Joint 3D Reconstruction of a Static Scene and Moving Objects

被引:7
|
作者
Caccamo, Sergio [1 ]
Ataer-Cansizoglu, Esra [2 ]
Taguchi, Yuichi [2 ]
机构
[1] KTH Royal Inst Technol, Stockholm, Sweden
[2] Mitsubishi Elect Res Labs, Cambridge, MA USA
关键词
SIMULTANEOUS LOCALIZATION;
D O I
10.1109/3DV.2017.00082
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a technique for simultaneous 3D reconstruction of static regions and rigidly moving objects in a scene. An RGB-D frame is represented as a collection of features, which are points and planes. We classify the features into static and dynamic regions and grow separate maps, static and object maps, for each of them. To robustly classify the features in each frame, we fuse multiple RANSAC-based registration results obtained by registering different groups of the features to different maps, including (1) all the features to the static map, (2) all the features to each object map, and (3) subsets of the features, each forming a segment, to each object map. This multi-group registration approach is designed to overcome the following challenges: scenes can be dominated by static regions, making object tracking more difficult; and moving object might have larger pose variation between frames compared to the static regions. We show qualitative results from indoor scenes with objects in various shapes. The technique enables on-the-fly object model generation to be used for robotic manipulation.
引用
收藏
页码:677 / 685
页数:9
相关论文
共 50 条
  • [1] Joint 3D Scene Reconstruction and Class Segmentation
    Haene, Christian
    Zach, Christopher
    Cohen, Andrea
    Angst, Roland
    Pollefeys, Marc
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 97 - 104
  • [2] Simultaneous 3D Tracking and Reconstruction of Multiple Moving Rigid Objects
    Ozawa, Takehiro
    Nakajima, Yoshikatsu
    Saito, Hideo
    2019 12TH ASIA PACIFIC WORKSHOP ON MIXED AND AUGMENTED REALITY (APMAR), 2019, : 58 - 62
  • [3] 3D shape measurement of static and moving objects with adaptive spatiotemporal correlation
    Harendt, Bastian
    Grosse, Marcus
    Schaffer, Martin
    Kowarschik, Richard
    APPLIED OPTICS, 2014, 53 (31) : 7507 - 7515
  • [4] Reconstruction of a scene with multiple linearly moving objects
    Han, M
    Kanade, T
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 59 (03) : 285 - 300
  • [5] Reconstruction of a scene with multiple linearly moving objects
    Han, M
    Kanade, T
    IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, VOL II, 2000, : 542 - 549
  • [6] Reconstruction of a Scene with Multiple Linearly Moving Objects
    Mei Han
    Takeo Kanade
    International Journal of Computer Vision, 2004, 59 : 285 - 300
  • [7] 3D crime scene reconstruction
    Buck, Ursula
    FORENSIC SCIENCE INTERNATIONAL, 2019, 304
  • [8] Forensic 3D scene reconstruction
    Little, CQ
    Small, DE
    Peters, RR
    Rigdon, JB
    28TH AIPR WORKSHOP: 3D VISUALIZATION FOR DATA EXPLORATION AND DECISION MAKING, 2000, 3905 : 67 - 73
  • [9] Multi-Scale Attention and Dilated Convolutional Neural Network-Based 3D Scene Reconstruction for Moving Objects
    Bian, Fuluo
    Zhang, Wentai
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2024, 33 (16)
  • [10] Noninterferometric Tomographic Reconstruction of 3D Static and Dynamic Phase and Amplitude Objects
    Memarzadeh, S.
    Nehmetallah, G. T.
    Banerjee, P. P.
    THREE-DIMENSIONAL IMAGING, VISUALIZATION, AND DISPLAY 2014, 2014, 9117