《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 214-222.DOI: 10.11772/j.issn.1001-9081.2024010045
梁杰涛1, 罗兵1, 付兰慧1, 常青玲1, 李楠楠2, 易宁波3, 冯其4, 何鑫4, 邓辅秦1()
收稿日期:
2024-01-17
修回日期:
2024-04-15
接受日期:
2024-04-15
发布日期:
2024-05-09
出版日期:
2025-01-10
通讯作者:
邓辅秦
作者简介:
梁杰涛(1999—),男,广东江门人,硕士研究生,主要研究方向:点云配准;基金资助:
Jietao LIANG1, Bing LUO1, Lanhui FU1, Qingling CHANG1, Nannan LI2, Ningbo YI3, Qi FENG4, Xin HE4, Fuqin DENG1()
Received:
2024-01-17
Revised:
2024-04-15
Accepted:
2024-04-15
Online:
2024-05-09
Published:
2025-01-10
Contact:
Fuqin DENG
About author:
LIANG Jietao, born in 1999, M. S. candidate. His research interests include point cloud registration.Supported by:
摘要:
为了提高点云配准的精度、鲁棒性和泛化性,解决迭代最近点(ICP)算法容易陷入局部最优解的问题,提出一种基于坐标几何采样的深度最近点(GSDCP)的点云配准方法。首先,基于每个点的周围点的坐标估计中心点曲率,并通过曲率大小筛选出能保留点云几何特征的点,从而完成点云下采样;然后,使用动态图卷积神经网络(DGCNN)配合下采样点云学习融入局部几何信息的点云特征,并通过Transformer捕获两个特征嵌入之间的上下文信息、使用软指针近似组合匹配;最后,利用一个可微的奇异值分解(SVD)层估计最终的刚性变换。在数据集ModelNet40上进行的点云配准实验结果表明,与ICP、Go-ICP (Globally optimal ICP)、PointNetLK、快速全局配准(FGR)、ADGCNNLK (Attention Dynamic Graph Convolutional Neural Network Lucas-Kanade)、深度最近点(DCP)和多特征引导网络(MFGNet)相比,在无噪声、有噪声和看不见点云类别的情况下GSDCP的配准精度和鲁棒性都最好;其中在无噪声的情况下,与MFGNet相比,GSDCP的旋转均方误差(MSE)降低了31.3%,平移MSE降低了58.3%;在有噪声的情况下, GSDCP的旋转MSE降低了33.9%,平移MSE降低了73.4%;在看不见点云类别的情况下, GSDCP的旋转MSE降低了57.7%,平移MSE降低了77.9%。除此之外,对不完整点云数据(包括随机遮挡和点云残缺),在点云完整度为75%以下时, GSDCP的旋转MSE降低了35.1%,平移MSE降低了39.8%。
中图分类号:
梁杰涛, 罗兵, 付兰慧, 常青玲, 李楠楠, 易宁波, 冯其, 何鑫, 邓辅秦. 基于坐标几何采样的点云配准方法[J]. 计算机应用, 2025, 45(1): 214-222.
Jietao LIANG, Bing LUO, Lanhui FU, Qingling CHANG, Nannan LI, Ningbo YI, Qi FENG, Xin HE, Fuqin DENG. Point cloud registration method based on coordinate geometric sampling[J]. Journal of Computer Applications, 2025, 45(1): 214-222.
