基于卷积神经网络的高效三维模型检索方法

doi:10.12263/DZXB.20191268

电子学报 ›› 2021, Vol. 49 ›› Issue (1): 64-71.DOI: 10.12263/DZXB.20191268

基于卷积神经网络的高效三维模型检索方法

汤磊, 丁博, 何勇军

哈尔滨理工大学计算机科学与技术学院, 黑龙江哈尔滨 150080

收稿日期:2019-11-13 修回日期:2020-05-18 出版日期:2021-01-25
- 通讯作者:
- 丁博
- 作者简介:
- 汤磊男,1995年出生,山东枣庄人.硕士,主要研究方向为三维模型检索、机器学习.E-mail:tanglei_8520@163.com;何勇军 男,1980年出生,四川南充人.博士,教授,博士生导师,CCF会员.主要研究方向为机器学习、模式识别.E-mail:holywit@163.com
- 基金资助:
- 国家自然科学基金面上项目 (No.61673142）; 黑龙江省自然科学基金杰出青年项目 (No.JJ2019JQ0013）; 黑龙江省普通本科高等学校青年创新人才项目 (No.UNPYSCT-2016034）; 哈尔滨市杰出青年人才基金 (No.2017RAYXJ013）

An Efficient 3D Model Retrieval Method Based on Convolutional Neural Network

TANG Lei, DING Bo, HE Yong-jun

Computer Science and Technology College, Harbin University of Science and Technology, Harbin, Heilongjiang 150080, China

Received:2019-11-13 Revised:2020-05-18 Online:2021-01-25 Published:2021-01-25
- Corresponding author:
- DING Bo
- Supported by:
- National Natural Science Foundation of China (No.61673142); Outstanding Youth Program of Natural Science Foundation of Heilongjiang Province (No.JJ2019JQ0013); Young Innovative Talents Project of Colleges and Universities of Heilongjiang Province (No.UNPYSCT-2016034); Harbin Outstanding Young Talent Fund (No.2017RAYXJ013)

摘要/Abstract

摘要： 目前基于视图的三维模型检索已经成为一个研究热点.该方法首先将三维模型表示为二维视图的集合，然后采用深度学习技术进行分类和检索.但是现有的方法在精度和效率方面都有待提升.本文提出了一种新的三维模型检索方法，该方法包括索引建立和模型检索.在索引建立阶段，选择代表性视图输入到训练好的卷积神经网络（Convolutional Neural Network，CNN）中以提取特征和分类，进而根据特征类别对特征进行组织以建立索引在检索阶段，使用CNN和投票算法将输入模型的代表性视图分类为一个类别，然后仅选择这个类别的特征而不是所有类别的特征进行相似度匹配，因此减少了搜索空间.此外，随着用于检索的视图数量的逐渐增加，一旦可以确定三维模型，检索过程将提前终止.实验的数据选用刚性三维模型数据集ModelNet10，ModelNet40和非刚性三维模型数据集McGill10.结果表明，该方法在提升检索效率的同时，确保检索准确率分别高达94%、92%和100%.

关键词: 模型检索, 模型分类, 代表性视图, 卷积神经网络

Abstract: Recently, 3D model retrieval based on views has become a research hotspot. In this method, 3D models are represented as a collection of 2D views, which allows deep learning techniques to be used for 3D model classification and retrieval. However, current methods need improvements on both accuracy and efficiency. We propose a 3D model retrieval method, which includes index building and model retrieval. In the index building stage, representative views are selected and input into a well-learned Convolutional Neural Network (CNN) for feature extraction and classification. Next, the features are organized according to their labels to build indexes. In the retrieval stage, the representative views of the input model are classified into a category with the CNN and voting algorithm, and then only the features of one category rather than all categories are chosen to perform similarity matching. In this way, the searching space for retrieval is reduced. In addition, the number of the used views for retrieval is gradually increased. Once there is enough evidence to determine a 3D model, the retrieval process will be terminated ahead of time. Experiments on the rigid 3D model datasets ModelNet10, ModelNet40, and the non-rigid 3D model dataset McGill10 show that the proposed method can improve the retrieval efficiency substantially while keeping high retrieval accuracy rates at 94%, 92% and 100%, respectively.

