Ground Point Filtering From Airborne Lidar Point Clouds Using Deep Learning: A Preliminary Study

Janssens-Coron, E.; Guilbert, Éric

doi:10.5194/isprs-archives-xlii-2-w13-1559-2019

Cited by 11 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of the literature suggests that the application of DL to LiDAR and digital terrain data is still limited. There has been some research relating to using DL for extracting ground returns from LiDAR point clouds for digital terrain model (DTM) generation (for example, [33,[42][43][44]). Specifically, Hu and Yuan [44] suggest that DL-based algorithms can outperform the current methods that are most commonly used for ground return classification.…”

Section: Deep Learningmentioning

confidence: 99%

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

2020

View full text Add to dashboard Cite

Modern elevation-determining remote sensing technologies such as light-detection and ranging (LiDAR) produce a wealth of topographic information that is increasingly being used in a wide range of disciplines, including archaeology and geomorphology. However, automated methods for mapping topographic features have remained a significant challenge. Deep learning (DL) mask regional-convolutional neural networks (Mask R-CNN), which provides context-based instance mapping, offers the potential to overcome many of the difficulties of previous approaches to topographic mapping. We therefore explore the application of Mask R-CNN to extract valley fill faces (VFFs), which are a product of mountaintop removal (MTR) coal mining in the Appalachian region of the eastern United States. LiDAR-derived slopeshades are provided as the only predictor variable in the model. Model generalization is evaluated by mapping multiple study sites outside the training data region. A range of assessment methods, including precision, recall, and F1 score, all based on VFF counts, as well as area- and a fuzzy area-based user’s and producer’s accuracy, indicate that the model was successful in mapping VFFs in new geographic regions, using elevation data derived from different LiDAR sensors. Precision, recall, and F1-score values were above 0.85 using VFF counts while user’s and producer’s accuracy were above 0.75 and 0.85 when using the area- and fuzzy area-based methods, respectively, when averaged across all study areas characterized with LiDAR data. Due to the limited availability of LiDAR data until relatively recently, we also assessed how well the model generalizes to terrain data created using photogrammetric methods that characterize past terrain conditions. Unfortunately, the model was not sufficiently general to allow successful mapping of VFFs using photogrammetrically-derived slopeshades, as all assessment metrics were lower than 0.60; however, this may partially be attributed to the quality of the photogrammetric data. The overall results suggest that the combination of Mask R-CNN and LiDAR has great potential for mapping anthropogenic and natural landscape features. To realize this vision, however, research on the mapping of other topographic features is needed, as well as the development of large topographic training datasets including a variety of features for calibrating and testing new methods.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

2020

View full text Add to dashboard Cite

show abstract

“…Winiwarter et al (2019) [43] investigated the applicability of PointNet++ for not only benchmark data, but also actual airborne lidar point clouds. Additionally, a task-specific deep learning method for the extraction of ground information [44,45], and a tree species classification network were proposed [46].…”

Section: Deep Learinigmentioning

confidence: 99%

FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning

Shinohara

Xiu

Matsuoka

2020

Sensors

View full text Add to dashboard Cite

In the computer vision field, many 3D deep learning models that directly manage 3D point clouds (proposed after PointNet) have been published. Moreover, deep learning-based-techniques have demonstrated state-of-the-art performance for supervised learning tasks on 3D point cloud data, such as classification and segmentation tasks for open datasets in competitions. Furthermore, many researchers have attempted to apply these deep learning-based techniques to 3D point clouds observed by aerial laser scanners (ALSs). However, most of these studies were developed for 3D point clouds without radiometric information. In this paper, we investigate the possibility of using a deep learning method to solve the semantic segmentation task of airborne full-waveform light detection and ranging (lidar) data that consists of geometric information and radiometric waveform data. Thus, we propose a data-driven semantic segmentation model called the full-waveform network (FWNet), which handles the waveform of full-waveform lidar data without any conversion process, such as projection onto a 2D grid or calculating handcrafted features. Our FWNet is based on a PointNet-based architecture, which can extract the local and global features of each input waveform data, along with its corresponding geographical coordinates. Subsequently, the classifier consists of 1D convolutional operational layers, which predict the class vector corresponding to the input waveform from the extracted local and global features. Our trained FWNet achieved higher scores in its recall, precision, and F1 score for unseen test data—higher scores than those of previously proposed methods in full-waveform lidar data analysis domain. Specifically, our FWNet achieved a mean recall of 0.73, a mean precision of 0.81, and a mean F1 score of 0.76. We further performed an ablation study, that is assessing the effectiveness of our proposed method, of the above-mentioned metric. Moreover, we investigated the effectiveness of our PointNet based local and global feature extraction method using the visualization of the feature vector. In this way, we have shown that our network for local and global feature extraction allows training with semantic segmentation without requiring expert knowledge on full-waveform lidar data or translation into 2D images or voxels.

show abstract

“…In recent years, the researchers have developed more advanced ground filtering approaches based on cloth simulation, 20 image segmentation, 21 interpolation, 22 progressive TIN densification, 23 empirical mode decomposition, 24 segment‐based filtering and multi‐scale morphological filtering, 25 voxelization, 26 geodesic transformations of mathematical morphology, 27 scanline density analysis, 28 deep learning, 29 morphological filtering, 30 expectation–maximization, 31 and so on.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the performances of advanced image classification‐based ground filtering approaches for digital terrain model generation

Yılmaz

2021

Concurrency and Computation

View full text Add to dashboard Cite

The majority of the ground filtering techniques proposed so far use several user‐defined parameter values. Since no standard protocols exist to define these parameters, obtaining the optimum filtering performance is very hard, especially in large‐extent areas with abrupt topography changes. This, of course, reveals the necessity of some more efficient strategies to ease the ground filtering process in such areas. Utilizing classified images for ground filtering purpose may be of help to achieve this. Hence, this study, for the first time in the literature, investigated the performances of the state‐of‐the‐art machine learning algorithms maximum likelihood (ML), artificial neural network (ANN), support vector machines (SVM), and random forest (RF) in ground filtering of a UAS‐based point cloud. The used approaches were based on the assignment of the points corresponding to the ground‐related classes to the ground class. Evaluations showed that the SVM‐based ground filtering approach achieved the optimum filtering result. The SVM‐, ML‐, RF‐, and ANN‐based ground filtering methods achieved the total errors of 13.2%, 16.4%, 19.6%, and 21.9% in the test site, respectively.

show abstract

Ground Point Filtering From Airborne Lidar Point Clouds Using Deep Learning: A Preliminary Study

Cited by 11 publications

References 14 publications

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning

Investigation of the performances of advanced image classification‐based ground filtering approaches for digital terrain model generation

Contact Info

Product

Resources

About