Through-the-Lens Multi-Camera Synchronisation and Frame-Drop Detection for 3D Reconstruction

被引:3
|
作者
Imre, Evren [1 ]
Guillemaut, Jean-Yves [1 ]
Hilton, Adrian [1 ]
机构
[1] Univ Surrey, CVSSP, Guildford GU2 5XH, Surrey, England
基金
英国工程与自然科学研究理事会;
关键词
VIDEO SYNCHRONIZATION;
D O I
10.1109/3DIMPVT.2012.31
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Synchronisation is an essential requirement for multiview 3D reconstruction of dynamic scenes. However, the use of HD cameras and large set-ups put a considerable stress on hardware and cause frame drops, which is usually detected by manually verifying very large amounts of data. This paper improves [9], and extends it with frame-drop detection capability. In order to spot frame-drop events, the algorithm fits a broken line to the frame index correspondences for each camera pair, and then fuses the pairwise drop hypotheses into a consistent, absolute frame-drop estimate. The success and the practical utility of the the improved pipeline is demonstrated through a number of experiments, including 3D reconstruction and free-viewpoint video rendering tasks.
引用
收藏
页码:395 / 402
页数:8
相关论文
共 50 条
  • [41] A new metrological characterization strategy for 3D multi-camera systems
    Servi, Michaela
    Buonamici, Francesco
    Puggelli, Luca
    Volpe, Yary
    International Journal on Interactive Design and Manufacturing, 2021, 15 (01) : 69 - 72
  • [42] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
    Liu, Haisong
    Teng, Yao
    Lu, Tao
    Wang, Haiguang
    Wang, Limin
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 18534 - 18544
  • [43] DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation
    Wang, Zeyu
    Li, Dingwen
    Luo, Chenxu
    Xie, Cihang
    Yang, Xiaodong
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 8603 - 8612
  • [44] siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection
    Cortes, Irene
    Beltran, Jorge
    de la Escalera, Arturo
    Garcia, Fernando
    2020 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2020, : 933 - 938
  • [45] Camera calibration and player detection in 3D reconstruction
    Yu, Jun-Qing
    Wang, Xuan
    He, Yun-Feng
    Ruan Jian Xue Bao/Journal of Software, 2008, 19 (SUPPL.): : 151 - 160
  • [46] Three-D Wide Faces (3DWF): Facial Landmark Detection and 3D Reconstruction over a New RGB-D Multi-Camera Dataset
    Quintana, Marcos
    Karaoglu, Sezer
    Alvarez, Federico
    Manuel Menendez, Jose
    Gevers, Theo
    SENSORS, 2019, 19 (05)
  • [47] Joint Camera Pose Estimation and 3D Human Pose Estimation in a Multi-camera Setup
    Puwein, Jens
    Ballan, Luca
    Ziegler, Remo
    Pollefeys, Marc
    COMPUTER VISION - ACCV 2014, PT II, 2015, 9004 : 473 - 487
  • [48] Reconstruction method and optimum range of camera-shooting angle for 3D plant modeling using a multi-camera photography system
    Xingtong Lu
    Eiichi Ono
    Shan Lu
    Yu Zhang
    Poching Teng
    Mitsuko Aono
    Yo Shimizu
    Fumiki Hosoi
    Kenji Omasa
    Plant Methods, 16
  • [49] Reconstruction method and optimum range of camera-shooting angle for 3D plant modeling using a multi-camera photography system
    Lu, Xingtong
    Ono, Eiichi
    Lu, Shan
    Zhang, Yu
    Teng, Poching
    Aono, Mitsuko
    Shimizu, Yo
    Hosoi, Fumiki
    Omasa, Kenji
    PLANT METHODS, 2020, 16 (01)
  • [50] Evaluating the Fuzzy Coverage Model for 3D Multi-camera Network Applications
    Mavrinac, Aaron
    Herrera, Jose Luis Alarcon
    Chen, Xiang
    INTELLIGENT ROBOTICS AND APPLICATIONS, PT I, 2010, 6424 : 692 - 701