KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation

Luo, Nan; Yu, Haiming; Huo, Zhenfeng; Liu, Jinhui; Wang, Quan; Xu, Ying; Gao, Yun

doi:10.3390/rs13051003

Cited by 10 publications

(7 citation statements)

References 34 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results are shown in Table 3. The proposed model has more prominent improvement, and the OAcc of the FGCN is 4.18% higher than that of the KVGCN [33], which is a graph convolution network with better experimental results. The OAcc of the FGCN is 9.38% higher than that of PointNet++ [16], which is a stable CNN network, and 1.38% higher than that of Point Transformer [34], which is a relatively new network.…”

Section: Resultsmentioning

confidence: 93%

See 1 more Smart Citation

FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network

Zhang,

Chen,

Peng

et al. 2023

Sensors

View full text Add to dashboard Cite

In interpreting a scene for numerous applications, including autonomous driving and robotic navigation, semantic segmentation is crucial. Compared to single-modal data, multi-modal data allow us to extract a richer set of features, which is the benefit of improving segmentation accuracy and effect. We propose a point cloud semantic segmentation method, and a fusion graph convolutional network (FGCN) which extracts the semantic information of each point involved in the two-modal data of images and point clouds. The two-channel k-nearest neighbors (KNN) module of the FGCN was created to address the issue of the feature extraction’s poor efficiency by utilizing picture data. Notably, the FGCN utilizes the spatial attention mechanism to better distinguish more important features and fuses multi-scale features to enhance the generalization capability of the network and increase the accuracy of the semantic segmentation. In the experiment, a self-made semantic segmentation KITTI (SSKIT) dataset was made for the fusion effect. The mean intersection over union (MIoU) of the SSKIT can reach 88.06%. As well as the public datasets, the S3DIS showed that our method can enhance data features and outperform other methods: the MIoU of the S3DIS can reach up to 78.55%. The segmentation accuracy is significantly improved compared with the existing methods, which verifies the effectiveness of the improved algorithms.

show abstract

Section: Resultsmentioning

confidence: 93%

“…The term NoRGB means that the R, G, and B columns of the fused data are hidden. The experiments were conducted using the S3DIS dataset and compared with the 3D point cloud semantic segmentation network models of PointNet++ [16], KVGCN [33], and Point Transformer [34]. The experimental results are shown in Table 3.…”

Section: Resultsmentioning

confidence: 99%

FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network

Zhang,

Chen,

Peng

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…However, this method only optimizes the feature encoding of the downsampling layer and does not consider the promoting effect of the self-attention mechanisms in deep learning, resulting in an OA and MIoU of only 86.8% and 66.8%. KVGCN [25] aggregated local-global context features to achieve a higher OA (87.4%) than GCN. However, it overlooks the impact of minority class features on MIoU (60.9%).…”

Section: Six-fold Cross-validationmentioning

confidence: 99%

“…The challenge of obtaining such networks lies in how to construct appropriate point-to-point relationships and the advantages lie in their ability to aggregate target structural features while maintaining translation invariance in a three-dimensional space. Representative works in this category include KVGCN [25], GCN-MLP [26], RG-GCN [27], DDGCN [28], and PointCCR [29]. Some researchers attempt to learn fine-grained point cloud features by introducing self-attention mechanisms in networks.…”

Section: Introductionmentioning

confidence: 99%

PointMM: Point Cloud Semantic Segmentation CNN under Multi-Spatial Feature Encoding and Multi-Head Attention Pooling

Chen,

Wu,

Luo

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

For the actual collected point cloud data, there are widespread challenges such as semantic inconsistency, density variations, and sparse spatial distribution. A network called PointMM is developed in this study to enhance the accuracy of point cloud semantic segmentation in complex scenes. The main contribution of PointMM involves two aspects: (1) Multi-spatial feature encoding. We leverage a novel feature encoding module to learn multi-spatial features from the neighborhood point set obtained by k-nearest neighbors (KNN) in the feature space. This enhances the network’s ability to learn the spatial structures of various samples more finely and completely. (2) Multi-head attention pooling. We leverage a multi-head attention pooling module to address the limitations of symmetric function-based pooling, such as maximum and average pooling, in terms of losing detailed feature information. This is achieved by aggregating multi-spatial and attribute features of point clouds, thereby enhancing the network’s ability to transmit information more comprehensively and accurately. Experiments on publicly available point cloud datasets S3DIS and ISPRS 3D Vaihingen demonstrate that PointMM effectively learns features at different levels, while improving the semantic segmentation accuracy of various objects. Compared to 12 state-of-the-art methods reported in the literature, PointMM outperforms the runner-up by 2.3% in OA on the ISPRS 3D Vaihingen dataset, and achieves the third best performance in both OA and MioU on the S3DIS dataset. Both achieve a satisfactory balance between OA, F1, and MioU.

show abstract

“…Since the semantic understanding and analysis of a 3D point cloud is the basis for realizing scene understanding [1,2], the application of semantic segmentation of 3D point cloud has been more and more extensive in recent years [3][4][5], such as augmented/virtual reality [6] and intelligent robot [7]. Moreover, in the field of self-driving, the accurate perception of the environment based on LIDAR point cloud data is the key to realize information decision-making and driving safely in the complex dynamic environment.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of 3D Point Cloud Based on Spatial Eight-Quadrant Kernel Convolution

Liu

Tan

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In order to deal with the problem that some existing semantic segmentation networks for 3D point clouds generally have poor performance on small objects, a Spatial Eight-Quadrant Kernel Convolution (SEQKC) algorithm is proposed to enhance the ability of the network for extracting fine-grained features from 3D point clouds. As a result, the semantic segmentation accuracy of small objects in indoor scenes can be improved. To be specific, in the spherical space of the point cloud neighborhoods, a kernel point with attached weights is constructed in each octant, the distances between the kernel point and the points in its neighborhood are calculated, and the distance and the kernel points’ weights are used together to weight the point cloud features in the neighborhood space. In this case, the relationship between points are modeled, so that the local fine-grained features of the point clouds can be extracted by the SEQKC. Based on the SEQKC, we design a downsampling module for point clouds, and embed it into classical semantic segmentation networks (PointNet++, PointSIFT and PointConv) for semantic segmentation. Experimental results on benchmark dataset ScanNet V2 show that SEQKC-based PointNet++, PointSIFT and PointConv outperform the original networks about 1.35–2.12% in terms of MIoU, and they effectively improve the semantic segmentation performance of the networks for small objects of indoor scenes, e.g., the segmentation accuracy of small object “picture” is improved from 0.70% of PointNet++ to 10.37% of SEQKC-PointNet++.

show abstract

KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation

Cited by 10 publications

References 34 publications

FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network

FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network

PointMM: Point Cloud Semantic Segmentation CNN under Multi-Spatial Feature Encoding and Multi-Head Attention Pooling

Semantic Segmentation of 3D Point Cloud Based on Spatial Eight-Quadrant Kernel Convolution

Contact Info

Product

Resources

About