FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS
Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2018-05-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2/231/2018/isprs-annals-IV-2-231-2018.pdf |
| _version_ | 1828377489529896960 |
|---|---|
| author | A. Rizaldy C. Persello C. M. Gevaert S. J. Oude Elberink |
| author_facet | A. Rizaldy C. Persello C. M. Gevaert S. J. Oude Elberink |
| author_sort | A. Rizaldy |
| collection | DOAJ |
| description | Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error. |
| first_indexed | 2024-04-14T08:13:27Z |
| format | Article |
| id | doaj.art-19e59c879f2f4ae8a1769764d3dacd40 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-04-14T08:13:27Z |
| publishDate | 2018-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-19e59c879f2f4ae8a1769764d3dacd402022-12-22T02:04:28ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502018-05-01IV-223123810.5194/isprs-annals-IV-2-231-2018FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDSA. Rizaldy0C. Persello1C. M. Gevaert2S. J. Oude Elberink3ITC, Faculty of Geo-Information Science and Earth Observation, University of Twente, the NetherlandsITC, Faculty of Geo-Information Science and Earth Observation, University of Twente, the NetherlandsITC, Faculty of Geo-Information Science and Earth Observation, University of Twente, the NetherlandsITC, Faculty of Geo-Information Science and Earth Observation, University of Twente, the NetherlandsDeep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2/231/2018/isprs-annals-IV-2-231-2018.pdf |
| spellingShingle | A. Rizaldy C. Persello C. M. Gevaert S. J. Oude Elberink FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS |
| title_full | FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS |
| title_fullStr | FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS |
| title_full_unstemmed | FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS |
| title_short | FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS |
| title_sort | fully convolutional networks for ground classification from lidar point clouds |
| url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2/231/2018/isprs-annals-IV-2-231-2018.pdf |
| work_keys_str_mv | AT arizaldy fullyconvolutionalnetworksforgroundclassificationfromlidarpointclouds AT cpersello fullyconvolutionalnetworksforgroundclassificationfromlidarpointclouds AT cmgevaert fullyconvolutionalnetworksforgroundclassificationfromlidarpointclouds AT sjoudeelberink fullyconvolutionalnetworksforgroundclassificationfromlidarpointclouds |