TY - JOUR
T1 - A TWO-STEP FEATURE EXTRACTION ALGORITHM
T2 - 9th International Workshop on 3D Virtual Reconstruction and Visualization of Complex Architectures, 3D-ARCH 2022
AU - Nurunnabi, A.
AU - Teferle, F. N.
AU - Laefer, D. F.
AU - Lindenbergh, R. C.
AU - Hunegnaw, A.
N1 - Funding Information:
This study is with the Project 2019-05-030-24, SOLSTICE - Programme Fonds Européen de Developpment Régional (FEDER)/Ministère de l’Economie of the G. D. of Luxembourg. Additional assistance was provided through the National Science Foundation award 1940145.
Publisher Copyright:
© 2022 Author(s).
PY - 2022/2/25
Y1 - 2022/2/25
N2 - 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.
AB - 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.
KW - Dimension Reduction
KW - Feature Selection
KW - LiDAR
KW - Machine Learning
KW - Neural Network
KW - PCA
KW - Semantic Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85126395689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126395689&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLVI-2-W1-2022-401-2022
DO - 10.5194/isprs-archives-XLVI-2-W1-2022-401-2022
M3 - Conference article
AN - SCOPUS:85126395689
SN - 1682-1750
VL - 46
SP - 401
EP - 408
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
IS - 2/W1-2022
Y2 - 2 March 2022 through 4 March 2022
ER -