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 894.897 339 | 29.914 835 | 23.544 817 | 0.084 643 | 0.084 643 | 0.248 755 |
Go-ICP | 140.477 325 | 11.852 313 | 2.588 463 | 0.000 659 | 0.025 665 | 0.007 092 |
FGR | 87.661 491 | 9.362 772 | 1.999 290 | 0.000 194 | 0.013 939 | 0.002 839 |
PointNetLK | 227.870 331 | 15.095 374 | 4.225 304 | 0.000 487 | 0.022 065 | 0.005 404 |
ADGCNNLK | 61.045 283 | 7.813 148 | 2.854 556 | 0.000 283 | 0.016 822 | 0.004 146 |
DCP | 7.960 885 | 2.821 504 | 1.920 297 | 0.000 445 | 0.021 104 | 0.013 548 |
MFGNet | 2.829 443 | 1.682 095 | 1.134 576 | 0.000 283 | 0.016 835 | 0.002 513 |
GSDCP | 1.944 644 | 1.394 505 | 0.981 491 | 0.000 118 | 0.010 864 | 0.001 986 |
表1 点云形状未知的测试结果
Tab. 1 Test results of unknown shape of point cloud
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 894.897 339 | 29.914 835 | 23.544 817 | 0.084 643 | 0.084 643 | 0.248 755 |
Go-ICP | 140.477 325 | 11.852 313 | 2.588 463 | 0.000 659 | 0.025 665 | 0.007 092 |
FGR | 87.661 491 | 9.362 772 | 1.999 290 | 0.000 194 | 0.013 939 | 0.002 839 |
PointNetLK | 227.870 331 | 15.095 374 | 4.225 304 | 0.000 487 | 0.022 065 | 0.005 404 |
ADGCNNLK | 61.045 283 | 7.813 148 | 2.854 556 | 0.000 283 | 0.016 822 | 0.004 146 |
DCP | 7.960 885 | 2.821 504 | 1.920 297 | 0.000 445 | 0.021 104 | 0.013 548 |
MFGNet | 2.829 443 | 1.682 095 | 1.134 576 | 0.000 283 | 0.016 835 | 0.002 513 |
GSDCP | 1.944 644 | 1.394 505 | 0.981 491 | 0.000 118 | 0.010 864 | 0.001 986 |
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 892.601 135 | 29.876 431 | 23.626 110 | 0.086 005 | 0.293 266 | 0.251 916 |
Go-ICP | 192.258 636 | 13.865 736 | 2.914 169 | 0.000 491 | 0.022 154 | 0.006 219 |
FGR | 97.002 747 | 9.848 997 | 1.445 460 | 0.000 182 | 0.013 503 | 0.002 531 |
PointNetLK | 306.323 975 | 17.502 113 | 5.280 545 | 0.000 784 | 0.028 007 | 0.007 203 |
ADGCNNLK | 84.145 566 | 9.173 089 | 3.155 154 | 0.000 454 | 0.021 307 | 0.005 651 |
DCP | 10.030 007 | 3.167 019 | 2.014 827 | 0.000 520 | 0.022 814 | 0.013 855 |
MFGNet | 3.941 372 | 1.959 942 | 1.539 593 | 0.000 420 | 0.020 518 | 0.003 482 |
GSDCP | 1.667 429 | 1.291 290 | 0.919 080 | 0.000 093 | 0.009 659 | 0.002 361 |
表2 点云类别未知的测试结果
Tab. 2 Test results of unknown category of point cloud
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 892.601 135 | 29.876 431 | 23.626 110 | 0.086 005 | 0.293 266 | 0.251 916 |
Go-ICP | 192.258 636 | 13.865 736 | 2.914 169 | 0.000 491 | 0.022 154 | 0.006 219 |
FGR | 97.002 747 | 9.848 997 | 1.445 460 | 0.000 182 | 0.013 503 | 0.002 531 |
PointNetLK | 306.323 975 | 17.502 113 | 5.280 545 | 0.000 784 | 0.028 007 | 0.007 203 |
ADGCNNLK | 84.145 566 | 9.173 089 | 3.155 154 | 0.000 454 | 0.021 307 | 0.005 651 |
DCP | 10.030 007 | 3.167 019 | 2.014 827 | 0.000 520 | 0.022 814 | 0.013 855 |
MFGNet | 3.941 372 | 1.959 942 | 1.539 593 | 0.000 420 | 0.020 518 | 0.003 482 |
GSDCP | 1.667 429 | 1.291 290 | 0.919 080 | 0.000 093 | 0.009 659 | 0.002 361 |
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 882.564 209 | 29.707 983 | 23.557 217 | 0.084 537 | 0.290 752 | 0.249 092 |
Go-ICP | 131.182 495 | 11.453 493 | 2.534 873 | 0.000 531 | 0.023 051 | 0.004 192 |
FGR | 607.694 885 | 24.651 468 | 10.055 918 | 0.011 876 | 0.108 977 | 0.027 393 |
PointNetLK | 256.155 548 | 16.004 860 | 4.595 617 | 0.000 465 | 0.021 558 | 0.005 652 |
ADGCNNLK | 70.512 636 | 8.397 180 | 2.559 214 | 0.000 278 | 0.016 673 | 0.004 526 |
DCP | 48.509 663 | 6.964 888 | 4.855 263 | 0.003 790 | 0.061 565 | 0.043 154 |
MFGNet | 19.317 484 | 4.395 166 | 3.610 706 | 0.000 847 | 0.029 113 | 0.009 011 |
