Automatic video logo detection and removal

被引:42
作者
Yan, WQ
Wang, J
Kankanhalli, MS [1 ]
机构
[1] Natl Univ Singapore, Sch Comp, Singapore 117548, Singapore
[2] Delft Univ Technol, Fac Elect Engn Math & Comp Sci, NL-2600 AA Delft, Netherlands
关键词
video logo detection; video logo removal; video inpainting; visual watermark attack; neural network;
D O I
10.1007/s00530-005-0167-6
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Most commercial television channels use video logos, which can be considered a form of visible watermark, as a declaration of intellectual property ownership. They are also used as a symbol of authorization to rebroadcast when original logos are used in conjunction with newer logos. An unfortunate side effect of such logos is the concomitant decrease in viewing pleasure. In this paper, we use the temporal correlation of video frames to detect and remove video logos. In the video-logo-detection part, as an initial step, the logo boundary box is first located by using a distance threshold of video frames and is further refined by employing a comparison of edge lengths. Second, our proposed Bayesian classifier framework locates fragments of logos called logo-lets. In this framework, we systematically integrate the prior knowledge about the location of the video logos and their intrinsic local features to achieve a robust detection result. In our logo-removal part, after the logo region is marked, a matching technique is used to find the best replacement patch for the marked region within that video shot. This technique is found to be useful for small logos. Furthermore, we extend the image inpainting technique to videos. Unlike the use of 2D gradients in the image inpainting technique, we inpaint the logo region of video frames by using 3D gradients exploiting the temporal correlations in video. The advantage of this algorithm is that the inpainted regions are consistent with the surrounding texture and hence the result is perceptually pleasing. We present the results of our implementation and demonstrate the utility of our method for logo removal.
引用
收藏
页码:379 / 391
页数:13
相关论文
共 50 条
[11]   A Hybrid Approach for Automatic Incident Detection [J].
Wang, Jiawei ;
Li, Xin ;
Liao, Stephen Shaoyi ;
Hua, Zhongsheng .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2013, 14 (03) :1176-1185
[12]   Automatic detection of intraoperative neurological injury [J].
Williams, LV ;
Eswaran, C .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1999, 46 (04) :481-483
[13]   Ghost shadow removal in multi-layered video inpainting [J].
Shih, Timothy K. ;
Tang, Nick C. ;
Hwang, Jenq-Neng .
2007 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-5, 2007, :1471-+
[14]   Video Completion Method for Static Object Removal Based on GLCM [J].
Zarif, Sameh ;
Faye, Ibrahima ;
Rambli, Dayang Rohaya Awang .
2015 IEEE 11TH INTERNATIONAL COLLOQUIUM ON SIGNAL PROCESSING & ITS APPLICATIONS (CSPA 2015), 2015, :57-62
[15]   An Advanced Motion Detection Algorithm with Video Quality Analysis for Video Surveillance Systems [J].
Huang, Shih-Chia .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2011, 21 (01) :1-14
[16]   Attention Guided Relation Detection Approach for Video Visual Relation Detection [J].
Cao, Qianwen ;
Huang, Heyan .
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 :3896-3907
[17]   Spike detection II: automatic, perception-based detection and clustering [J].
Wilson, SB ;
Turner, CA ;
Emerson, RG ;
Scheuer, ML .
CLINICAL NEUROPHYSIOLOGY, 1999, 110 (03) :404-411
[18]   Detection of Shoplifting on Video Using a Hybrid Network [J].
Kirichenko, Lyudmyla ;
Radivilova, Tamara ;
Sydorenko, Bohdan ;
Yakovlev, Sergiy .
COMPUTATION, 2022, 10 (11)
[19]   Visualization system for fire detection in the video sequences [J].
Laptev N.V. ;
Laptev V.V. ;
Gerget O.M. ;
Kravchenko A.A. ;
Kolpashchikov D.Yu. .
Scientific Visualization, 2021, 13 (02) :1-9
[20]   Generalising across Domains in Video Misinformation Detection [J].
Walker, David ;
Rananga, Seani ;
Isong, Bassey ;
Marivate, Vukosi .
2024 IST-AFRICA CONFERENCE, 2024,