Local Spatio-Temporal Representation Using the 3D Shearlet Transform

被引：0
|
作者：
Damiano Malafronte
Ernesto De Vito
Francesca Odone
机构：
[1] Università di Genova,DIBRIS
[2] Università di Genova,DIMA
来源：
Sampling Theory in Signal and Image Processing | 2018年 / 17卷 / 1期
关键词：
shearlet transform; spatio-temporal features; video analysis; 42C40;
D O I：
10.1007/BF03549613
中图分类号：
学科分类号：
摘要：
In this work we address the problem of analyzing video sequences and of representing meaningful space-time points of interest by using the 3D shearlet transform. We introduce a local representation based on shearlet coefficients of the video, regarded as 2D+T signal. This representation turns out to be informative to understand the local spatio-temporal characteristics, which can be easily detected by an unsupervised clustering algorithm.
引用
收藏
页码：57 / 72
页数：15
相关论文
共 50 条
  • [1] Local Spatio-Temporal Representation using the 3D Shearlet Transform
    Malafronte, Damiano
    Odone, Francesca
    De Vito, Ernesto
    2017 INTERNATIONAL CONFERENCE ON SAMPLING THEORY AND APPLICATIONS (SAMPTA), 2017, : 585 - 589
  • [2] A Spatio-Temporal 3D Representation of a Historic Dataset
    Papasarantou, Chrissa
    Kalaouzis, Giorgos
    Pentazou, Ioulia
    Bourdakis, Vassilis
    ECAADE 2015: REAL TIME - EXTENDING THE REACH OF COMPUTATION, VOL 1, 2015, : 701 - 708
  • [3] Efficient Multiscale and Multidirectional Representation of 3D Data using the 3D Discrete Shearlet Transform
    Goossens, Bart
    Luong, Hiep
    Aelterman, Jan
    Pizurica, Aleksandra
    Philips, Wilfried
    WAVELETS AND SPARSITY XIV, 2011, 8138
  • [4] 3D R Transform on Spatio-Temporal Interest Points for Action Recognition
    Yuan, Chunfeng
    Li, Xi
    Hu, Weiming
    Ling, Haibin
    Maybank, Stephen
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 724 - 730
  • [5] Spatio-temporal segmentation using 3D morphological tools
    Vincent, A
    Christian, R
    Fabrice, H
    15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS: IMAGE, SPEECH AND SIGNAL PROCESSING, 2000, : 877 - 880
  • [6] Global and Local Spatio-Temporal Encoder for 3D Human Pose Estimation
    Wang, Yong
    Kang, Hongbo
    Wu, Doudou
    Yang, Wenming
    Zhang, Longbin
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 4039 - 4049
  • [7] Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
    Huang, Siyuan
    Degrees, Yichen Xie
    Zhu, Song-Chun
    Zhu, Yixin
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 6515 - 6525
  • [8] 3D Gait Recognition Using Spatio-Temporal Motion Descriptors
    Kwolek, Bogdan
    Krzeszowski, Tomasz
    Michalczuk, Agnieszka
    Josinski, Henryk
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS, PT II, 2014, 8398 : 595 - 604
  • [9] Spatio-temporal descriptor using 3D curvature scale space
    Dyana, A.
    Das, Sukhendu
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS, 2007, 4815 : 632 - 640
  • [10] Multi-scale pedestrian intent prediction using 3D joint information as spatio-temporal representation
    Ahmed, Sarfraz
    Al Bazi, Ammar
    Saha, Chitta
    Rajbhandari, Sujan
    Huda, M. Nazmul
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 225
12345