Automatic generation of soccer video content hierarchy by mapping low-level features to high-level semantics

被引：0
|
作者：
Chen, JY [1 ]
Li, YH [1 ]
Lao, SY [1 ]
Wu, LD [1 ]
机构：
[1] Natl Univ Def & Technol, Multimedia Res & Dev Ctr, Changsha 410073, Peoples R China
来源：
THIRD INTERNATIONAL SYMPOSIUM ON MULTISPECTRAL IMAGE PROCESSING AND PATTERN RECOGNITION, PTS 1 AND 2 | 2003年 / 5286卷
关键词：
content-based; video content hierarchy; video segmentation; semantic event detection; soccer video;
D O I：
10.1117/12.539019
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we address the problem of semantically generating hierarchical and meaningful content for soccer video by mapping low-level features to high-level semantics. Our goal is to construct a hierarchical and compact content abstraction of soccer video that can serve as an effective index table, allowing users to browse through lots of soccer videos in a flexible and efficient way. And we generated three-layer semantic hierarchies of soccer video according to characteristics of soccer video through bridging the gap between features and semantics. Some experimental results are presented and discussed in the paper.
引用
收藏
页码：541 / 546
页数：6
相关论文
共 50 条
  • [1] CBIR: From low-level features to high-level semantics
    Zhou, XS
    Huang, TS
    IMAGE AND VIDEO COMMUNICATIONS AND PROCESSING 2000, 2000, 3974 : 426 - 431
  • [2] From low-level features to high-level semantics: Are we bridging the gap?
    Chen, TH
    ISM 2005: SEVENTH IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA, PROCEEDINGS, 2005, : 179 - 179
  • [3] High-level soccer indexing on low-level feature space
    Sugano, M
    Uemura, K
    Nakajima, Y
    Yanagihara, H
    ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5, 2004, : 1625 - 1628
  • [4] Learning Low-Level Behaviors and High-Level Strategies in Humanoid Soccer
    Simoes, David
    Amaro, Pedro
    Silva, Tiago
    Lau, Nuno
    Reis, Luis Paulo
    FOURTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, ROBOT 2019, VOL 2, 2020, 1093 : 537 - 548
  • [5] Combination of high-level features with low-level features for detection of pedestrian
    Fariba Takarli
    Ali Aghagolzadeh
    Hadi Seyedarabi
    Signal, Image and Video Processing, 2016, 10 : 93 - 101
  • [6] Combination of high-level features with low-level features for detection of pedestrian
    Takarli, Fariba
    Aghagolzadeh, Ali
    Seyedarabi, Hadi
    SIGNAL IMAGE AND VIDEO PROCESSING, 2016, 10 (01) : 93 - 101
  • [7] From low-level geometric features to high-level semantics: An axiomatic fuzzy set clustering approach
    Li, Qilin
    Ren, Yan
    Li, Ling
    Liu, Wanquan
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2016, 31 (02) : 775 - 786
  • [8] Visual high-level regions respond to high-level stimulus content in the absence of low-level confounds
    Schindler, Andreas
    Bartels, Andreas
    NEUROIMAGE, 2016, 132 : 520 - 525
  • [9] Mapping low-level features to high-level semantic concepts in region-based image retrieval
    Jiang, W
    Chan, KL
    Li, MJ
    Zhang, HJ
    2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, : 244 - 249
  • [10] The High-Level Benefits of Low-Level Sandboxing
    Sammler, Michael
    Garg, Deepak
    Dreyer, Derek
    Litak, Tadeusz
    PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL, 2020, 4 (POPL):
12345