Abstract
This paper presented a virtual-real synthesis image composition method, called match-moving, which is suitable for the graphic image composition or the stereoscopic image composition. The proposed method consists of two subsystems for camera tracking and virtue-real preview, respectively. The camera tracking subsystem based on the temporal depth fusion is used to acquire the camera pose and trajectory. In order to compensate the existing noises in dynamic scenes, a priori model is employed while developing a human skeleton detection method and a spatial temporal attention analysis method. The composition of real and virtual objects is performed by a real-time virtual-real synthesis preview system. In exemplary results, the measurement of camera pose has shown that the proposed system was achieved with high accuracy. Our goal is to design an intuitive camera match-moving system to perform a virtual-real synthesis with real-time 3D preview visualization.
Original language | English |
---|---|
Title of host publication | Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 35-39 |
Number of pages | 5 |
ISBN (Electronic) | 9781509008797 |
DOIs | |
Publication status | Published - 2016 Aug 1 |
Event | 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016 - Warsaw, Poland Duration: 2016 Jun 10 → 2016 Jun 12 |
Publication series
Name | Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016 |
---|
Other
Other | 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016 |
---|---|
Country | Poland |
City | Warsaw |
Period | 16/6/10 → 16/6/12 |
Fingerprint
Keywords
- camera tracking
- match-moving
- temporal depth fusion
- virtual-real synthesis
ASJC Scopus subject areas
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
A real-time camera match-moving method for virtual-real synthesis image composition using temporal depth fusion. / Luo, An Chun; Chen, Sei-Wang; Tseng, Kun Lung.
Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 35-39 7528515 (Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A real-time camera match-moving method for virtual-real synthesis image composition using temporal depth fusion
AU - Luo, An Chun
AU - Chen, Sei-Wang
AU - Tseng, Kun Lung
PY - 2016/8/1
Y1 - 2016/8/1
N2 - This paper presented a virtual-real synthesis image composition method, called match-moving, which is suitable for the graphic image composition or the stereoscopic image composition. The proposed method consists of two subsystems for camera tracking and virtue-real preview, respectively. The camera tracking subsystem based on the temporal depth fusion is used to acquire the camera pose and trajectory. In order to compensate the existing noises in dynamic scenes, a priori model is employed while developing a human skeleton detection method and a spatial temporal attention analysis method. The composition of real and virtual objects is performed by a real-time virtual-real synthesis preview system. In exemplary results, the measurement of camera pose has shown that the proposed system was achieved with high accuracy. Our goal is to design an intuitive camera match-moving system to perform a virtual-real synthesis with real-time 3D preview visualization.
AB - This paper presented a virtual-real synthesis image composition method, called match-moving, which is suitable for the graphic image composition or the stereoscopic image composition. The proposed method consists of two subsystems for camera tracking and virtue-real preview, respectively. The camera tracking subsystem based on the temporal depth fusion is used to acquire the camera pose and trajectory. In order to compensate the existing noises in dynamic scenes, a priori model is employed while developing a human skeleton detection method and a spatial temporal attention analysis method. The composition of real and virtual objects is performed by a real-time virtual-real synthesis preview system. In exemplary results, the measurement of camera pose has shown that the proposed system was achieved with high accuracy. Our goal is to design an intuitive camera match-moving system to perform a virtual-real synthesis with real-time 3D preview visualization.
KW - camera tracking
KW - match-moving
KW - temporal depth fusion
KW - virtual-real synthesis
UR - http://www.scopus.com/inward/record.url?scp=84992047464&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84992047464&partnerID=8YFLogxK
U2 - 10.1109/OPTIP.2016.7528515
DO - 10.1109/OPTIP.2016.7528515
M3 - Conference contribution
AN - SCOPUS:84992047464
T3 - Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016
SP - 35
EP - 39
BT - Proceedings - 2016 International Conference on Optoelectronics and Image Processing, ICOIP 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -