AIPUB归智期刊联盟

微信公众号

网站二维码

2025年4月1日 10:17 星期二
首页 > 过刊浏览>2025年第34卷第3期 >1-13. DOI:10.15888/j.cnki.csa.009796
PDF HTML阅读 XML下载 导出引用 引用提醒
Point-GBLS: 结合深宽度学习的三维点云分类网络
作者:
基金项目:

山西省自然科学基金 (202203021221145); 国家自然科学基金 (62072325)


Point-GBLS: 3D Point Cloud Classification Network Combined with Deep-broad Learning
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [38]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    基于点云的三维物体识别和检测是计算机视觉和自主导航领域的一个重要研究课题. 如今, 深度学习算法大大提高了三维点云分类的准确性和鲁棒性. 然而, 深度学习网络通常存在网络结构复杂、训练过程耗时等问题. 本文提出了一种三维点云分类网络Point-GBLS, 它将深度学习和宽度学习系统结合在一起. 网络结构简单, 训练时间短. 首先通过基于深度学习的特征提取网络提取点云特征, 然后用改进的宽度学习系统对其进行分类. ModelNet40和ScanObjectNN数据集上的实验表明, Point-GBLS识别准确率分别达到92%以上和78%以上, 训练时间低于同类深度学习方法的50%以上, 优于具有相同骨干的深度学习网络.

    Abstract:

    3D object recognition and detection based on point clouds is an important research topic in the fields of computer vision and autonomous navigation. Nowadays, deep learning algorithms have greatly improved the accuracy and robustness of 3D point cloud classification. However, deep learning networks usually have problems such as complex network structure and time-consuming training. This study proposes a three-dimensional point cloud classification network named Point-GBLS, which combines deep learning and a broad learning system. The network structure is simple and the training time is short. Firstly, point cloud features are extracted by a deep learning-based feature extraction network. Then, an improved broad learning system is used to classify them. Experiments on the ModelNet40 and ScanObjectNN dataset show that the recognition accuracy of Point-GBLS is more than 92% and 78% respectively. The training time is less than 50% of that of similar deep learning methods. It is superior to deep learning networks with the same backbone.

    参考文献
    [1] Maturana D, Scherer S. VoxNet: A 3D convolutional neural network for real-time object recognition. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Hamburg: IEEE, 2015. 922–928.
    [2] Zhou Y, Tuzel O. VoxelNet: End-to-end learning for point cloud based 3D object detection. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 4490–4499.
    [3] Liu ZS, Song W, Tian YF, et al. VB-Net: Voxel-based broad learning network for 3D object classification. Applied Sciences, 2020, 10(19): 6735.
    [4] Su H, Maji S, Kalogerakis E, et al. Multi-view convolutional neural networks for 3D shape recognition. Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015. 945–953.
    [5] Yang Z, Wang LW. Learning relationships for multi-view 3D object recognition. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019. 7504–7513.
    [6] Wang WJ, Cai Y, Wang T. Multi-view dual attention network for 3D object recognition. Neural Computing and Applications, 2022, 34(4): 3201–3212.
    [7] Qi CR, Su H, Mo K, et al. PointNet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 652–660.
    [8] Qi CR, Yi L, Su H, et al. PointNet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: ACM, 2017. 5105–5114.
    [9] Xu QG, Sun XD, Wu CY, et al. Grid-GCN for fast and scalable point cloud learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 5660–5669.
    [10] Xu MT, Zhang JB, Zhou ZP, et al. Learning geometry-disentangled representation for complementary understanding of 3D object point cloud. arXiv:2012.10921v3, 2021.
    [11] Zhang RR, Wang LH, Wang YL, et al. Starting from non-parametric networks for 3D point cloud analysis. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023. 5344–5353.
    [12] Huang GB, Zhu QY, Siew CK. Extreme learning machine: Theory and applications. Neurocomputing, 2006, 70(1–3): 489–501.
    [13] Huang GB, Zhou HM, Ding XJ, et al. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513–529.
    [14] Zhang R, Lan Y, Huang GB, et al. Universal approximation of extreme learning machine with adaptive growth of hidden nodes. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(2): 365–371.
    [15] Liu Z, Jin W, Mu Y. Variances-constrained weighted extreme learning machine for imbalanced classification. Neurocomputing, 2020, 403: 45–52.
    [16] Chen CLP, Liu ZL. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(1): 10–24.
    [17] Liu Z, Huang SL, Jin W, et al. Graph-based broad learning system for classification. Neurocomputing, 2021, 463: 535–544.
    [18] Wu ZR, Song SR, Khosla A, et al. 3D ShapeNets: A deep representation for volumetric shapes. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 1912–1920.
    [19] Rusu RB, Blodow N, Marton ZC, et al. Aligning point cloud views using persistent feature histograms. Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice: IEEE, 2008. 3384–3391.
    [20] Rusu RB, Blodow N, Beetz M. Fast point feature histograms (FPFH) for 3D registration. Proceedings of the 2009 IEEE International Conference on Robotics and Automation. Kobe: IEEE, 2009. 3212–3217.
    [21] Salti S, Tombari F, Di Stefano L. SHOT: Unique signatures of histograms for surface and texture description. Computer Vision and Image Understanding, 2014, 125: 251–264.
    [22] Zhou H, Li QD, Xie QJ. Individual pig identification using back surface point clouds in 3D vision. Sensors, 2023, 23(11): 5156.
    [23] Li YY, Bu R, Sun MC, et al. PointCNN: Convolution on X-transformed points. Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: ACM, 2018. 828–838.
    [24] Wu WX, Qi ZG, Li FX. PointConv: Deep convolutional networks on 3D point clouds. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 9613–9622.
    [25] 单铉洋, 孙战里, 曾志刚. RFNet: 用于三维点云分类的卷积神经网络. 自动化学报, 2023, 49(11): 2350–2359.
    [26] Chen C, Fragonara LZ, Tsourdos A. GAPointNet: Graph attention based point neural network for exploiting local feature of point cloud. Neurocomputing, 2021, 438: 122–132.
    [27] 史豪斌, 王少熙, 黄睿茜. 融合注意力机制与神经网络的三维点云分类算法. 微电子学与计算机, 2023, 40(5): 12–19.
    [28] Guo MH, Cai JX, Liu ZN, et al. PCT: Point cloud Transformer. Computational Visual Media, 2021, 7(2): 187–199.
    [29] He CH, Li RH, Li S, et al. Voxel set Transformer: A set-to-set approach to 3D object detection from point clouds. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8407–8417.
    [30] Kasun LLC, Zhou H, Huang GB, et al. Representational learning with ELMs for big data. IEEE Intelligent Systems, 2013, 28(6): 31–34.
    [31] Kasun LLC, Yang Y, Huang GB, et al. Dimension reduction with extreme learning machine. IEEE Transactions on Image Processing, 2016, 25(8): 3906–3918.
    [32] Pao YH, Park GH, Sobajic DJ. Learning and generalization characteristics of the random vector functional-link net. Neurocomputing, 1994, 6(2): 163–180.
    [33] Chu YH, Lin HF, Yang L, et al. Hyperspectral image classification with discriminative manifold broad learning system. Neurocomputing, 2021, 442: 236–248.
    [34] Chen GM, Zhang D, Xian ZY, et al. Facial expressions classification based on broad learning network. Proceedings of the 10th International Conference on Information Systems and Computing Technology (ISCTech). Guilin: IEEE, 2022. 715–720.
    [35] Liu WT, Zuo Y, Li TS, et al. Application of image recognition for on-board sailor behavior based on broad learning system. Proceedings of the 4th International Conference on Data-driven Optimization of Complex Systems (DOCS). Chengdu: IEEE, 2022. 1–5.
    [36] 刘万军, 李雨萌, 曲海成. 基于频谱增强和卷积宽度学习的音乐流派分类. 计算机系统应用, 2023, 32(10): 85–95.
    [37] Xue H, Wang XY, Meng Y, et al. Fine-grained classification of YOLOv5 remote sensing aircraft targets incorporating broad learning system. Proceedings of the 9th International Conference on Cloud Computing and Intelligent Systems (CCIS). Dali: IEEE, 2023. 414–418.
    [38] Li HM, Ma JW, Zang SF, et al. Hyperspectral image classification based on cross-domain adaptive broad learning system. Proceedings of the 39th Youth Academic Annual Conference of Chinese Association of Automation (YAC). Dalian: IEEE, 2024. 1499–1503.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张国有,左嘉欣,潘理虎,郝志祥,郭伟,张雪楠. Point-GBLS: 结合深宽度学习的三维点云分类网络.计算机系统应用,2025,34(3):1-13

复制
分享
文章指标
  • 点击次数:227
  • 下载次数: 783
  • HTML阅读次数: 101
  • 引用次数: 0
历史
  • 收稿日期:2024-09-07
  • 最后修改日期:2024-09-30
  • 在线发布日期: 2025-01-16
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会软件学报
您是第11124894位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码：100190
电话：010-62661041 传真： Email：csa (a) iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号