一种用于点云分类的轻量级深度神经网络

doi:10.19665/j.issn1001-2400.2020.02.007

Abstract

Abstract:

For point cloud classification, deep learning based methods use operations like voxelization to generate regular 3D grids or render the 3D mesh into a collection of images from multiple angles. However, the conversion will introduce additional computing and storage consumption. Some methods directly consume the raw point cloud. But their network scale and computational complexity make it difficult for them to deploy in embedded environments. On the basis of intensive studies of these algorithms, a novel lightweight dual path way network is proposed in this paper. Without additional conversion, our network attains a comparable performance but has 0.8 million floating parameters only. With point-wise and neighbor-wise representations, our approach incorporates global and local features of the point cloud. Experimental results on ModelNet40 and MNIST data-set demonstrate that our method achieves a good accuracy, and prove the effectiveness of our design.

Key words: machine learning, deep learning, pattern recognition, point cloud classification

CLC Number:

TP391

YAN Lin,LIU Kai,DUAN Meiyu. Lightweight deep neural network for point cloud classification[J].Journal of Xidian University, 2020, 47(2): 46-53.

Figures/Tables 15

References 21

[1]	张金刚, 方圆, 袁豪 , 等. 一种识别表情序列的卷积神经网络[J]. 西安电子科技大学学报, 2018,45(1):150-155.
[2]	ZHANG Jingang, FANG Yuan, YUAN Hao , et al. Multiple Convolutional Neural Networks for Facial Expression Sequence Recognition[J]. Journal of Xidian University, 2018,45(1):150-155.
[3]	朱苏雅, 杜建超, 李云松 , 等. 采用U-Net卷积网络的桥梁裂缝检测方法[J]. 西安电子科技大学学报, 2019,46(4):35-42.
[4]	ZHU Suya, Du Jianchao, LI Yunsong , et al. Method for Bridge Crack Detection Based on the U-Net Convolutional Networks[J]. Journal of Xidian University, 2019,46(4):35-42.
[5]	刘道华, 崔玉爽, 赵岩松 , 等. 一种改进卷积神经网络的教学图像检索方法[J]. 西安电子科技大学学报, 2019,46(3):52-58.
[6]	LIU Daohua, CUI Yushuang, ZHAO Yansong , et al. Method for Retrieving the Teaching Image Based on the Improved Convolutional Neural Network s[J]. Journal of Xidian University, 2019,46(3):52-58.
[7]	MATURANA D, SCHERER S , et al. VoxNet: A 3D Convolutional Neural Network forReal-time Object Recognition[C]// Proceedings of the 2015 IEEE International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2015: 922-928.
[8]	WANG P S, LIU Y, GUO Y X , et al. O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis[J]. ACM Transactions on Graphics, 2017,36(4):72.
[9]	RIEGLERG, ULUSOY A O, GEIGER A , et al. OctNet: Learning Deep 3D Representations at High Resolutions[C]// Proceedings of the 2017 30th IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6620-6629.
[10]	SU H, MAJI S, KALOGERAKIS E , et al. Multi-view Convolutional Neural Networks for 3D Shape Recognition[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 945-953.
[11]	QI C R, SU H, NIEBNER M , et al. Volumetric and Multi-view CNNs for Object Classification on 3D Data[C]// Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 5648-5656.
[12]	HONG R, HU Z, WANG R , et al. Multi-view Object Retrieval via Multi-scale Topic Models[J]. IEEE Transactions on Image Processing, 2016,25(12):5814-5827.
[13]	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 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 77-85.
[14]	QI C R, YI L, SU H , et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space[C]// Advances in Neural Information Processing Systems: 2017. Vancouver: Neural Information Processing Systems Foundation, 2017: 5100-5109.
[15]	ZAHEER M, KOTTUR S, RAVANBAKHSH S , et al. Deep Sets[C]// Advances in Neural Information Processing Systems: 2017. Vancouver: Neural Information Processing Systems Foundation, 2017: 3392-3402.
[16]	WU Z, SONG S, KHOSLA A , et al. 3D ShapeNets:a Deep Representation for Volumetric Shapes[C]// Proceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2015: 1912-1920.
[17]	HUA B S, TRANM K, YEUNG S K , et al. Pointwise Convolutional Neural Networks[C]// Proceedings of the 2018 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2018: 984-993.
[18]	LI Q D, GRIFFITHS J G , et al. Least Squares Ellipsoid Specific Fitting[C]// Proceedings-Geometric Modeling and Processing 2004. Washington: IEEE Computer Society, 2004: 335-340.
[19]	RAVANBAKHSH S, SCHNEIDER J, POCZOS B , et al. Deep Learning with Sets and Point Clouds[C]// Workshop Track Proceedings of the 2019 5th International Conference on Learning Representations. San Diego: International Conference on Learning Representations, 2019: 149805.
[20]	LECUN Y, BOTTOU L, BENGIO Y , et al. Gradient-based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998,86(11):2278-2324.
[21]	LIN M, CHEN Q, YAN S C , et al. Network in Network[C]// Conference Track Proceedings of the 2014 2nd International Conference on Learning Representations. San Diego: International Conference on Learning Representations, 2014: 149797.

