FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY

We describe an effective and efficient method for point-wise semantic classification of 3D point clouds. The method can handle unstructured and inhomogeneous point clouds such as those derived from static terrestrial LiDAR or photogammetric reconstruction; and it is computationally efficient, making it possible to process point clouds with many millions of points in a matter of minutes. The key issue, both to cope with strong variations in point density and to bring down computation time, turns out to be careful handling of neighborhood relations. By choosing appropriate definitions of a point’s (multi-scale) neighborhood, we obtain a feature set that is both expressive and fast to compute. We evaluate our classification method both on benchmark data from a mobile mapping platform and on a variety of large, terrestrial laser scans with greatly varying point density. The proposed feature set outperforms the state of the art with respect to per-point classification accuracy, while at the same time being much faster to compute.

Download Full-text

An Inverse Node Graph-Based Method for the Urban Scene Segmentation of 3D Point Clouds

Remote Sensing ◽

10.3390/rs13153021 ◽

2021 ◽

Vol 13 (15) ◽

pp. 3021

Author(s):

Bufan Zhao ◽

Xianghong Hua ◽

Kegen Yu ◽

Xiaoxing He ◽

Weixing Xue ◽

...

Keyword(s):

Semantic Segmentation ◽

Point Clouds ◽

Intelligent Vehicles ◽

Critical Data ◽

Multi Scale ◽

3D Point Clouds ◽

Cluster Optimization ◽

Urban Scene ◽

Processing Steps

Urban object segmentation and classification tasks are critical data processing steps in scene understanding, intelligent vehicles and 3D high-precision maps. Semantic segmentation of 3D point clouds is the foundational step in object recognition. To identify the intersecting objects and improve the accuracy of classification, this paper proposes a segment-based classification method for 3D point clouds. This method firstly divides points into multi-scale supervoxels and groups them by proposed inverse node graph (IN-Graph) construction, which does not need to define prior information about the node, it divides supervoxels by judging the connection state of edges between them. This method reaches minimum global energy by graph cutting, obtains the structural segments as completely as possible, and retains boundaries at the same time. Then, the random forest classifier is utilized for supervised classification. To deal with the mislabeling of scattered fragments, higher-order CRF with small-label cluster optimization is proposed to refine the classification results. Experiments were carried out on mobile laser scan (MLS) point dataset and terrestrial laser scan (TLS) points dataset, and the results show that overall accuracies of 97.57% and 96.39% were obtained in the two datasets. The boundaries of objects were retained well, and the method achieved a good result in the classification of cars and motorcycles. More experimental analyses have verified the advantages of the proposed method and proved the practicability and versatility of the method.

Download Full-text

MULTI-SCALE BASED EXTRACION OF VEGETATION FROM TERRESTRIAL LiDAR DATA FOR ASSESSING LOCAL LANDSCAPE

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsannals-ii-3-w4-263-2015 ◽

2015 ◽

Vol II-3/W4 ◽

pp. 263-270 ◽

Cited By ~ 4

Author(s):

T. Wakita ◽

J. Susaki

Keyword(s):

Urban Areas ◽

Three Dimensional ◽

Point Clouds ◽

Lidar Data ◽

Data Sets ◽

Landscape Index ◽

Terrestrial Lidar ◽

Multi Scale ◽

3D Point Clouds ◽

Set Of Points

In this study, we propose a method to accurately extract vegetation from terrestrial three-dimensional (3D) point clouds for estimating landscape index in urban areas. Extraction of vegetation in urban areas is challenging because the light returned by vegetation does not show as clear patterns as man-made objects and because urban areas may have various objects to discriminate vegetation from. The proposed method takes a multi-scale voxel approach to effectively extract different types of vegetation in complex urban areas. With two different voxel sizes, a process is repeated that calculates the eigenvalues of the planar surface using a set of points, classifies voxels using the approximate curvature of the voxel of interest derived from the eigenvalues, and examines the connectivity of the valid voxels. We applied the proposed method to two data sets measured in a residential area in Kyoto, Japan. The validation results were acceptable, with F-measures of approximately 95% and 92%. It was also demonstrated that several types of vegetation were successfully extracted by the proposed method whereas the occluded vegetation were omitted. We conclude that the proposed method is suitable for extracting vegetation in urban areas from terrestrial light detection and ranging (LiDAR) data. In future, the proposed method will be applied to mobile LiDAR data and the performance of the method against lower density of point clouds will be examined.

Download Full-text

A Multi-scale Network for Semantic Segmentation of 3D Point Clouds

2020 Chinese Automation Congress (CAC) ◽

10.1109/cac51589.2020.9327290 ◽

2020 ◽

Author(s):

Ying He ◽

Li Xiao ◽

Yong Jiang ◽

Zhigang Sun ◽

Zhuo Wang ◽

...