Key words: model retrieval, model classification, representative views, convolutional neural network

中图分类号:

TP391

汤磊, 丁博, 何勇军. 基于卷积神经网络的高效三维模型检索方法[J]. 电子学报, 2021, 49(1): 64-71.

TANG Lei, DING Bo, HE Yong-jun . An Efficient 3D Model Retrieval Method Based on Convolutional Neural Network[J]. Acta Electronica Sinica, 2021, 49(1): 64-71.

参考文献

[1] 李荫民,薛凯心,高赞.基于残差网络的三维模型检索算法[J].计算机科学,2019,46(3):148-153. LI Yin-min,XUE Kai-xin,GAO Zan.3-D model retrieval algorithm based on residual network[J].Computer Science,2019,46(3):148-153.(in Chinese)
[2] 杨军,王亦民.基于深度卷积神经网络的三维模型识别[J].重庆邮电大学学报(自然科学版),2019,31(2):254-261. YANG Jun,WANG Yi-min.3D model recognition based on depth convolution neural network[J].Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition),2019,31(2):254-261.(in Chinese)
[3] Qin F W,Li L Y,Gao S M,et al.A deep learning approach to the classification of 3D CAD models[J].Journal of Zhejiang University:Science C,2014,15(2):91-106.
[4] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[A].Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].San Diego,CA,USA:IEEE,2005.886-893.
[5] Sun J,Ovsjanikov M,Guibas L.A concise and provably informative multi-scale signature based on heat diffusion[J].Computer Graphics Forum,2009,28(5):1383-1392.
[6] Aubry M,Schlickewei U,Cremers D.The wave kernel signature:A quantum mechanical approach to shape analysis[A].Proceedings of IEEE International Conference on Computer Vision Workshops[C].Barcelona,Spain:IEEE,2011.1626-1633.
[7] Zeng H,Liu Y,Li S,et al.Convolutional neural network based multi-feature fusion for non-rigid 3D model retrieval[J].Journal of Information Processing Systems,2018,14(1):176-190.
[8] Chen D Y,Tian X P,Shen Y T,et al.On visual similarity based on 3D model retrieval[J].Computer Graphics Forum,2003,22(3):223-232.
[9] Su H,Maji S,Kalogerakis E,et al.Multi-view convolutional neural networks for 3D shape recognition[A].Proceedings of the IEEE International Conference on Computer Vision[C].Santiago,Chile:IEEE,2015.945-953.
[10] Wang C,Pelillo M,Siddiqi K,et al.Dominant set clustering and pooling for multi-view 3D object recognition[A].Proceedings of the British Machine Vision Conference[C].Heidelberg:Springer,2017.1-11.
[11] Ma Y X,Zheng B,Guo Y L,et al.Boosting multi-view convolutional neural networks for 3D object recognition via view saliency[A].Proceedings of the Chinese Conference on Image and Graphics Technologies[C].Singapore:Springer,2017.199-209.
[12] Sfikas K,Theoharis T,Pratikakis I.Exploiting the PANORAMA representation for convolutional neural network classification and retrieval[A].Proceedings of Eurographics Workshop on 3D Object Retrieval[C].Lyon,France:The Eurographics Association,2017.1-7.
[13] Shi B,Bai S,Zhou Z,et al.DeepPano:deep panoramic representation for 3-D shape recognition[J].IEEE Signal Processing Letters,2015,22(12):2339-2343.
[14] Gao Y,Dai Q,Wang M,et al.3D model retrieval using weighted bipartite graph matching[J].Signal Processing:Image Communication,2011,26(1):39-47.
[15] 石民,张树生,李亮,白晓亮.基于二维典型视图的三维CAD模型检索算法[J].制造业自动化,2012,34(09):82-84,126. SHI Min,ZHANG Shu-sheng,LI Liang,BAI Xiao-liang.3D CAD model retrieval using 2D characteristic views[J].Manufacturing Automation,2012,34(09):82-84,126.(in Chinese)
[16] 白静,司庆龙,秦飞巍.基于卷积神经网络和投票机制的三维模型分类与检索[J].计算机辅助设计与图形学学报,2019,31(2):303-314. BAI Jing,SI Qing-long,QIN Fei-wei.3D model classification and retrieval based on CNN and voting scheme[J].Journal of Computer-Aided Design & Computer Graphics,2019,31(2):303-314.(in Chinese)
[17] Phong B T.Illumination for computer generated pictures[J].Communications of the ACM,1975,18(6):311-317.
[18] Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun.Deep residual learning for image recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Las Vegas,NV,USA:IEEE,2016.770-778.
[19] Bholowalia P,Kumar A.EBK-means:A clustering technique based on elbow method and k-means in WSN[J].International Journal of Computer Applications,2014,105(9):17-24.
[20] Shilane P,Min P,Kazhdan M,et al.The princeton shape benchmark[A].Proceedings of the Shape Modeling Applications[C].Genova,Italy:IEEE,2004.167-178.
[21] Siddiqi K,Zhang J,Macrini D,et al.Retrieving articulated 3D models using medial surfaces[J].Machine Vision and Applications,2008,19(4):261-275.
[22] Han Z,Lu H,Liu Z,et al.3D2SeqViews:Aggregating sequential views for 3D global feature learning by CNN with hierarchical attention aggregation[J].IEEE Transactions on Image Processing,2019,28(3):3986-3999.
[23] Hegde V,Zadeh R.Fusionnet:3D object classification using multiple data representations[J].arXiv Preprint,2016,arXiv:1607.05695.
[24] Kazhdan M,Funkhouser T,Rusinkiewicz S.Rotation invariant spherical harmonic representation of 3D shape descriptors[A].Proceedings of Eurographics Symposium on Geometry Processing[C].Granada,Spain:The Eurographics Association,2003.156-165.
[25] Wu Z,Song S,Khosla A,et al.3D shapenets:a deep representation for volumetric shapes[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Boston,MA,USA:IEEE,2015.1912-1920.
[26] Lian Z,et al.SHREC'15 Track:non-rigid 3D shape retrieval[A].Proceedings of the Eurographics Workshop on 3D Object Retrieval[C].Zurich,Switzerland:The Eurographics Association,2015.107-120.
[27] Xie J,Dai G,Zhu F,et al.DeepShape:deep-learned shape descriptor for 3D shape retrieval[J].Pattern Analysis and Machine Intelligence,2017,39(7):1335-1345.

