Key Frame Extraction Based on Scale Invariant Feature Transform

被引：1
|
作者：
Liu, Gentao [1 ]
Wen, Xiangming [1 ]
Lin, Xinqi [1 ]
Zhang, Hua [1 ]
机构：
[1] BUPT, Sch Informat & Telecommun, Beijing 100876, Peoples R China
来源：
THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA AND UBIQUITOUS ENGINEERING (MUE 2009) | 2009年
关键词：
key frame; SIFT; chain-match; rule-match; video clip;
D O I：
10.1109/MUE.2009.19
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Key frames are the subset of still images which best represent the content of a video sequence in an abstracted manner. They are widely used in video indexing, browsing and retrieval. In this paper, a novel content-based method for key frame extraction using scale invariant feature transform (SIFT) is proposed. Two mechanisms called chain-match and rule-match are developed to segment a video into groups of frames (video clips) according to vision content firstly. Then the frame with most SIFT keypoints in each video clip is extracted as the key frame. Experimental results show the method is effective and has a good performance.
引用
收藏
页码：45 / 48
页数：4
相关论文
共 50 条
  • [1] GRADIENT-BASED MUSICAL FEATURE EXTRACTION BASED ON SCALE-INVARIANT FEATURE TRANSFORM
    Matsui, Tomoko
    Goto, Masataka
    Vert, Jean-Philippe
    Uchiyama, Yuji
    19TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO-2011), 2011, : 724 - 728
  • [2] Shot Boundary Detection and Keyframe Extraction based on Scale Invariant Feature Transform
    Liu, Gentao
    Wen, Xiangming
    Zheng, Wei
    He, Peizhou
    PROCEEDINGS OF THE 8TH IEEE/ACIS INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE, 2009, : 1126 - 1130
  • [3] A scale Invariant Feature Transform based method
    Wang, Y.-Y. (shinewyy@gmail.com), 2013, Ubiquitous International (04):
  • [4] Trace transform based invariant feature extraction system
    Filo, P
    Turán, J
    Ovseník, L
    Fazekas, K
    IWSSIP 2005: PROCEEDINGS OF THE 12TH INTERNATIONAL WORSHOP ON SYSTEMS, SIGNALS & IMAGE PROCESSING, 2005, : 183 - 186
  • [5] Super resolution based on scale invariant feature transform
    Yuan, Zhi
    Yan, Peimin
    Li, Sheng
    2008 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING, VOLS 1 AND 2, PROCEEDINGS, 2008, : 1550 - 1554
  • [6] An Experimental Study Using Scale Invariant Feature Transform and Key-Point Extraction for Human Ear Recognition System
    Som, Subhranil
    Mahajan, Renuka
    INTELLIGENT COMPUTING, INFORMATION AND CONTROL SYSTEMS, ICICCS 2019, 2020, 1039 : 653 - 665
  • [7] Feature extraction for hyperspectral image classification based on scale invariant feature transform-locality preserving projection algorithm
    College of Computer and Information Engineering, Hohai University, Nanjing
    210098, China
    J. Comput. Theor. Nanosci., 12 (5833-5838):
  • [8] Scale Invariant Feature Transform Based Fingerprint Corepoint Detection
    Hanmandlu, M.
    Ansari, A. Q.
    Kour, Jaspreet
    Goyal, Kunal
    Malekar, Rutvik
    DEFENCE SCIENCE JOURNAL, 2013, 63 (04) : 402 - 407
  • [9] Fast Implementation of Scale Invariant Feature Transform Based on CUDA
    Lu, Meng
    APPLIED MATHEMATICS & INFORMATION SCIENCES, 2013, 7 (02): : 717 - 722
  • [10] Scale Invariant Feature Transform Based Image Matching and Registration
    Kher, Heena R.
    Thakar, Vishvjit K.
    2014 FIFTH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP 2014), 2014, : 50 - 55
12345