Semantic Labeling of ALS Point Cloud via Learning Voxel and Pixel Representations

Qin, Nannan; Hu, Xiangyun; Wang, Puzuo; Shan, Jie; Li, Yijing

doi:10.1109/lgrs.2019.2931119

Cited by 20 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, on other classic benchmark datasets-for example, the Vaihingen dataset-the methods utilizing a hierarchical or multi-scale strategy also show promising performance. We have collected and compared the results of classification methods including LUH [35], PointNet++ [34], multi-scale convolutional neural network (MCNN) [36], rectified linear units neural network (ReLu-NN) [37], PointNet on multiple scales (PointNet-MS) [38]deep point embedding (DPE) [13], geometry-attentional network (GA-Conv) [39], and voxel and pixel representation-based networks (VPNet) [40], and we can see that for methods that work directly on 3D points, those (e.g., LUH, DPE, and GA-Conv) utilizing a hierarchical or multi-scale strategy show noteworthy performance. For example, the GA-Conv method proposed a dense hierarchical architecture and elevation-attention module and achieves a promising result.…”

Section: Classification Results Of Lasdu Dataset Using Additional Poi...mentioning

confidence: 99%

LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas

Huang

et al. 2020

IJGI

View full text Add to dashboard Cite

The semantic labeling of the urban area is an essential but challenging task for a wide variety of applications such as mapping, navigation, and monitoring. The rapid advance in Light Detection and Ranging (LiDAR) systems provides this task with a possible solution using 3D pointclouds, which are accessible, affordable, accurate, and applicable. Among all types of platforms, the airborne platform with LiDAR can serve as an efficient and effective tool for large-scale 3D mapping in the urban area. Against this background, a large number of algorithms and methods have been developed to fully explore the potential of 3D point clouds. However, the creation ofpublicly accessible large-scale annotated datasets, which are critical for assessing the performance of the developed algorithms and methods, is still at an early age. In this work, we present a large-scale aerial LiDAR point cloud dataset acquired in a highly-dense and complex urban area for the evaluation of semantic labeling methods. This dataset covers an urban area with highly-dense buildings of approximately 1 km2 and includes more than 3 million points with five classes of objects labeled. Moreover, experiments are carried out with the results from several baseline methods, demonstrating the feasibility and capability of the dataset serving as a benchmark for assessing semantic labeling methods.

show abstract

Section: Classification Results Of Lasdu Dataset Using Additional Poi...mentioning

confidence: 99%

LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas

Huang

et al. 2020

IJGI

View full text Add to dashboard Cite

show abstract

“…Voxel structures can also combine with pixels. For example, in Qin et al (2019), both voxels and pixels were used as inputs in the proposed VPNet for semantic labeling of ALS data. The generation of voxels provided contextual information from the local area.…”

Section: Voxel-based Methodsmentioning

confidence: 99%

GraNet: Global Relation-aware Attentional Network for ALS Point Cloud Classification

Huang,

Xu,

Stilla

2020

Preprint

View full text Add to dashboard Cite

Semantic labeling is an essential but challenging task when interpreting point clouds of 3D scenes. As a core step for interpretation, semantic labeling is to annotate every point in the point cloud with a label of semantic meaning, which plays a significant role in many point cloud related applications. Especially for airborne laser scanning (ALS) point clouds, precise annotations can considerably broaden its use in various applications. However, accurate and efficient semantic labeling is still a challenging task, due to the sensor noise, complex object structures, incomplete points, and uneven point densities. In this work, we propose a novel neural network focusing on semantic labeling of ALS point clouds, which investigates the importance of long-range spatial and channelwise relations and is termed as global relation-aware attentional network (GraNet). GraNet first learns local geometric description and local dependencies using a local spatial discrepancy attention convolution module (LoSDA). In LoSDA, the orientation information, spatial distribution, and elevation differences are fully considered by stacking several local spatial geometric learning modules and the local dependencies are embedded by using an attention pooling module. Then, a global relation-aware attention module (GRA), consisting of a spatial relation-aware attention module (SRA) and a channel relation aware attention module (CRA), are investigated to further learn the global spatial and channel-wise relationship between any spatial positions and feature vectors. The aforementioned two important modules are embedded in the multi-scale network architecture to further consider scale changes in large urban areas. We conducted comprehensive experiments on two ALS point cloud datasets to evaluate the performance of our proposed framework. The results show that our method can achieve higher classification accuracy compared with other commonly used advanced classification methods. The overall accuracy (OA) of our method on the ISPRS benchmark dataset can be improved to 84.5 % to classify nine semantic classes, with an average F 1 measure (AvgF 1 ) of 73.5 %, which outperforms other strategies. Besides, experiments were conducted using a new ALS point cloud dataset covering highly dense urban areas.

show abstract

“…Subsequently, prior knowledge or supervised methods are employed to label segments rather than individual points. In [23] DL approaches on the semantic segmentation of point cloud can be classified into 3 categories: projection-based [30,31], voxel-based [32][33][34], and point-based. Now, the point-based networks have established as mainstream method for point cloud semantic segmentation.…”

Section: Related Workmentioning

confidence: 99%

MP-DGCNN for the Semantic Segmentation of Chinese Ancient Building Point Clouds

Dong,

Hou,

Zhou

et al. 2024

Preprint

View full text Add to dashboard Cite

Point cloud semantic segmentation is a key step in the scan-to-HBIM process. In order to reduce the information in the process of DGCNN, this paper proposes a Mix Pooling Dynamic Graph Convolutional Neural Network (MP-DGCNN) for the segmentation of ancient architecture point clouds. The proposed MP-DGCNN differs from DGCNN mainly in two aspects: (1) to more comprehensively characterize the local topological structure of points, the edge features are redefined, and distance and neighboring points are added to the original edge features; (2) based on a Multilayer Perceptron (MLP), an internal feature adjustment mechanism is established, and a learnable mix pooling operator is designed by fusing adaptive pooling, max pooling, average pooling, and aggregation pooling, to learn local graph features from the point cloud topology. To verify the proposed algorithm, experiments are conducted on the Qutan Temple point cloud dataset, and the results show that compared with PointNet, PointNet++, DGCNN, and LDGCNN, the MP-DGCNN segmentation network achieves the highest OA and mIOU, reaching 90.19% and 65.34%, respectively.

show abstract

Semantic Labeling of ALS Point Cloud via Learning Voxel and Pixel Representations

Cited by 20 publications

References 17 publications

LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas

LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas

GraNet: Global Relation-aware Attentional Network for ALS Point Cloud Classification

MP-DGCNN for the Semantic Segmentation of Chinese Ancient Building Point Clouds

Contact Info

Product

Resources

About