Fast Approximate Matching of Videos from Hand-Held Cameras for Robust Background Subtraction

被引:0
|
作者
Hamid, Raffay [1 ]
Das Sarma, Atish [2 ]
DeCoste, Dennis [2 ]
Sundaresan, Neel [2 ]
机构
[1] DigitalGlobe Labs, Sydney, NSW, Australia
[2] eBay Res Labs, Sydney, NSW, Australia
来源
2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2015年
关键词
D O I
10.1109/WACV.2015.46
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We identify a novel instance of the background subtraction problem that focuses on extracting near-field foreground objects captured using handheld cameras. Given two user-generated videos of a scene, one with and the other without the foreground object(s), our goal is to efficiently generate an output video with only the foreground object(s) present in it. We cast this challenge as a spatio-temporal frame matching problem, and propose an efficient solution for it that exploits the temporal smoothness of the video sequences. We present theoretical analyses for the error bounds of our approach, and validate our findings using a detailed set of simulation experiments. Finally, we present the results of our approach tested on multiple real videos captured using handheld cameras, and compare them to several alternate foreground extraction approaches.
引用
收藏
页码:294 / 301
页数:8
相关论文
共 50 条
  • [21] Coherent video generation for multiple hand-held cameras with dynamic foreground
    Fang-Lue Zhang
    Connelly Barnes
    Hao-Tian Zhang
    Junhong Zhao
    Gabriel Salas
    ComputationalVisualMedia, 2020, 6 (03) : 291 - 306
  • [22] Coherent video generation for multiple hand-held cameras with dynamic foreground
    Fang-Lue Zhang
    Connelly Barnes
    Hao-Tian Zhang
    Junhong Zhao
    Gabriel Salas
    Computational Visual Media, 2020, 6 : 291 - 306
  • [23] Coherent video generation for multiple hand-held cameras with dynamic foreground
    Zhang, Fang-Lue
    Barnes, Connelly
    Zhang, Hao-Tian
    Zhao, Junhong
    Salas, Gabriel
    COMPUTATIONAL VISUAL MEDIA, 2020, 6 (03) : 291 - 306
  • [24] 3D model reconstruction with common hand-held cameras
    Maoteng Zheng
    Junfeng Zhu
    Xiaodong Xiong
    Shunping Zhou
    Yongjun Zhang
    Virtual Reality, 2016, 20 : 221 - 235
  • [25] Parallax Tolerant Light Field Stitching for Hand-Held Plenoptic Cameras
    Jin, Xin
    Wang, Pei
    Dai, Qionghai
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 1929 - 1943
  • [26] ROI-Based Video Stabilization Algorithm for Hand-Held Cameras
    Lee, Dong-bok
    Choi, Ick-hyun
    Song, Byung Cheol
    Lee, Tae Hwan
    2012 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (ICMEW), 2012, : 314 - 318
  • [27] 3D model reconstruction with common hand-held cameras
    Zheng, Maoteng
    Zhu, Junfeng
    Xiong, Xiaodong
    Zhou, Shunping
    Zhang, Yongjun
    VIRTUAL REALITY, 2016, 20 (04) : 221 - 235
  • [28] Fast background subtraction for moving cameras based on nonparametric models
    Sun, Feng
    Qin, Kaihuai
    Sun, Wei
    Guo, Huayuan
    JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (03)
  • [29] DEVELOPMENT OF A HAND-HELD FAST NEUTRON SURVEY METER
    Yoshida, T.
    Tsujimura, N.
    Yamano, T.
    RADIATION PROTECTION DOSIMETRY, 2011, 146 (1-3) : 72 - 75
  • [30] Slippage-free Background Replacement for Hand-held Video
    Zhong, Fan
    Yang, Song
    Qin, Xueying
    Lischinski, Dani
    Cohen-Or, Daniel
    Chen, Baoquan
    ACM TRANSACTIONS ON GRAPHICS, 2014, 33 (06):