Feature-Based Monocular Dynamic 3D Object Reconstruction

被引:0
|
作者
Jin, Shaokun [2 ,3 ]
Ou, Yongsheng [1 ,2 ,4 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Guangdong Prov Key Lab Robot & Intelligent Syst, Shenzhen 518055, Peoples R China
[2] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
[3] Univ Chinese Acad Sci, Shenzhen Coll Adv Technol, Shenzhen, Peoples R China
[4] Chinese Acad Sci, Shenzhen Inst Adv Technol, CAS Key Lab Human Machine Intelligence Synerg Sys, Shenzhen 518055, Peoples R China
来源
SOCIAL ROBOTICS, ICSR 2018 | 2018年 / 11357卷
基金
中国国家自然科学基金;
关键词
Dynamic 3D object reconstruction; Topological segmentation; Pose estimation; Monocular; DEPTH;
D O I
10.1007/978-3-030-05204-1_37
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Dynamic 3D object reconstruction becomes increasingly crucial to various intelligent applications. Most existing algorithms, in spite of the accurate performances, have the problems of high cost and complex computations. In this paper, we propose a novel framework for dynamic 3D object reconstruction with a single camera in an attempt to address this problem. The gist of the proposed approach is to reduce the reconstruction problem to a pose estimation problem. We reconstruct the whole object by estimating the poses of its topological segmentations. Experiments are undertaken to validate the effectiveness of the proposed method in comparison with several state-of-art methods.
引用
收藏
页码:380 / 389
页数:10
相关论文
共 50 条
  • [41] Monocular Panoramic 3D Reconstruction Based on a Particle Filter
    Pagel, Frank
    UNMANNED SYSTEMS TECHNOLOGY XII, 2010, 7692
  • [42] Feature-based 3D motif filtering for ribosomal RNA
    Shen, Ying
    Wong, Hau-San
    Zhang, Shaohong
    Yu, Zhiwen
    BIOINFORMATICS, 2011, 27 (20) : 2828 - 2835
  • [43] An experimental comparison of feature-based 3D retrieval methods
    Bustos, B
    Keim, D
    Saupe, D
    Schreck, T
    Vranic, D
    2ND INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, 2004, : 215 - 222
  • [44] Keypoint identification and feature-based 3D face recognition
    Mian, Ajmal
    Bennamoun, Mohammed
    Owens, Robyn
    ADVANCES IN BIOMETRICS, PROCEEDINGS, 2007, 4642 : 163 - +
  • [45] Monocular 3D Object Detection With Sequential Feature Association and Depth Hint Augmentation
    Gao, Tianze
    Pan, Huihui
    Gao, Huijun
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2022, 7 (02): : 240 - 250
  • [46] Aerial Monocular 3D Object Detection
    Hu, Yue
    Fang, Shaoheng
    Xie, Weidi
    Chen, Siheng
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (04) : 1959 - 1966
  • [47] Depth dynamic center difference convolutions for monocular 3D object detection
    Wu, Xinyu
    Ma, Dongliang
    Qu, Xin
    Jiang, Xin
    Zeng, Dan
    NEUROCOMPUTING, 2023, 520 : 73 - 81
  • [48] Disentangling Monocular 3D Object Detection
    Simonelli, Andrea
    Bulo, Samuel Rota
    Porzi, Lorenzo
    Lopez-Antequera, Manuel
    Kontschieder, Peter
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 1991 - 1999
  • [49] Probabilistic instance shape reconstruction with sparse LiDAR for monocular 3D object detection
    Ji, Chaofeng
    Wu, Han
    Liu, Guizhong
    NEUROCOMPUTING, 2023, 529 : 92 - 100
  • [50] Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
    Ma, Xinzhu
    Wang, Zhihui
    Li, Haojie
    Zhang, Pengbo
    Ouyang, Wanli
    Fan, Xin
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6850 - 6859