1.Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System,Hubei University of Technology,Wuhan 430068,China
2.College of Computer,Hubei University of Education,Wuhan 430205,China
In response to the existing issue of incomplete geometry modeling caused by the prevalent approach of simply concatenating raw 3D coordinate information in current point cloud semantic segmentation algorithms, a Cross-Fusion Self-Attention Network is proposed. Within the encoding layers of the network, the Cross-Fusion Self-Attention Mechanism module is introduced, which leverages interactive learning between coordinate and feature information to enhance the capability of describing fine-grained local features. This leads to a more comprehensive modeling of geometric information. Additionally, to effectively integrate shallow and deep-level features, a Hierarchical Feature Fusion module that adaptively connects different layers of the network is proposed, enabling the integration of features from various levels. Experimental results on the S3DIS, Semantic3D, and SemanticKITTI datasets demonstrate the superiority of our algorithm over advanced approaches such as RandLA-Net.
WUB C, ZHOUX Y, ZHAOS C, et al. SqueezeSegV2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud[C]//2019 International Conference on Robotics and Automation (ICRA). Montreal:ACM, 2019: 4376-4382.
[5]
ROSUR A, SCHÜTTP, QUENZELJ, et al. LatticeNet: Fast spatio-temporal point cloud segmentation using permutohedral lattices[J]. Autonomous Robots, 2022, 46(1): 45-60.
[6]
GANL, ZHANGR, GRIZZLEJ W, et al. Bayesian spatial kernel smoothing for scalable dense semantic mapping[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 790-797.
[7]
ZHOUW, ZHANGX D, HAOX X, et al. Multi Point-Voxel Convolution (MPVConv) for deep learning on point clouds[J]. Computers & Graphics, 2023, 112: 72-80.
[8]
CHARLESR Q, HAOS, MOK C, et al. PointNet: Deep learning on point sets for 3D classification and segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE, 2017: 77-85.
[9]
QIC R, YIL, SUH, et al. PointNet++: Deep hierarchical feature learning on point sets in a metric space[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach:ACM, 2017: 5105-5114.
[10]
THOMASH, QIC R, DESCHAUDJ E, et al. KPConv: Flexible and deformable convolution for point clouds[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul:IEEE, 2019: 6410-6419.
[11]
HUQ Y, YANGB, XIEL H, et al. Learning semantic segmentation of large-scale point clouds with random sampling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 8338-8354.
[12]
ENGELN, BELAGIANNISV, DIETMAYERK. Point transformer[J]. IEEE Access, 2005, 9: 134826-134840.
[13]
GUOM H, CAIJ X, LIUZ N, et al. PCT: Point cloud transformer[J]. Computational Visual Media, 2021, 7(2): 187-199.
[14]
REND Y, WUZ Y, LIJ W, et al. Point attention network for point cloud semantic segmentation[J]. Science China Information Sciences, 2022, 65(9): 192104.
[15]
ZENGZ Y, XUY Y, XIEZ, et al. LEARD-Net: Semantic segmentation for large-scale point cloud scene[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102953.
[16]
GUF, BURLUTSKIYN, ANDERSSONM, et al. Multi-resolution networks for semantic segmentation in whole slide images[C]//International Workshop on Ophthalmic Medical Image Analysis, International Workshop on Computational Pathology. Cham: Springer, 2018: 11-18.
[17]
ZHAOH S, SHIJ P, QIX J, et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE, 2017: 6230-6239.
[18]
HUANGZ T, YUY K, XUJ W, et al. PF-net: Point fractal network for 3D point cloud completion[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle:IEEE, 2020: 7659-7667.
[19]
LID W, SHIG L, WUY H, et al. Multi-scale neighborhood feature extraction and aggregation for point cloud segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(6): 2175-2191.
[20]
GENGX X, JIS P, LUM, et al. Multi-scale attentive aggregation for LiDAR point cloud segmentation[J]. Remote Sensing, 2021, 13(4): 691.
LANDRIEUL, SIMONOVSKYM. Large-scale point cloud semantic segmentation with superpoint graphs[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE, 2018: 4558-4567.
[23]
ZHAOH S, JIANGL, FUC W, et al. PointWeb: Enhancing local neighborhood features for point cloud processing[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach:IEEE, 2019: 5560-5568.
[24]
BOULCHA, LE SAUXB, AUDEBERTN. Unstructured point cloud semantic labeling using deep segmentation networks[C]//Proceedings of the Workshop on 3D Object Retrieval. ACM, 2017: 17–24.
[25]
ZHANGZ Y, HUAB S, YEUNGS K. ShellNet: Efficient point cloud convolutional neural networks using concentric shells statistics[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul:IEEE, 2019: 1607-1616.
[26]
WANGL, HUANGY C, HOUY L, et al. Graph attention convolution for point cloud semantic segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach:IEEE, 2019: 10288-10297.
[27]
WUB C, WANA, YUEX Y, et al. SqueezeSeg: Convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud[C]//2018 IEEE International Conference on Robotics and Automation (ICRA). Brisbane:IEEE, 2018: 1887-1893.
[28]
MILIOTOA, VIZZOI, BEHLEYJ, et al. RangeNet: Fast and accurate LiDAR semantic segmentation[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Macau: IEEE, 2019: 4213-4220.
[29]
ZHANGY, ZHOUZ X, DAVIDP, et al. PolarNet: An improved grid representation for online LiDAR point clouds semantic segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle:IEEE, 2020: 9598-9607.
[30]
CORTINHALT, TZELEPISG, AKSOYE.SalsaNext: Fast semantic segmentation of LiDAR point clouds for autonomous driving[J]. arXiv: 2020, 2003.03653.