Deep models for multi-view 3D object recognition: a review

被引：1

作者：

Alzahrani, Mona ^{[1
,2
]}

Usman, Muhammad ^{[1
,3
,5
]}

Jarraya, Salma Kammoun ^{[4
]}

Anwar, Saeed ^{[1
,3
]}

Helmy, Tarek ^{[1
,5
]}

机构：

[1] KFUPM, Dept Informat & Comp Sci, Dhahran, Saudi Arabia

[2] Jouf Univ, Coll Comp & Informat Sci, Sakaka, Saudi Arabia

[3] KFUPM, SDAIA KFUPM Joint Res Ctr Artificial Intelligence, Dhahran, Saudi Arabia

[4] KAU, Fac Comp & Informat Technol, Comp Sci Dept, Jeddah 21589, Saudi Arabia

[5] KFUPM, Ctr Intelligent Secure Syst, Dhahran, Saudi Arabia

来源：

ARTIFICIAL INTELLIGENCE REVIEW | 2024年 / 57卷 / 12期

关键词：

3D object recognition; Multi-view object recognition; Multi-view conventional neural network; 3D object classification; 3D object retrieval; CONVOLUTIONAL NEURAL-NETWORK; CLASSIFICATION; CONTACTLESS; IMAGES;

D O I：

10.1007/s10462-024-10941-w

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This review paper focuses on the progress of deep learning-based methods for multi-view 3D object recognition. It covers the state-of-the-art techniques in this field, specifically those that utilize 3D multi-view data as input representation. The paper provides a comprehensive analysis of the pipeline for deep learning-based multi-view 3D object recognition, including the various techniques employed at each stage. It also presents the latest developments in CNN-based and transformer-based models for multi-view 3D object recognition. The review discusses existing models in detail, including the datasets, camera configurations, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance. Additionally, it examines various computer vision applications that use multi-view classification. Finally, it highlights future directions, factors impacting recognition performance, and trends for the development of multi-view 3D object recognition method.

引用

页数：71