《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1818-1825.DOI: 10.11772/j.issn.1001-9081.2022050688
收稿日期:
2022-05-13
修回日期:
2022-08-05
接受日期:
2022-08-08
发布日期:
2023-06-08
出版日期:
2023-06-10
通讯作者:
柳杰林
作者简介:
鲁斌(1975—),男,宁夏银川人,教授,博士,CCF高级会员,主要研究方向:智能计算、计算机视觉、综合能源系统Bin LU1,2, Jielin LIU1,2()
Received:
2022-05-13
Revised:
2022-08-05
Accepted:
2022-08-08
Online:
2023-06-08
Published:
2023-06-10
Contact:
Jielin LIU
About author:
LU Bin, born in 1975, Ph. D., professor. His research interests include intelligent computing, computer vision, integrated energy systems.
摘要:
为挖掘感知点云几何特征并通过特征增强的方式进一步提高点云语义分割效果,提出了一种基于特征增强的点云语义分割网络。首先,通过设计点云的几何特征感知(GFSOP)模块赋予网络点云局部几何结构的感知能力,捕获点间的空间特征以强化语义表征,并利用分层提取特征思想获得多尺度特征。同时,使用空间注意力和通道注意力融合预测点云语义标签,并通过强化空间关联性和通道依赖性提升分割性能。在室内数据集S3DIS(Stanford large-scale 3D Indoor Spaces)上的实验结果显示,所提网络相较于PointNet++在平均交并比(mIoU)上提升了5.7个百分点,在总体准确度(OA)上提升了3.1个百分点,且在存在噪声、点云密度不均和边界不清晰等问题的点云上表现出更强的泛化性能和更加鲁棒的分割效果。
中图分类号:
鲁斌, 柳杰林. 基于特征增强的三维点云语义分割[J]. 计算机应用, 2023, 43(6): 1818-1825.
Bin LU, Jielin LIU. Semantic segmentation for 3D point clouds based on feature enhancement[J]. Journal of Computer Applications, 2023, 43(6): 1818-1825.
网络 | OA | mAcc | mIoU |
---|---|---|---|
PointNet | 78.6 | 57.8 | 47.7 |
PointNet++ | 81.0 | 67.1 | 52.8 |
RSNet | — | 65.5 | 56.1 |
DGCNN | 82.7 | — | 56.3 |
本文网络 | 84.1 | 71.0 | 58.5 |
表1 S3DIS数据集上的语义分割实验结果 (%)
Tab. 1 Experimental results of semantic segmentation on S3DIS dataset
网络 | OA | mAcc | mIoU |
---|---|---|---|
PointNet | 78.6 | 57.8 | 47.7 |
PointNet++ | 81.0 | 67.1 | 52.8 |
RSNet | — | 65.5 | 56.1 |
DGCNN | 82.7 | — | 56.3 |
本文网络 | 84.1 | 71.0 | 58.5 |
方法 | 模块 | mIoU | OA | mAcc |
---|---|---|---|---|
PointNet++ | 基准模型 | 56.7 | 84.6 | 71.1 |
+GFSOP | 添加几何特征感知模块 | 58.6 | 86.4 | 72.6 |
+SAM | 添加空间注意力模块 | 56.9 | 84.7 | 71.9 |
+CAM | 添加通道注意力模块 | 57.6 | 85.0 | 72.1 |
+SCAM | 添加双注意力融合模块 | 57.9 | 86.5 | 73.2 |
+GFSOP+SCAM | 添加几何特征感知模块、双注意力融合模块 | 60.3 | 87.0 | 73.9 |
表2 不同模块组合的消融实验结果 (%)
Tab. 2 Results of ablation experiments of different module combinations
方法 | 模块 | mIoU | OA | mAcc |
---|---|---|---|---|
PointNet++ | 基准模型 | 56.7 | 84.6 | 71.1 |
+GFSOP | 添加几何特征感知模块 | 58.6 | 86.4 | 72.6 |
+SAM | 添加空间注意力模块 | 56.9 | 84.7 | 71.9 |
+CAM | 添加通道注意力模块 | 57.6 | 85.0 | 72.1 |
+SCAM | 添加双注意力融合模块 | 57.9 | 86.5 | 73.2 |
+GFSOP+SCAM | 添加几何特征感知模块、双注意力融合模块 | 60.3 | 87.0 | 73.9 |
1 | 王明军,李乐,易芳,等. 模拟真实水体环境下目标激光点云数据的三维重建与分析[J]. 中国激光, 2022, 49(3): No.0309001. 10.3788/CJL202249.0309001 |
WANG M J, LI L, YI F, et al. Three-dimensional reconstruction and analysis of target laser point cloud data in simulated real water environment[J]. Chinese Journal of Lasers, 2022, 49(3): No.0309001. 10.3788/CJL202249.0309001 | |
2 | 缪永伟,刘家宗,孙瑜亮,等. 基于类别-实例分割的室内点云场景修复补全[J]. 计算机学报, 2021, 44(11): 2189-2202. 10.11897/SP.J.1016.2021.02189 |
MIAO Y W, LIU J Z, SUN Y L, et al. Point cloud completion of indoor scenes based on category-instance segmentation [J]. Chinese Journal of Computers, 2021, 44(11): 2189-2202. 10.11897/SP.J.1016.2021.02189 | |
3 | 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. | |
4 | MI X X, YANG B S, CHEN C, et al. Automatic road structure detection and vectorization using MLS point clouds[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019, XLII-2/W13: 1069-1075. 10.5194/isprs-archives-xlii-2-w13-1069-2019 |
5 | WU Y C, RIVENSON Y, ZHANG Y B, et al. Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery [J]. Optica, 2018, 5(6): 704-710. 10.1364/optica.5.000704 |
6 | CHEN H, LIANG M, LIU W Q, et al. An approach to boundary detection for 3D point clouds based on DBSCAN clustering[J]. Pattern Recognition, 2022, 124: No.108431. 10.1016/j.patcog.2021.108431 |
7 | GHAHREMANI M, WILLIAMS K, CORKE F, et al. Direct and accurate feature extraction from 3D point clouds of plants using RANSAC[J]. Computers and Electronics in Agriculture, 2021, 187: No.106240. 10.1016/j.compag.2021.106240 |
8 | BUI M, CHANG L C, LIU H, et al. Comparative study of 3D point cloud compression methods[C]// Proceedings of the 2021 IEEE International Conference on Big Data. Piscataway: IEEE, 2021: 5859-5861. 10.1109/bigdata52589.2021.9671822 |
9 | LI Y Y, BU R, SUN M C, et al. PointCNN: convolution on Χ-transformed points[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2018: 828-838. |
10 | ANGULO V, RODRIGUEZ J, GAONA E, et al. A supervoxel-based approach for leaves segmentation of potato plants from point clouds[C]// Proceedings of the 2020 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2020: 4902-4905. 10.1109/igarss39084.2020.9324365 |
11 | ZHOU H Y, LIU A A, NIE W Z, et al. Multi-view saliency guided deep neural network for 3-D object retrieval and classification[J]. IEEE Transactions on Multimedia, 2020, 22(6): 1496-1506. 10.1109/tmm.2019.2943740 |
12 | 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. 10.1109/cvpr.2017.16 |
13 | 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, NY: Curran Associates Inc., 2017: 5105-5114. |
14 | WU W, QI Z, LI F X. 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: 9621-9630. 10.1109/cvpr.2019.00985 |
15 | LU Q, CHEN C, XIE W J, et al. PointNGCNN: deep convolutional networks on 3D point clouds with neighborhood graph filters [J]. Computers and Graphics, 2020, 86: 42-51. 10.1016/j.cag.2019.11.005 |
16 | LI J X, CHEN B M, LEE G H. SO-Net: self-organizing network for point cloud analysis[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 9397-9406. 10.1109/cvpr.2018.00979 |
17 | LIU T, YANG Z H, HU S J, et al. Neighbor reweighted local centroid for geometric feature identification[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(2): 1545-1558. 10.1109/tvcg.2021.3124911 |
18 | JIANG M Y, WU Y R, ZHAO T Q, et al. PointSIFT: a SIFT-like network module for 3D point cloud semantic segmentation[EB/OL]. (2018-11-24) [2022-05-02].. 10.1145/3503161.3548251 |
19 | FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 3141-3149. 10.1109/cvpr.2019.00326 |
20 | ARMENI I, SENER O, ZAMIR A R, et al. 3D semantic parsing of large-scale indoor spaces[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1534-1543. 10.1109/cvpr.2016.170 |
[1] | 郑智雄, 刘建华, 孙水华, 徐戈, 林鸿辉. 融合多窗口局部信息的方面级情感分析模型[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1796-1802. |
[2] | 王辉, 李建红. 基于Transformer的三维模型小样本识别方法[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1750-1758. |
[3] | 张慧斌, 冯丽萍, 郝耀军, 王一宁. 基于注意力机制和迁移学习的古壁画朝代识别[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1826-1832. |
[4] | 方可, 刘蓉, 魏驰宇, 张心月, 刘杨. 复杂场景下的行人跌倒检测算法[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1811-1817. |
[5] | 张奕, 王真梅. 图自动编码器上二阶段融合实现的环状RNA-疾病关联预测[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1979-1986. |
[6] | 刘阳, 陆志扬, 王骏, 施俊. 基于自注意力连接UNet的磁共振成像去吉布斯伪影算法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1606-1611. |
[7] | 丁正凯, 傅启明, 陈建平, 陆悠, 吴宏杰, 方能炜, 邢镔. 结合注意力机制与深度强化学习的超短期光伏功率预测[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1647-1654. |
[8] | 刘辉, 张琳玉, 王复港, 何如瑾. 基于注意力机制和上下文信息的目标检测算法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1557-1564. |
[9] | 黄晓辉, 杨凯铭, 凌嘉壕. 基于共享注意力的多智能体强化学习订单派送[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1620-1624. |
[10] | 张凯, 覃正楚, 刘月, 秦心怡. 多学习行为协同的知识追踪模型[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1422-1429. |
[11] | 石利锋, 倪郑威. 基于槽位相关信息提取的对话状态追踪模型[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1430-1437. |
[12] | 蒋瑞林, 覃仁超. 基于深度可分离卷积的多神经网络恶意代码检测模型[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1527-1533. |
[13] | 吴家皋, 章仕稳, 蒋宇栋, 刘林峰. 基于状态精细化长短期记忆和注意力机制的社交生成对抗网络用于行人轨迹预测[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1565-1570. |
[14] | 朱周华, 齐琦. 基于改进YOLOv5s电动车头盔的自动检测与识别[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1291-1296. |
[15] | 陈路, 陈道喜, 陆一鸣, 陆卫忠. 基于注意力机制编码器‒解码器的手写数学公式识别模型[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1297-1302. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||