GSDCP | 12.772 079 | 3.573 805 | 2.557 062 | 0.000 225 | 0.015 000 | 0.001 812 |
表3 在含有随机噪声的数据集上测试结果
Tab. 3 Test results on dataset containing random noise
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
ICP | 882.564 209 | 29.707 983 | 23.557 217 | 0.084 537 | 0.290 752 | 0.249 092 |
Go-ICP | 131.182 495 | 11.453 493 | 2.534 873 | 0.000 531 | 0.023 051 | 0.004 192 |
FGR | 607.694 885 | 24.651 468 | 10.055 918 | 0.011 876 | 0.108 977 | 0.027 393 |
PointNetLK | 256.155 548 | 16.004 860 | 4.595 617 | 0.000 465 | 0.021 558 | 0.005 652 |
ADGCNNLK | 70.512 636 | 8.397 180 | 2.559 214 | 0.000 278 | 0.016 673 | 0.004 526 |
DCP | 48.509 663 | 6.964 888 | 4.855 263 | 0.003 790 | 0.061 565 | 0.043 154 |
MFGNet | 19.317 484 | 4.395 166 | 3.610 706 | 0.000 847 | 0.029 113 | 0.009 011 |
GSDCP | 12.772 079 | 3.573 805 | 2.557 062 | 0.000 225 | 0.015 000 | 0.001 812 |
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
FPS+PointNet | 76.249 426 | 8.732 091 | 5.929 955 | 0.005 915 | 0.076 911 | 0.053 945 |
GS+PointNet | 51.354 679 | 7.166 218 | 4.514 465 | 0.003 403 | 0.058 338 | 0.037 922 |
FPS+DGCNN | 7.960 885 | 2.821 504 | 1.920 297 | 0.000 445 | 0.021 104 | 0.013 548 |
GS+DGCNN | 1.944 644 | 1.394 505 | 0.981 491 | 0.000 118 | 0.010 864 | 0.001 986 |
表4 消融实验测试结果
Tab. 4 Results of ablation experiments
模块 | MSE(R) | RMSE(R) | MAE(R) | MSE(t) | RMSE(t) | MAE(t) |
---|---|---|---|---|---|---|
FPS+PointNet | 76.249 426 | 8.732 091 | 5.929 955 | 0.005 915 | 0.076 911 | 0.053 945 |
GS+PointNet | 51.354 679 | 7.166 218 | 4.514 465 | 0.003 403 | 0.058 338 | 0.037 922 |
FPS+DGCNN | 7.960 885 | 2.821 504 | 1.920 297 | 0.000 445 | 0.021 104 | 0.013 548 |
GS+DGCNN | 1.944 644 | 1.394 505 | 0.981 491 | 0.000 118 | 0.010 864 | 0.001 986 |
1 | BESL P J, McKAY N D. Method for registration of 3-D shapes [C]// Proceedings of the SPIE 1611, Sensor Fusion IV: Control Paradigms and Data Structures. Bellingham, WA: SPIE, 1992: No.57955. |
2 | 王飞鹏,肖俊,王颖,等.一种基于高斯曲率的ICP改进算法[J].中国科学院大学学报, 2019, 36(5): 702-708. |
WANG F P, XIAO J, WANG Y, et al. An improved ICP method using Gaussian curvature [J]. Journal of University of Chinese Academy of Sciences, 2019, 36(5): 702-708. | |
3 | SHI X, LIU T, HAN X. Improved Iterative Closest Point (ICP) 3D point cloud registration algorithm based on point cloud filtering and adaptive fireworks for coarse registration [J]. International Journal of Remote Sensing, 2020, 41(8): 3197-3220. |
4 | LIU H, LIU T, LI Y, et al. Point cloud registration based on MCMC-SA ICP algorithm [J]. IEEE Access, 2019, 7: 73637-73648. |
5 | SHI X, PENG J, LI J, et al. The iterative closest point registration algorithm based on the normal distribution transformation [J]. Procedia Computer Science, 2019, 147: 181-190. |
6 | YANG J, LI H, JIA Y. Go-ICP: solving 3D registration efficiently and globally optimally [C]// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 1457-1464. |
7 | ZHOU Q Y, PARK J, KOLTUN V. Fast global registration [C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9906. Cham: Springer, 2016: 766-782. |
8 | QI C R, SU H, MO K, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 77-85. |
9 | QI C R, YI L, SU H, 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. Red Hook: Curran Associates Inc., 2017: 5105-5114. |
10 | AOKI Y, GOFORTH H, SRIVATSAN R A, et al. PointNetLK: robust & efficient point cloud registration using PointNet [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 7156-7165. |
11 | LUCAS B D, KANADE T. An iterative image registration technique with an application to stereo vision [C]// Proceedings of the 7th International Joint Conference on Artificial Intelligence — Volume 2. San Francisco: Morgan Kaufmann Publishers Inc., 1981: 674-679. |
