Feature selection for machine learning classification problems: a recent overview. Artificial Intelligence Review, 42(1), 157-176.
Li, Y., et al., 2018. PointCNN: Convolution on x-transformed points. Advances in Neural Information Processing Systems, 31. 820-830.
Li, N., Kähler, O., Pfeifer, N., 2021. A comparison of deep learning methods for airborne lidar point clouds classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 6467-6486.
Liu, W. B., Liang, S. N., Qin, X. W., 2021. A novel dimension reduction algorithm based on weighted kernel principal analysis for gene expression data. PloS One, 16(10), e0258326.
Mika, S., Ratsch, G., Weston, J., Scholkopf, B., Mullers, K. R., 1999. Fisher discriminant analysis with kernels. Neural Networks for Signal Processing IX: Proc. of the 1999 IEEE Signal Processing Society Workshop (cat. no. 98th8468), 41-48.
Murphy, K. P., 2012. Machine Learning: A Probabilistic Perspective. MIT Press.
Niemeyer, J., Rottensteiner, F., Soergel, U., 2014. Contextual classification of lidar data and building object detection in urban areas. ISPRS J. Photogramm. Remote Sens. 87, 152-165.
Nurunnabi, A., Belton, D., West, G., 2012. Robust segmentation for multiple planar surface extraction in laser scanning 3D point cloud data. IAPR Int. Conf. on Pattern Recognition (ICPR'2012), 1367-1370.
Nurunnabi, A., West, G., Belton, D., 2013. Robust outlier detection and saliency features estimation in point cloud data. IEEE Int. Conf. on Computer and Robot Vision (CRV), 28-31 May, Regina, SK, Canada, 98-105.
Nurunnabi, A., Belton, D., West, G., 2014. Robust statistical approaches for local planar surface fitting in 3D laser scanning data. ISPRS J. of Photogramm. and Remote Sens., 96, 106-122.
Nurunnabi, A., West, G., Belton, D., 2015. Outlier detection and robust normal-curvature estimation in mobile laser scanning 3D point cloud data. Pattern Recognition. 48(4), 1404-1419.
Nurunnabi, A., Teferle, F. N., Li, J., Lindenbergh, R., Hunegnaw, A., 2021a. An efficient deep learning approach for ground point filtering in aerial laser scanning point clouds. Int. Arch. of the Photogramm. Remote Sens. and Spat. Info. Sci., Vol. XLIII-B1-2021, 31-38, XXIV-ISPRS Congress, 5-9 July.
Nurunnabi, A., Teferle, F. N., Li, J., Lindenbergh, R., Parvaz, S., 2021b. Investigation of PointNet for semantic segmentation of large-scale outdoor point clouds. Int. Arch. of the Photogramm. Remote Sens. and Spat. Info. Sci. Vol. XLVI-4/W5, 397-404.
Pauly, M., Gross, M., Kobbelt, L. P., 2002. Efficient simplification of point-sampled surfaces. IEEE Visualization, 163-170.
Qi, C. R., Su, H., Mo, K., Guibas, L. J., 2017a. PointNet : Deep learning on point sets for 3d classification and segmentation. IEEE CVPR, 652-660.
Qi, C. R., Yi, L., Su, H., Guibas, L. J., 2017b. PointNet++ : Deep hierarchical feature learning on point sets in a metric space. arXiv:1706.02413.
Reddy, G. T., et al., 2020. Analysis of dimensionality reduction techniques on big data. IEEE Access, 8: 54776-54788.
Scholkopf B, Smola A, Muller K. R., 1998. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 10(5), 1299-1319.
Sidhu, G. S., Asgarian, N., Greiner, R., Brown, M. R., 2012. Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD. Frontiers in Systems Neuroscience, 6, 74.
Su, Y., et al., 2022. DLA-Net: Learning dual local attention features for semantic segmentation of large-scale building facade point clouds. Pattern Recognition, 123, 108372.
Thomas, M., De Brabanter, K., De Moor, B., 2014. New bandwidth selection criterion for Kernel PCA: approach to dimensionality reduction and classification problems. BMC Bioinformatics, 15(1), 1-12.
Thomas, H., Goulette, F., Deschaud, J. E., Marcotegui, B., LeGall, Y., 2018. Semantic classification of 3D point clouds with multiscale spherical neighborhoods. IEEE International Conference on 3D Vision (3DV), 390-398.
Thomas, H., Qi, C. R., Deschaud, J-E., Marcotegui, B., Goulette, F., Guibas. L. J., 2019. KPConv: Flexible and deformable convolution for point clouds. IEEE ICCV, 6411-6420.
Wang, X., Paliwal, K. K., 2003. Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition. Pattern Recognition, 36(10), 2429-2439.
Wang, Y., Cang, S., Yu, H., 2019. Mutual information inspired feature selection using kernel canonical correlation analysis. Experts Systems with Applications: X, 4, 1-9.
Weinmann, M., Jutzi, B., Hinz, S., Mallet, C., 2015. Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers. ISPRS J. Photogram. Remote Sens. 105: 286-304.
Weinmann, M., Weinmann, M. 2019. Fusion of hyperspectral, multispectral, color and 3D point cloud information for the semantic interpretation of urban environments. Int. Arch. of the Photogramm. Remote Sens. and Spat. Info. Sci., Vol. XLII-2/W13, 1899-1906.
Zebari, R., Abdulazeez, A., Zeebaree, D., Zebari, D., Saeed, J., 2020. A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction. Journal of Applied Science and Technology Trends, 1(2), 56-70.
Zou, Y., Weinacker, H., Koch, B., 2021. Towards urban scene semantic segmentation with deep learning from LiDAR point clouds: A case study in Baden-Wurttemberg, Germany. Remote Sensing, 13, 3220, 1-20.
