A Convolutional Neural Networks Oriented Approach for Voxel-Based 3D Object Classification

被引：0

作者：

Sirma, Ridvan ^{[1
]}

Dinar, Berkan ^{[1
]}

Sahin, Yusuf Huseyin ^{[1
]}

Unal, Gozde ^{[1
]}

机构：

[1] Istanbul Tech Univ, Bilgisayar & Bilisim Fak, Istanbul, Turkey

来源：

2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU) | 2018年

关键词：

convolutional neural networks; deep learning; 3D object classification;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In our work, 3D objects classification has been dealt with convolutional neural networks which is a common paradigm recently in image recognition. In the first phase of experiments, 3D models in ModelNet10 and ModelNet40 data sets were voxelized and scaled with certain parameters. Classical CNN and 3D Dense CNN architectures were designed for training the pre-processed data. In addition, the two trained CNNs were ensembled and the results of them were observed. A success rate of 95.37% achieved on ModelNet10 by using 3D dense CNN, a success rate of 91.24% achieved with ensemble of two CNNs on ModelNet40.

引用

页数：4

共 50 条

[1] 3D Object Classification Based on Multi Convolutional Neural Networks
Lu, Mei-qi
Li, Wei
Ning, Ya-guang
[J]. INTERNATIONAL CONFERENCE ON APPLIED MECHANICS AND MECHANICAL AUTOMATION (AMMA 2017), 2017, : 204 - 208
[2] Voxel-Based 3D Shape Segmentation Using Deep Volumetric Convolutional Neural Networks
Liu, Yuqi
Long, Wei
Shu, Zhenyu
Yi, Shun
Xin, Shiqing
[J]. ADVANCES IN COMPUTER GRAPHICS, CGI 2022, 2022, 13443 : 489 - 500
[3] NormalNet: A voxel-based CNN for 3D object classification and retrieval
Wang, Cheng
Cheng, Ming
Sohel, Ferdous
Bennamoun, Mohammed
Li, Jonathan
[J]. NEUROCOMPUTING, 2019, 323 : 139 - 147
[4] A 3D Neuronal Morphology Classification Approach Based on Convolutional Neural Networks
Lin, Xianghong
Zheng, Jianyang
[J]. 2018 11TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN (ISCID), VOL 2, 2018, : 244 - 248
[5] 3D Object Classification using 3D Racah Moments Convolutional Neural Networks
Mesbah, Abderrahim
Berrahou, Aissam
El Alami, Abdelmajid
Berrahou, Nadia
Berbia, Hassan
Qjidaa, Hassan
[J]. PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON NETWORKING, INFORMATION SYSTEMS & SECURITY (NISS19), 2019,
[6] Voxel-based three-view hybrid parallel network for 3D object classification
Cai, Weiwei
Liu, Dong
Ning, Xin
Wang, Chen
Xie, Guojie
[J]. DISPLAYS, 2021, 69
[7] VB-Net: Voxel-Based Broad Learning Network for 3D Object Classification
Liu, Zishu
Song, Wei
Tian, Yifei
Ji, Sumi
Sung, Yunsick
Wen, Long
Zhang, Tao
Song, Liangliang
Gozho, Amanda
[J]. APPLIED SCIENCES-BASEL, 2020, 10 (19): : 1 - 13
[8] Dense graph convolutional neural networks on 3D meshes for 3D object segmentation and classification
Tang, Wenming
Qiu, Guoping
[J]. IMAGE AND VISION COMPUTING, 2021, 114
[9] 3D object understanding with 3D Convolutional Neural Networks
Leng, Biao
Liu, Yu
Yu, Kai
Zhang, Xiangyang
Xiong, Zhang
[J]. INFORMATION SCIENCES, 2016, 366 : 188 - 201
[10] 3D Object Detection Based on Convolutional Neural Networks: A Survey
Wang, Yadong
Tian, Yonglin
Li, Guoqiang
Wang, Kunfeng
Li, Dazi
[J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2021, 34 (12): : 1103 - 1119

← 1 2 3 4 5 →