A contribution to 3D tracking of deformable bubbles in swarms using temporal information

被引:0
|
作者
Wang, Lantian [1 ]
Ma, Tian [1 ]
Lucas, Dirk [1 ]
Eckert, Kerstin [1 ,2 ]
Hessenkemper, Hendrik [1 ]
机构
[1] Helmholtz Zentrum Dresden Rossendorf, Inst Fluid Dynam, Bautzner Landstr 400, D-01328 Dresden, Saxony, Germany
[2] Tech Univ Dresden, Inst Proc Engn & Environm Technol, D-01069 Dresden, Saxony, Germany
关键词
IMAGE MEASUREMENT TECHNIQUE; RECONSTRUCTION; FLOWS;
D O I
10.1007/s00348-025-03963-9
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Reliable Lagrangian 3D tracking of individual bubble swarm members allows a deeper understanding of hydrodynamic bubble-bubble interactions and their collective rise. For multi-view measurements, we have recently developed such a tracking method (Hessenkemper in Int J Multiph Flow 179:104932, 2024), which is able to track deformable bubbles with low to moderate view obstruction through the bubbles to each other. In the present work, we aim to further enhance the 3D tracking performance by additionally incorporating 2D temporal information in the form of previously established 2D tracks in each camera view. The new 3D tracking method is able to disambiguate cross-view object associations at each time step by using the 2D track information accumulated over time. In addition, the temporal information from multiple 2D domains is used in two post-processing steps to improve the completeness of established 3D trajectories. Compared to the previous 3D tracking method, the extended 3D tracking framework shows noticeable improvements in tracking ability, accuracy, and completeness of trajectories. [GRAPHICS] .
引用
收藏
页数:13
相关论文
共 50 条
  • [1] 3D detection and tracking of deformable bubbles in swarms with the aid of deep learning models
    Hessenkemper, Hendrik
    Wang, Lantian
    Lucas, Dirk
    Tan, Shiyong
    Ni, Rui
    Ma, Tian
    INTERNATIONAL JOURNAL OF MULTIPHASE FLOW, 2024, 179
  • [2] FITTING AND TRACKING 3D/4D FACIAL DATA USING A TEMPORAL DEFORMABLE SHAPE MODEL
    Canavan, Shaun
    Zhang, Xing
    Yin, Lijun
    2013 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2013), 2013,
  • [3] Towards 3D hand tracking using a deformable model
    Heap, T
    Hogg, D
    PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, : 140 - 145
  • [4] Monocular 3D Tracking of Deformable Surfaces
    Puig, Luis
    Daniilidis, Kostas
    2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2016, : 580 - 586
  • [5] Improving wildlife tracking using 3D information
    Klasen, Morris
    Steinhage, Volker
    ECOLOGICAL INFORMATICS, 2022, 68
  • [6] A fast approach to deformable surface 3D tracking
    Wang, Chenhao
    Shen, Shuhan
    Liu, Yuncai
    PATTERN RECOGNITION, 2011, 44 (12) : 2915 - 2925
  • [7] An Effective Approach to 3D Deformable Surface Tracking
    Zhu, Jianke
    Hoi, Steven C. H.
    Xu, Zenglin
    Lyu, Michael R.
    COMPUTER VISION - ECCV 2008, PT III, PROCEEDINGS, 2008, 5304 : 766 - +
  • [8] Tracking 3D Deformable Objects in Real Time
    Silva, Tiago
    Magalhaes, Luis
    Ferreira, Manuel
    Khanal, Salik Ram
    Silva, Jorge
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 4, 2022, : 823 - 830
  • [9] Joint 3D Tracking of a Deformable Object in Interaction with a Hand
    Tsoli, Aggeliki
    Argyros, Antonis A.
    COMPUTER VISION - ECCV 2018, PT XIV, 2018, 11218 : 504 - 520
  • [10] 3D Tracking of Deformable Surface by Propagating Feature Correspondences
    Liu, Ye
    Chen, Yan Qiu
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 2202 - 2205