TY - JOUR
T1 - Classification of airborne laser scanning point cloud using point-based convolutional neural network
AU - Zhu, Jianfeng
AU - Sui, Lichun
AU - Zang, Yufu
AU - Zheng, He
AU - Jiang, Wei
AU - Zhong, Mianqing
AU - Ma, Fei
PY - 2021
Y1 - 2021
N2 - In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.
AB - In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.
KW - Airborne laser scanning
KW - Convolutional neural network
KW - Deep learning
KW - Point cloud classification
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85109405498&partnerID=8YFLogxK
U2 - 10.3390/ijgi10070444
DO - 10.3390/ijgi10070444
M3 - Article
AN - SCOPUS:85109405498
SN - 2220-9964
VL - 10
JO - ISPRS International Journal of Geo-Information
JF - ISPRS International Journal of Geo-Information
IS - 7
M1 - 444
ER -