A Boundary-Enhanced Supervoxel Method for Extraction of Road Edges in MLS Point Clouds

Sha, Zhengchuan; Chen, Y.; Li, W.; Wang, Cheng; Nurunnabi, Abdul; Li, J.

doi:10.5194/isprs-archives-xliii-b1-2020-65-2020

Cited by 4 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And it is the pioneering over-segmentation method based on clustering. VCCS-knn method (Sha et al, 2020) improves the neighboring searching methods on the basis of VCCS, which better ensured that the super points obtained by segmentation would not destroy the boundaries between real objects. PCLV method (Ben-Shabat et al, 2018) extends the graph cut problem in 2D images to point cloud data, and realizes the over-segmentation of point clouds.…”

Section: Point Cloud Oversegmentationmentioning

confidence: 99%

Spdc: A Super-Point and Point Combining Based Dual-Scale Contrastive Learning Network for Point Cloud Semantic Segmentation

Chen

Zhang

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Semantic segmentation of point clouds is one of the fundamental tasks of point cloud processing and is the basis for other downstream tasks. Deep learning has become the main method to solve point cloud processing. Most existing 3D deep learning models require large amounts of point cloud data to drive them, but annotating the data requires significant time and economic costs. To address the problem of semantic segmentation requiring large amounts of annotated data for training, this paper proposes a Super-point-level and Point-level Dual-scale Contrast learning network (SPDC). To solve the problem that contrastive learning is difficult to train and feature extraction is not sufficient, we introduce super-point maps to assist the network in feature extraction. We use a pre-trained super-point generation network to convert the original point cloud into a super-point map. A dynamic data augmentation(DDA) module is designed for the super-point maps for super-point-level contrastive learning. We map the extracted super-point-level features back to the original point-level scale and conduct secondary contrastive learning with the original point features. The whole feature extraction network is parameter sharing and to reduce the number of parameters we used the lightweight network DGCNN (encoder)+Self-attention as the backbone network. And we did a few-shot pre-training of the backbone network to make the network converge easily. Analogous to CutMix, we designed a new method for point cloud data augmentation called PointObjectMix (POM). This method solves the sample imbalance problem while preserving the overall characteristics of the objects in the scene. We conducted experiments on the S3DIS dataset and obtained 63.3% mIoU. We have also done a large number of ablation experiments to verify the effectiveness of the modules in our method. Experimental results show that our method outperforms the best-unsupervised network available.

show abstract

Section: Point Cloud Oversegmentationmentioning

confidence: 99%

Spdc: A Super-Point and Point Combining Based Dual-Scale Contrastive Learning Network for Point Cloud Semantic Segmentation

Chen

Zhang

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Supervoxels were applied in a convolution operation (SVConv) by Huang, Ma et al to effectively accomplish online 3D semantic segmentation [16]. In Sha, Chen et al's work, road contours were extracted efficiently and based completely on a supervoxel method without any trajectory data [17]. The Euclidean clustering algorithm was optimized by supervoxels to improve the anti-noise ability of the clustering process by Chen et al [18].…”

Section: Introductionmentioning

confidence: 99%

An Improved Supervoxel Clustering Algorithm of 3D Point Clouds for the Localization of Industrial Robots

Xie

Liang²,

Tao

et al. 2022

Electronics

View full text Add to dashboard Cite

Supervoxels have a widespread application of instance segmentation on account of the merit of providing a highly approximate representation with fewer data. However, low accuracy, mainly caused by point cloud adhesion in the localization of industrial robots, is a crucial issue. An improved bottom-up clustering method based on supervoxels was proposed for better accuracy. Firstly, point cloud data were preprocessed to eliminate the noise points and background. Then, improved supervoxel over-segmentation with moving least squares (MLS) surface fitting was employed to segment the point clouds of workpieces into supervoxel clusters. Every supervoxel cluster can be refined by MLS surface fitting, which reduces the occurrence that over-segmentation divides the point clouds of two objects into a patch. Additionally, an adaptive merging algorithm based on fusion features and convexity judgment was proposed to accomplish the clustering of the individual workpiece. An experimental platform was set up to verify the proposed method. The experimental results showed that the recognition accuracy and the recognition rate in three different kinds of workpieces were all over 0.980 and 0.935, respectively. Combined with the sample consensus initial alignment (SAC-IA) coarse registration and iterative closest point (ICP) fine registration, the coarse-to-fine strategy was adopted to obtain the location of the segmented workpieces in the experiments. The experimental results demonstrate that the proposed clustering algorithm can accomplish the localization of industrial robots with higher accuracy and lower registration time.

show abstract

Extraction of road boundary from MLS data using laser scanner ground trajectory

et al. 2021

View full text Add to dashboard Cite

Various means of extracting road boundary from mobile laser scanning data based on vehicle trajectories have been investigated. Independent of positioning and navigation data, this study estimated the scanner ground track from the spatial distribution of the point cloud as an indicator of road location. We defined a typical edge block consisting of multiple continuous upward fluctuating points by abrupt changes in elevation, upward slope, and road horizontal slope. Subsequently, such edge blocks were searched for on both sides of the estimated track. A pseudo-mileage spacing map was constructed to reflect the variation in spacing between the track and edge blocks over distance, within which road boundary points were detected using a simple linear tracking model. Experimental results demonstrate that the ground trajectory of the extracted scanner forms a smooth and continuous string just on the road; this can serve as the basis for defining edge block and road boundary tracking algorithms. The defined edge block has been experimentally verified as highly accurate and strongly noise resistant, while the boundary tracking algorithm is simple, fast, and independent of the road boundary model used. The correct detection rate of the road boundary in two experimental data is more than 99.2%.

show abstract

A Boundary-Enhanced Supervoxel Method for Extraction of Road Edges in MLS Point Clouds

Cited by 4 publications

References 27 publications

Spdc: A Super-Point and Point Combining Based Dual-Scale Contrastive Learning Network for Point Cloud Semantic Segmentation

Spdc: A Super-Point and Point Combining Based Dual-Scale Contrastive Learning Network for Point Cloud Semantic Segmentation

An Improved Supervoxel Clustering Algorithm of 3D Point Clouds for the Localization of Industrial Robots

Extraction of road boundary from MLS data using laser scanner ground trajectory

Contact Info

Product

Resources

About