层名称	输入维度	输出维度
点内表示	(N, 3)	(N, 1, 25)
Conv2D, [1, 1]	(N, 1, 25)	(N, 1, 64)
Conv2D, [1, 1]	(N, 1, 64)	(N, 1, 128)

层名称	输入维度	输出维度
点间表示	(N, 3)	(N, K, 25)
Conv2D, [1, 1]	(N, K, 25)	(N, K, 128)
Max pooling	(N, K, 128)	(N, 1, 128)
Conv2D, [1, 1]	(N, 1, 128)	(N, 1, 128)

层名称	输入维度	输出维度
Concatenation	(N, 1, 3)、(N, 1, 128)、(N, 1, 128)	(N, 1, 259)
Conv2D, [1, 1]	(N, 1, 259)	(N, 1, 256)
Conv2D, [1, 1]	(N, 1, 256)	(N, 1, 384)
Conv2D, [1, 1]	(N, 1, 384)	(N, 1, 512)
Max pooling	(N, 1, 512)	(512)
FC, 512	(512)	(512)
FC, 256	(512)	(256)
FC, 40	(256)	(40)
Softmax	(40)	(40)

名称	类平均精度/%	精度/%	数据类型	数据维度	权重数量(百万)	GFLOP
MVCNN^[8]	91.4	90.1	图片	60×244²	180	233
PointNet^[10]	86.2	89.2	点云	1024×3	3.5	14.7
PointNet++^[11]		90.7	点云	1024×3	4.1	26.9
PointWiseConv^[14]	81.4	86.1	点云	2048×3	1.8	16.8
VoxNet^[4]	83	85.9	体素	30³	0.9
ShapeNets^[13]	77.3	84.7	体素	30³	11
文中方法	89.2	91.1	点云	1024×3	0.8	18.4

名称	错误率/%	输入数据类型	输入数据维度
LeNet^[17]	0.80	图片	28²
Network in Network^[18]	0.47	图片	28²
PointNet^[10]	0.78	点云	512×3
PointNet++^[11]	0.51	点云	512×3
文中方法	0.59	点云	1024×3

Lightweight deep neural network for point cloud classification

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 21

Related Articles 15

Metrics

Comments

Recommended 10

通路类型			精度/%
跳连通路	点内通路	点间通路	精度/%
√	×	×	87.0
×	√	×	88.4
×	×	√	83.7
√	×	√	90.7
√	√	×	88.2
×	√	√	90.4
√	√	√	91.1

类型			扩展后通道数	精度/%
二阶多项式	三阶多项式	极坐标	扩展后通道数	精度/%
√	×	×	9	89.4
×	√	×	12	90.2
×	×	√	10	90.1
×	√	√	19	91.0
√	×	√	16	90.6
√	√	×	18	90.4
√	√	√	25	91.1

[1]	LIU Jiawei,ZHANG Wenhui,KOU Xiaoli,LI Yanni. Harnessing adversarial examples via input denoising and hidden information restoring [J]. Journal of Xidian University, 2021, 48(6): 23-31.
[2]	LI Peng,FENG Cunqian,XU Xuguang,TANG Zixiang. Ballistic target fretting classification network based on Bayesian optimization [J]. Journal of Xidian University, 2021, 48(5): 139-148.
[3]	YAN Jia,CAO Yudong,REN Jiaxing,CHEN Donghao,LI Xiaohui. Deep asymmetric compression Hashing algorithm [J]. Journal of Xidian University, 2021, 48(5): 212-221.
[4]	NING Yang,DU Jianchao,HAN Shuo,YANG Chuankai. Fire segmentation based on the improved DeeplabV3+ and the analytical method for fire development [J]. Journal of Xidian University, 2021, 48(5): 38-46.
[5]	ZHOU Peng,YANG Jun. Semantic segmentation of remote sensing images based on neural architecture search [J]. Journal of Xidian University, 2021, 48(5): 47-57.
[6]	QI Yanjun,KONG Yueping,WANG Jiajing,ZHU Xudong. Gait recognition method combining LSTM and CNN [J]. Journal of Xidian University, 2021, 48(5): 78-85.
[7]	SONG Jianfeng,MIAO Qiguang,WANG Chongxiao,XU Hao,YANG Jin. Multi-scale single object tracking based on the attention mechanism [J]. Journal of Xidian University, 2021, 48(5): 110-116.
[8]	ZHANG Yuhao,CHENG Peitao,ZHANG Shuhao,WANG Xiumei. Lightweight image super-resolution with the adaptive weight learning network [J]. Journal of Xidian University, 2021, 48(5): 15-22.
[9]	HUI Haisheng,ZHANG Xueying,WU Zelin,LI Fenglian. Method for stroke lesion segmentation using the primary-auxiliary path attention compensation network [J]. Journal of Xidian University, 2021, 48(4): 200-208.
[10]	SUN Haojie,LI Miaoyu,ZHANG Panpan,XU Pengfei. Self-supervised facial asymmetry learning for automatic evaluation of facial paralysis [J]. Journal of Xidian University, 2021, 48(3): 115-122.
[11]	ZENG Yong,WU Zhengyuan,DONG Lihua,LIU Zhihong,MA Jianfeng,LI Zan. Research on malicious traffic identification technology in encrypted traffic [J]. Journal of Xidian University, 2021, 48(3): 170-187.
[12]	WANG Junxiang,HUANG Lin,ZHANG Ying,NI Jiangqun,LIN Lang. Algorithm for the detection of a low complexity contrast enhanced image source [J]. Journal of Xidian University, 2021, 48(1): 96-106.
[13]	ZHANG Hua,GAO Haoran,YANG Xingguo,LI Wenmin,GAO Fei,WEN Qiaoyan. TargetedFool:an algorithm for achieving targeted attacks [J]. Journal of Xidian University, 2021, 48(1): 149-159.
[14]	ZHANG Shudong,GAO Haichang,CAO Xiwen,KANG Shuai. Adaptive fast and targeted adversarial attack for speech recognition [J]. Journal of Xidian University, 2021, 48(1): 168-175.
[15]	YANG Hongyu,ZENG Renyun. Method for assessment of network security situation with deep learning [J]. Journal of Xidian University, 2021, 48(1): 183-190.