基于卷积神经网络的高效三维模型检索方法

An Efficient 3D Model Retrieval Method Based on Convolutional Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	黄赟, 张帆, 郭威, 陈立, 羊光. 一种基于数据标准差的卷积神经网络量化方法[J]. 电子学报, 2023, 51(3): 639-647.
[2]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[3]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[4]	丁琪, 田萱, 孙国栋. 基于注意力增强的热点感知新闻推荐模型[J]. 电子学报, 2023, 51(1): 93-104.
[5]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[6]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[7]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[8]	毛国君, 王者浩, 黄山, 王翔. 基于剪边策略的图残差卷积深层网络模型[J]. 电子学报, 2022, 50(9): 2205-2214.
[9]	袁海英, 曾智勇, 成君鹏. 面向灵活并行度的稀疏卷积神经网络加速器[J]. 电子学报, 2022, 50(8): 1811-1818.
[10]	王相海, 赵晓阳, 王鑫莹, 赵克云, 宋传鸣. 非抽取小波边缘学习深度残差网络的单幅图像超分辨率重建[J]. 电子学报, 2022, 50(7): 1753-1765.
[11]	张志文, 刘天歌, 聂鹏举. 基于实景数据增强和双路径融合网络的实时街景语义分割算法[J]. 电子学报, 2022, 50(7): 1609-1620.
[12]	丁毅, 沈薇, 李海生, 钟琼慧, 田明宇, 李洁. 面向CNN的区块链可信隐私服务计算模型[J]. 电子学报, 2022, 50(6): 1399-1409.
[13]	张波, 陆云杰, 秦东明, 邹国建. 一种卷积自编码深度学习的空气污染多站点联合预测模型[J]. 电子学报, 2022, 50(6): 1410-1427.
[14]	张云, 化青龙, 姜义成, 徐丹. 基于混合型复数域卷积神经网络的三维转动舰船目标识别[J]. 电子学报, 2022, 50(5): 1042-1049.
[15]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.