Advanced search
1 file | 442.99 KB Add to list

Depth extraction from monocular video using bidirectional energy minimization and initial depth segmentation

Chunyu Lin (UGent) , Jan De Cock, Jürgen Slowack (UGent) , Peter Lambert (UGent) and Rik Van de Walle (UGent)
Author
Organization
Abstract
In this paper, we propose to extract depth information from a monocular video sequence. When estimating the depth of the current frame, the bidirectional energy minimization in our scheme considers both the previous frame and next frame, which promises a much more robust depth map and reduces the problems associated with occlusion to a certain extent. After getting an initial depth map from bidirectional energy minimization, we further refine the depth map using segmentation by assuming similar depth values in one segmented region. Different from other segmentation algorithms, we use initial depth information together with the original color image to get more reliable segmented regions. Finally, detecting the sky region using a dark channel prior is employed to correct some possibly wrong depth values for outdoor video. The experimental results are much more accurate compared with the state-of-the-art algorithms.
Keywords
Depth Extraction, depth segmentation, 2D to 3D, BELIEF PROPAGATION, GRAPH CUTS, IMAGE, RECOVERY

Downloads

  • 2012.07 - ICME2012 - Chunyu Lin et al.-Depth Extraction from Monocular Video Using Bidirectional Energy Minimization and Initial Depth Segmentation.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 442.99 KB

Citation

Please use this url to cite or link to this publication:

MLA
Lin, Chunyu et al. “Depth Extraction from Monocular Video Using Bidirectional Energy Minimization and Initial Depth Segmentation.” 2012 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). New York, NY, USA: IEEE, 2012. 505–510. Print.
APA
Lin, Chunyu, De Cock, J., Slowack, J., Lambert, P., & Van de Walle, R. (2012). Depth extraction from monocular video using bidirectional energy minimization and initial depth segmentation. 2012 IEEE International conference on multimedia and expo workshops (ICMEW) (pp. 505–510). Presented at the 2012 IEEE International conference on Multimedia and Expo Workshops (ICMEW 2012), New York, NY, USA: IEEE.
Chicago author-date
Lin, Chunyu, Jan De Cock, Jürgen Slowack, Peter Lambert, and Rik Van de Walle. 2012. “Depth Extraction from Monocular Video Using Bidirectional Energy Minimization and Initial Depth Segmentation.” In 2012 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 505–510. New York, NY, USA: IEEE.
Chicago author-date (all authors)
Lin, Chunyu, Jan De Cock, Jürgen Slowack, Peter Lambert, and Rik Van de Walle. 2012. “Depth Extraction from Monocular Video Using Bidirectional Energy Minimization and Initial Depth Segmentation.” In 2012 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 505–510. New York, NY, USA: IEEE.
Vancouver
1.
Lin C, De Cock J, Slowack J, Lambert P, Van de Walle R. Depth extraction from monocular video using bidirectional energy minimization and initial depth segmentation. 2012 IEEE International conference on multimedia and expo workshops (ICMEW). New York, NY, USA: IEEE; 2012. p. 505–10.
IEEE
[1]
C. Lin, J. De Cock, J. Slowack, P. Lambert, and R. Van de Walle, “Depth extraction from monocular video using bidirectional energy minimization and initial depth segmentation,” in 2012 IEEE International conference on multimedia and expo workshops (ICMEW), Melbourne, Australia, 2012, pp. 505–510.
@inproceedings{2975075,
  abstract     = {In this paper, we propose to extract depth information from a monocular video sequence. When estimating the depth of the current frame, the bidirectional energy minimization in our scheme considers both the previous frame and next frame, which promises a much more robust depth map and reduces the problems associated with occlusion to a certain extent. After getting an initial depth map from bidirectional energy minimization, we further refine the depth map using segmentation by assuming similar depth values in one segmented region. Different from other segmentation algorithms, we use initial depth information together with the original color image to get more reliable segmented regions. Finally, detecting the sky region using a dark channel prior is employed to correct some possibly wrong depth values for outdoor video. The experimental results are much more accurate compared with the state-of-the-art algorithms.},
  author       = {Lin, Chunyu and De Cock, Jan and Slowack, Jürgen and Lambert, Peter and Van de Walle, Rik},
  booktitle    = {2012 IEEE International conference on multimedia and expo workshops (ICMEW)},
  isbn         = {9780769547299},
  keywords     = {Depth Extraction,depth segmentation,2D to 3D,BELIEF PROPAGATION,GRAPH CUTS,IMAGE,RECOVERY},
  language     = {eng},
  location     = {Melbourne, Australia},
  pages        = {505--510},
  publisher    = {IEEE},
  title        = {Depth extraction from monocular video using bidirectional energy minimization and initial depth segmentation},
  url          = {http://dx.doi.org/10.1109/ICMEW.2012.94},
  year         = {2012},
}

Altmetric
View in Altmetric
Web of Science
Times cited: