Rasterization strategies for airborne LiDAR classification using attribute profiles

IEEE Geosci. Remote Sensing Lett.

Pham

Dambreville

et al. 2020

Self Cite

LiDAR point clouds are receiving a growing interest in remote sensing as they provide rich information to be used independently or together with optical data sources such as aerial imagery. However, their non-structured and sparse nature make them difficult to handle, conversely to raw imagery for which many efficient tools are available. To overcome this specific nature of LiDAR point clouds, standard approaches often rely in converting the point cloud into a digital elevation model, represented as a 2D raster. Such a raster can then be used similarly as optical images, e.g. with 2D convolutional neural networks for semantic segmentation. In this letter, we show that LiDAR point clouds provide more information than only the DEM, and that considering alternative rasterization strategies helps to achieve better semantic segmentation results. We illustrate our findings on the IEEE DFC 2018 dataset.

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Segmentation of LiDAR Points Clouds: Rasterization Beyond Digital Elevation Models

IEEE Geosci. Remote Sensing Lett.

Pham

Dambreville

et al. 2020

Self Cite

“…The usual approach remains to first rasterize the point cloud to obtain a digital image (also called a raster of pixels) on which standard morphological operators are applied [18]. This strategy was also recently followed for morphological hierarchies on LiDAR point clouds [8].…”

Section: Introductionmentioning

confidence: 99%

Attribute Filtering of Urban Point Clouds Using Max-Tree on Voxel Data

Lecture Notes in Computer Science

Lefèvre

Corpetti

2019

Self Cite

This paper deals with morphological characterization of unstructured 3D point clouds issued from LiDAR data. A large majority of studies first rasterize 3D point clouds onto regular 2D grids and then use standard 2D image processing tools for characterizing data. In this paper, we suggest instead to keep the 3D structure as long as possible in the process. To this end, as raw LiDAR point clouds are unstructured, we first propose some voxelization strategies and then extract some morphological features on voxel data. The results obtained with attribute filtering show the ability of this process to efficiently extract useful information.

“…For example authors of [1] perform the segmentation and classification of urban point clouds with mathematical morphology after a projection of raw data on digital elevation model (DEM), and then re-project the results on point clouds. The same idea is used in [2] where a series of attribute profiles are computed on 2D grids containing various information related extracted during the mapping from 3D to 2D (number of points in a cell, first echo, last echo, . .…”

Section: Introductionmentioning

confidence: 99%

Voxel-Based Attribute Profiles on LIDAR Data for Land Cover Mapping

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

Lefèvre

Corpetti

2019

Self Cite

This paper deals with strategies for LiDAR data analysis. While a large majority of studies first rasterize 3D point clouds onto regular 2D grids and then use 2D image processing tools for characterizing data, our work rather suggests to keep as long as possible the 3D structure by computing features on 3D data and rasterize later in the process. By this way, the vertical component is still taken into account. In practice, a voxelization step of raw data is performed in order to exploit mathematical tools defined on regular volumes. More precisely, we focus on attribute profiles that have been shown to be very efficient features to characterize remote sensing scenes. They require the computation of an underlying hierarchical structure (through a Max-Tree). Experimental results obtained on urban LiDAR data classification support the performances of this strategy compared with an early rasterization process.