AVScreen: a real-time video augmentation method

被引:0
作者
Francisco J. Hernandez–Lopez
Mariano Rivera
机构
[1] Centro de Investigacion en Matematicas AC,
来源
Journal of Real-Time Image Processing | 2015年 / 10卷
关键词
Video augmentation; Video segmentation; Video stabilization; Mosaic; CUDA GPU;
D O I
暂无
中图分类号
学科分类号
摘要
We present a tool for video augmentation in real-time, which we name the augmentation virtual screen (AVScreen). AVScreen is useful for developing advertisements, commercials, music videos, movies, etc. The main challenges for augmenting videos, in contrast to fixed images, is that moving objects in the foreground may occlude the region to be augmented in the background and that the composition can be affected by camera movements. Therefore, we use a procedure for foreground–background video segmentation in order to deal with such occlusions. Comparisons with foreground–background video segmentation methods of the state of the art in both accuracy and computational efficiency support our choice: we reduce around 70 % of the segmentation error in a popular benchmark database and achieve real-time performance. Moreover, a new stabilization method to augment unstable camera videos is presented. For augmenting video shots, we present an efficient graph-based method for panorama (mosaic) computation. The real-time performance is reached by implementing high computational demanding procedures in GPU. The frame rate of our method is 18 frames per second for a video size of 640 × 480 pixels.
引用
收藏
页码:453 / 465
页数:12
相关论文
共 50 条
[41]   Video Augmentation Method for the Facilitation of Skill Learning in Karate [J].
Tanaka, Kazumoto .
PROCEEDINGS OF 2020 IEEE INTERNATIONAL CONFERENCE ON TEACHING, ASSESSMENT, AND LEARNING FOR ENGINEERING (IEEE TALE 2020), 2020, :674-677
[42]   A Real Time Video Stabilization Algorithm [J].
Kancharla, Tarun ;
Gindi, Sanjyot .
ADVANCES IN COMPUTING AND COMMUNICATIONS, PT 4, 2011, 193 :349-357
[43]   A VGA 30 fps Affine Motion Model Estimation VLSI for Real-Time Video Segmentation [J].
Yunbe, Yoshiki ;
Miyama, Masayuki ;
Matsuda, Yoshio .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2010, E93D (12) :3284-3293
[44]   Statistical sequential analysis for real-time video scene change detection on compressed multimedia bitstream [J].
Lelescu, D ;
Schonfeld, D .
IEEE TRANSACTIONS ON MULTIMEDIA, 2003, 5 (01) :106-117
[45]   Real-Time SURF-Based Video Stabilization System for an FPGA-Driven Mobile Robot [J].
Shene, Tahiyah Nou ;
Sridharan, K. ;
Sudha, N. .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (08) :5012-5021
[46]   High-Quality Real-Time Video Stabilization Using Trajectory Smoothing and Mesh-Based Warping [J].
Wang, Zhongqiang ;
Zhang, Lei ;
Huang, Hua .
IEEE ACCESS, 2018, 6 :25157-25166
[47]   A Novel Real-Time Digital Video Stabilization Algorithm Based on the Improved Diamond Search and Modified Kalman Filter [J].
Song, Jifei ;
Ma, Xiaohong .
2015 IEEE 7TH INTERNATIONAL CONFERENCE ON AWARENESS SCIENCE & TECHNOLOGY (ICAST), 2015, :91-95
[48]   An Intelligent Hybrid Machine Learning With Meta-Heuristic Optimization Algorithms for Enhancing Real-Time Video Stabilization [J].
Afsal, S. ;
Linsely, J. Arul .
INTERNET TECHNOLOGY LETTERS, 2025, 8 (05)
[49]   Real-time video stabilization via camera path correction and its applications to augmented reality on edge devices [J].
Cao, Mingwei ;
Zheng, Liping ;
Jia, Wei ;
Liu, Xiaoping .
COMPUTER COMMUNICATIONS, 2020, 158 :104-115
[50]   Real-Time Adaptive Foreground/Background Segmentation [J].
Darren E. Butler ;
V. Michael Bove ;
Sridha Sridharan .
EURASIP Journal on Advances in Signal Processing, 2005