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
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
收藏
页数:71
相关论文
共 124 条
  • [1] Ahmed E, 2019, Arxiv, DOI arXiv:1808.01462
  • [2] Alam Md Tanveer, 2021, 2021 INT C COMM INF, P1
  • [3] Alzahrani Mona, 2024, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), P728, DOI 10.1109/CVPRW63382.2024.00077
  • [4] Watchful-Eye: A 3D Skeleton-Based System for Fall Detection of Physically-Disabled Cane Users
    Alzahrani, Mona Saleh
    Jarraya, Salma Kammoun
    Ali, Manar Salamah
    Ben-Abdallah, Hanene
    [J]. WIRELESS MOBILE COMMUNICATION AND HEALTHCARE, 2018, 247 : 107 - 116
  • [5] AntWeb, 2021, Antweb version 8.66
  • [6] Learning to Detect Partially Overlapping Instances
    Arteta, Carlos
    Lempitsky, Victor
    Noble, J. Alison
    Zisserman, Andrew
    [J]. 2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 3230 - 3237
  • [7] GIFT: A Real-time and Scalable 3D Shape Search Engine
    Bai, Song
    Bai, Xiang
    Zhou, Zhichao
    Zhang, Zhaoxiang
    Latecki, Longin Jan
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 5023 - 5032
  • [8] Besl PJ., 1985, Three-dimensional object recognition. ACM Computing Surveys (CSUR), V17, P75, DOI [10.1145/4078.4081, DOI 10.1145/4078.4081]
  • [9] CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope
    Bhatt, Dulari
    Patel, Chirag
    Talsania, Hardik
    Patel, Jigar
    Vaghela, Rasmika
    Pandya, Sharnil
    Modi, Kirit
    Ghayvat, Hemant
    [J]. ELECTRONICS, 2021, 10 (20)
  • [10] Flora Capture: a citizen science application for collecting structured plant observations
    Boho, David
    Rzanny, Michael
    Waeldchen, Jana
    Nitsche, Fabian
    Deggelmann, Alice
    Wittich, Hans Christian
    Seeland, Marco
    Maeder, Patrick
    [J]. BMC BIOINFORMATICS, 2020, 21 (01)