Keyword(s):

Semantic Segmentation ◽

Point Clouds ◽

Multi Scale ◽

3D Point Clouds ◽

Scale Network

Download Full-text

Multi-scale Information Extraction Residual Network for 3D Point Clouds Classification

2020 Chinese Automation Congress (CAC) ◽

10.1109/cac51589.2020.9327126 ◽

2020 ◽

Author(s):

Yumei Li ◽

Shan Meng ◽

Daoyuan Liang

Keyword(s):

Information Extraction ◽

Point Clouds ◽

Residual Network ◽

Multi Scale ◽

3D Point Clouds

Download Full-text

Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds

2018 International Conference on 3D Vision (3DV) ◽

10.1109/3dv.2018.00053 ◽

2018 ◽

Cited By ~ 15

Author(s):

Chris Zhang ◽

Wenjie Luo ◽

Raquel Urtasun

Keyword(s):

Real Time ◽

Semantic Segmentation ◽

Point Clouds ◽

3D Point Clouds

Download Full-text

SEMANTIC LABELLING OF ULTRA DENSE MLS POINT CLOUDS IN URBAN ROAD CORRIDORS BASED ON FUSING CRF WITH SHAPE PRIORS

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w7-971-2017 ◽

2017 ◽

Vol XLII-2/W7 ◽

pp. 971-976 ◽

Cited By ~ 2

Author(s):

W. Yao ◽

P. Polewski ◽

P. Krzystek

Keyword(s):

Semantic Analysis ◽

Sampling Rate ◽

Point Clouds ◽

Shape Priors ◽

High Point ◽

Urban Road ◽

3D Point Clouds ◽

Point Density ◽

Object Classes ◽

Road Corridors

In this paper, a labelling method for the semantic analysis of ultra-high point density MLS data (up to 4000 points/m<sup>2</sup>) in urban road corridors is developed based on combining a conditional random field (CRF) for the context-based classification of 3D point clouds with shape priors. The CRF uses a Random Forest (RF) for generating the unary potentials of nodes and a variant of the contrastsensitive Potts model for the pair-wise potentials of node edges. The foundations of the classification are various geometric features derived by means of co-variance matrices and local accumulation map of spatial coordinates based on local neighbourhoods. Meanwhile, in order to cope with the ultra-high point density, a plane-based region growing method combined with a rule-based classifier is applied to first fix semantic labels for man-made objects. Once such kind of points that usually account for majority of entire data amount are pre-labeled; the CRF classifier can be solved by optimizing the discriminative probability for nodes within a subgraph structure excluded from pre-labeled nodes. The process can be viewed as an evidence fusion step inferring a degree of belief for point labelling from different sources. The MLS data used for this study were acquired by vehicle-borne Z+F phase-based laser scanner measurement, which permits the generation of a point cloud with an ultra-high sampling rate and accuracy. The test sites are parts of Munich City which is assumed to consist of seven object classes including impervious surfaces, tree, building roof/facade, low vegetation, vehicle and pole. The competitive classification performance can be explained by the diverse factors: e.g. the above ground height highlights the vertical dimension of houses, trees even cars, but also attributed to decision-level fusion of graph-based contextual classification approach with shape priors. The use of context-based classification methods mainly contributed to smoothing of labelling by removing outliers and the improvement in underrepresented object classes. In addition, the routine operation of a context-based classification for such high density MLS data becomes much more efficient being comparable to non-contextual classification schemes.

Download Full-text

HYBRID ACQUISITION OF HIGH QUALITY TRAINING DATA FOR SEMANTIC SEGMENTATION OF 3D POINT CLOUDS USING CROWD-BASED ACTIVE LEARNING

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-501-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 501-508

Author(s):

M. Kölle ◽

V. Walter ◽

S. Schmohl ◽

U. Soergel

Keyword(s):

Active Learning ◽

Semantic Segmentation ◽

Point Clouds ◽

Human Interaction ◽

Training Data ◽

Semantic Interpretation ◽

Training Dataset ◽

3D Point Clouds ◽

Semantic Labeling ◽

3D Cnn

Abstract. Automated semantic interpretation of 3D point clouds is crucial for many tasks in the domain of geospatial data analysis. For this purpose, labeled training data is required, which has often to be provided manually by experts. One approach to minimize effort in terms of costs of human interaction is Active Learning (AL). The aim is to process only the subset of an unlabeled dataset that is particularly helpful with respect to class separation. Here a machine identifies informative instances which are then labeled by humans, thereby increasing the performance of the machine. In order to completely avoid involvement of an expert, this time-consuming annotation can be resolved via crowdsourcing. Therefore, we propose an approach combining AL with paid crowdsourcing. Although incorporating human interaction, our method can run fully automatically, so that only an unlabeled dataset and a fixed financial budget for the payment of the crowdworkers need to be provided. We conduct multiple iteration steps of the AL process on the ISPRS Vaihingen 3D Semantic Labeling benchmark dataset (V3D) and especially evaluate the performance of the crowd when labeling 3D points. We prove our concept by using labels derived from our crowd-based AL method for classifying the test dataset. The analysis outlines that by labeling only 0:4% of the training dataset by the crowd and spending less than 145 $, both our trained Random Forest and sparse 3D CNN classifier differ in Overall Accuracy by less than 3 percentage points compared to the same classifiers trained on the complete V3D training set.

Download Full-text