access icon free Motion depth generation using MHI for 2D-to-3D video conversion

2D-to-3D conversion has been studied over past decades and integrated to commercial 3D displays and 3DTVs. Generally, depth cues extracted from a static image are used for generating a depth map followed by depth image-based rendering for producing a stereoscopic image. Further, the motion has been considered as an important cue for motion depth estimation. In most works, motion estimation has relied on block-based motion estimation, optical flows, and their variants even though they provide inaccurate data and high computation time, posing performance bottleneck. These problems by proposing Motion History Image-based motion depth estimation method are addressed. Experimental results show that the proposed method is not only faster than the conventional methods but also outperforms them in terms of motion depth estimation.

Inspec keywords: motion estimation; stereo image processing; image sequences; video signal processing; three-dimensional displays; rendering (computer graphics)

Other keywords: motion depth generation; depth cues extraction; performance bottleneck; depth map generation; motion history image-based motion depth estimation method; block-based motion estimation; 2D-to-3D video conversion; optical flows; computation time; commercial 3D displays; 3DTV; depth image-based rendering; stereoscopic image; MHI

Subjects: Computer vision and image processing techniques; Display technology; Optical, image and video signal processing; Graphics techniques; Computer displays; Video signal processing

References

    1. 1)
      • 1. Po, L., Xu, X., Zhu, Y., et al: ‘Automatic 2D-to-3D video conversion technique based on depth-from motion and color segmentation’. IEEE Int. Conf. Signal Processing, Beijing, China, 2010, pp. 10001003.
    2. 2)
    3. 3)
      • 7. Tsia, D., Flagg, M., Rehg, J.: ‘Motion coherent tracking with multi-label MRF optimization’. Proc. British Machine Vision Conf., Aberystwyth, UK, September 2010.
    4. 4)
    5. 5)
    6. 6)
      • 4. Xu, F., Er, G., Xie, X., et al: ‘2D-to-3D conversion based on motion and color mergence’. 3DTV Conf.: The True Vision – Capture, Transmission and Display of 3D Video, Istanbul, Turkey, 2008, pp. 205208.
    7. 7)
      • 6. Fukuchi, K., Miyazato, K., Kimura, A., et al: ‘Saliency-based video segmentation with graph cuts and sequentially updated priors’. IEEE Int. Conf. Multi Expo, New York, USA, June–July 2009, pp. 638641.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.1505
Loading

Related content

content/journals/10.1049/el.2017.1505
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading