Abstract
In this paper, a segment-guided depth extraction approach is proposed for monocular image with linear perspective. Firstly, foreground depth is learned from a RGBD database with segment-based calibration to adjust the initial coarse depth, and background depth is estimated from linear perspective by vanishing cues. Then, the foreground depth and background one are linearly combined with a statistically optimal balance factor to obtain a holistic fused depth map. Lastly, bilateral filter is exploited to suppress the depth disturbance with edge-preserving. Experiments demonstrate that the proposed technique can produce accurate and dense depths with distinct object boundaries and correct relation among the object positions for a single image.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cheng, C.M., Hsu, X.A., Lai, S.H.: A Novel Structure-from-Motion Strategy for Refining Depth Map Estimation and Multi-view Synthesis in 3DTV. In: IEEE International Conference on Multimedia and Expo, pp. 944–949. IEEE press, Suntec City (2010)
Favaro, P.: Recovering Thin Structures via Nonlocal-means Regularization with Application to Depth from Defocus. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1133–1140. IEEE press, San Francisco (2010)
Saxena, A., Sun, M., Ng, A.Y.: Make3D: Learning 3D Scene Structure from Single Still Image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824–840 (2009)
Karsch, K., Liu, C., Kang, S.B.: Depth Extraction from Video Using Non-parametric Sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 775–788. Springer, Heidelberg (2012)
Um, G.M., Bang, G., Cheong, W.S., Hur, N., Lee, S.I.: Improvement of Segment-based Depth Estimation using a Novel Segment Extraction. In: 3DTV Conf., Tampere, pp. 1–4 (2010)
Lai, Y.K., Lai, Y.F., Chen, Y.C.: An Effective Hybrid Depth-generation Algorithm for 2D-to-3D Conversion in 3D Displays. J. Disp. Technol. 9(3), 154–161 (2013)
Saxena, A., Chung, S.H., Ng, A.Y.: Learning Depth from Single Monocular Images. J. Adv. Neural Inf. Process. Syst. 18, 1161 (2006)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886–893. IEEE press, Can Diego (2005)
Oliva, A., Torralba, A.: Building the Gist of a Scene: The Role of Global Image Features in Recognition. Prog. Brain Res. 155, 23–36 (2006)
Liu, C., Yuen, J., Antonio, A.B.: SIFT Flow: Dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)
Criminisi, A., Reid, I., Zisserman, A.: Efficient graph-based image segmentation. Int. J. Comput. Vision. 59(2), 167–181 (2004)
Schmitt, F., Priese, L.: Vanishing Point Detection with an Intersection Point Neighborhood. In: Brlek, S., Reutenauer, C., Provençal, X. (eds.) DGCI 2009. LNCS, vol. 5810, pp. 132–143. Springer, Heidelberg (2009)
Tian, C., Krishnan, S.: Accelerated Bilateral Filtering with Block Skipping. IEEE Signal Process. Lett. 20(5), 419–422 (2013)
Hore, A., Ziou, D.: Image Quality Metrics: PSNR vs. SSIM. In: 20th International Conference on Pattern Recognition, pp. 2366–2369. IEEE press, Istanbul (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mo, Y., Liu, T., Zhu, X., Dai, X., Luo, J. (2013). Segment Based Depth Extraction Approach for Monocular Image with Linear Perspective. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)