12 | 秦庭威,赵鹏程,秦品乐,等.基于残差注意力机制的点云配准算法[J].计算机应用, 2022, 42(7): 2184-2191. |
QIN T W, ZHAO P C, QIN P L, et al. Point cloud registration algorithm based on residual attention mechanism [J]. Journal of Computer Applications, 2022, 42(7): 2184-2191. | |
13 | WANG Y, SUN Y, LIU Z, et al. Dynamic graph CNN for learning on point clouds [J]. ACM Transactions on Graphics, 2019, 38(5): No.146. |
14 | WANG Y, SOLOMON J. Deep closest point: learning representations for point cloud registration [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 3522-3531. |
15 | 侯维广,付生鹏,夏鑫,等.基于自适应采样和混合注意力的点云配准算法[J].组合机床与自动化加工技术, 2023(12): 45-49. |
HOU W G, FU S P, XIA X, et al. Point cloud registration algorithm based on adaptive sampling and mixed attention [J]. Modular Machine Tool and Automatic Manufacturing Technique, 2023(12): 45-49. | |
16 | 刘旭珩,柏正尧,许祝,等.结合注意力机制的多重引导点云配准网络[J].计算机科学, 2024, 51(2): 142-150. |
LIU X H, BAI Z Y, XU Z, et al. Multi-guided point cloud registration network combined with attention mechanism [J]. Computer Science, 2024, 51(2): 142-150. | |
17 | WANG H, LIU X, KANG W, et al. Multi-features guidance network for partial-to-partial point cloud registration [J]. Neural Computing and Applications, 2022, 34(2): 1623-1634. |
18 | SHE R, KANG Q, WANG S, et al. PointDifformer: robust point cloud registration with neural diffusion and transformer [J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: No.5701015. |
19 | QIN Z, YU H, WANG C, et al. Geometric Transformer for fast and robust point cloud registration [C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 11133-11142. |
20 | DENG H, BIRDAL T, ILIC S. PPFNet: global context aware local features for robust 3D point matching [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 195-205. |
21 | SARODE V, LI X, GOFORTH H, et al. PCRNet: point cloud registration network using PointNet encoding [EB/OL]. [2023-05-10]. . |
22 | PAPADOPOULO T, LOURAKIS M I A. Estimating the Jacobian of the singular value decomposition: theory and applications [C]// Proceedings of the 2000 European Conference on Computer Vision, LNCS 1842. Berlin: Springer, 2000: 554-570. |
23 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010. |
24 | VINYALS O, FORTUNATO M, JAITLY N. Pointer networks [C]// Proceedings of the 28th International Conference on Neural Information Processing Systems — Volume 2. Cambridge: MIT Press, 2015: 2692-2700. |
25 | YEW Z J, LEE G H. RPM-Net: robust point matching using learned features [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11821-11830. |
26 | GOLD S, RANGARAJAN A, LU C P, et al. New algorithms for 2D and 3D point matching: pose estimation and correspondence [J]. Pattern Recognition, 1998, 31(8): 1019-1031. |
27 | SINKHORN R. A relationship between arbitrary positive matrices and doubly stochastic matrices [J]. The Annals of Mathematical Statistics, 1964, 35(2): 876-879. |
28 | RUSU R B, BLODOW N, BEETZ M. Fast Point Feature Histograms (FPFH) for 3D registration [C]// Proceedings of the 2009 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2009: 3212-3217. |
29 | YEW Z J, LEE G H. REGTR: end-to-end point cloud correspondences with Transformers [C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 6667-6676. |
30 | MATURANA D, SCHERER S. VoxNet: a 3D convolutional neural network for real-time object recognition [C]// Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2015: 922-928. |
31 | WU Z, SONG S, KHOSLA A, et al. 3D ShapeNets: a deep representation for volumetric shapes [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1912-1920. |
32 | ZHOU Y, TUZEL O. VoxelNet: end-to-end learning for point cloud based 3D object detection [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4490-4499. |
33 | XIANG Y, SCHMIDT T, NARAYANAN V, et al. PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes [EB/OL]. [2023-11-09]. . |
34 | BRISTOW H, VALMADRE J, LUCEY S. Dense semantic correspondence where every pixel is a classifier [C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 4024-4031. |
35 | GEORGAKIS G, KARANAM S, WU Z, et al. Matching RGB images to CAD models for object pose estimation [EB/OL]. [2023-11-09]. . |
36 | WANG Y, SOLOMON J. PRNet: self-supervised learning for partial-to-partial registration [C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2019: 8814-8826. |
37 | MOENNING C, DODGSON N A. Fast marching farthest point sampling [R/OL]. [2023-10-25]. . |
38 | LI Y, BU R, SUN M, et al. PointCNN: convolution on X-transformed points [C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2018: 828-838. |
39 | WU W, QI Z, LI F. PointConv: deep convolutional networks on 3D point clouds [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9613-9622. |
40 | LIU Y, FAN B, XIANG S, et al. Relation-shape convolutional neural network for point cloud analysis [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 8887-8896. |
41 | HU Q, YANG B, XIE L, et al. RandLA-Net: efficient semantic segmentation of large-scale point clouds [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11105-11114. |
42 | QI H, FENG C, CAO Z, et al. P2B: point-to-box network for 3D object tracking in point clouds [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 6328-6337. |
43 | GROH F, WIESCHOLLEK P, LENSCH H P A. Flex-convolution: million-scale point-cloud learning beyond grid-worlds [C]// Proceedings of the 2018 Asian Conference on Computer Vision, LNCS 11361. Cham: Springer, 2019: 105-122. |
44 | WU C, ZHENG J, PFROMMER J, et al. Attention-based point cloud edge sampling [C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 5333-5343. |
[1] | 郑宗生, 杜嘉, 成雨荷, 赵泽骋, 张月维, 王绪龙. 用于红外-可见光图像分类的跨模态双流交替交互网络[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 275-283. |
[2] | 徐欣然, 张绍兵, 成苗, 张洋, 曾尚. 基于多路层次化混合专家模型的轴承故障诊断方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 59-68. |
[3] | 晏燕, 钱星颖, 闫鹏斌, 杨杰. 位置大数据的联邦学习统计预测与差分隐私保护方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 127-135. |
[4] | 张思齐, 张金俊, 王天一, 秦小林. 基于信号时态逻辑的深度时序事件检测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 90-97. |
[5] | 贾洁茹, 杨建超, 张硕蕊, 闫涛, 陈斌. 基于自蒸馏视觉Transformer的无监督行人重识别[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2893-2902. |
[6] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[7] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[8] | 方介泼, 陶重犇. 应对零日攻击的混合车联网入侵检测系统[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2763-2769. |
[9] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[10] | 任烈弘, 黄铝文, 田旭, 段飞. 基于DFT的频率敏感双分支Transformer多变量长时间序列预测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2739-2746. |
[11] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[12] | 杨鑫, 陈雪妮, 吴春江, 周世杰. 结合变种残差模型和Transformer的城市公路短时交通流预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2947-2951. |
[13] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[14] | 李金金, 桑国明, 张益嘉. APK-CNN和Transformer增强的多域虚假新闻检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2674-2682. |
[15] | 付帅, 郭小英, 白茹意, 闫涛, 陈斌. 改进的CloFormer模型与有序回归相结合的年龄评估方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2372-2380. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||