Abstract
The image depth estimation problem is the basic issue of computer vision, and extracting the depth information from the two-dimensional image information is a challenge work. Focusing on the issue of extracting the depth information, an algorithm based on Markov Random Field (MRF) model has been proposed to estimate depth from single image. It includes calculating multi-scale texture features using Laws filers to the two-dimensional image, and calculating the probability relationship between texture clues and scene depth according to the texture features at different scales. Then, it establishes MRF probabilistic model and estimate parameters of MRF to get the initial depth image using the least squares method. Finally, an iterating algorithm depending on neighborhood mixing depth information is adopted to further improve the estimation accuracy. The experimental results show that the method performs well both in areas with small range of depth and areas with large range of depth when the texture feature is obvious.
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
References
Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: Conference on Computer Vision and Pattern Recognition (2015)
Zhou, W., Dai, Y., He, R.: Efficient depth estimation from single image. In: IEEE China Summit & International Conference on Signal and Information Processing (2014)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47(1), 7–42 (2002)
Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach. Prentice Hall, New York (2003)
Das, S., Ahuja, N.: Performance analysis of stereo, vergence, and focus as depth cues for active vision. IEEE Trans. Pattern Anal. Mach. Intell. 17(12), 1213–1219 (1995)
Ge, L., Zhu, Q., Fu, S.: Application of laws’ masks to stereo matching. Acta Optica Sinica 29(9), 2507–2508 (2009)
Sun, J., Xu, Z.: A review on scale method in computer vision. Chin. J. Eng. Math. 22(6), 951–960 (2005)
Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 30(5), 824–840 (2009)
Lan, J., Ding, Y., Huang, D.: Depth estimation of single image based on multi-scale texture energy measure. Comput. Eng. Des. 32(1), 224–231 (2011)
Davies, E.R.: Laws texture energy in TEXTURE. In: Machine Vision: Theory, Algorithms, Practicalities, 3rd edn., pp. 756–799 (2005)
Acknowledgement
This work is supported by the Harbin Science and Technology Bureau outstanding subject leader fund project (2017RAXXJ055), Nature Science Foundation of Heilongjiang Province (F2018020).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Zhang, L., Chen, Y., Niu, L., Zhao, Z., Han, X. (2019). An Algorithm of Single Image Depth Estimation Based on MRF Model. In: Jia, M., Guo, Q., Meng, W. (eds) Wireless and Satellite Systems. WiSATS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 281. Springer, Cham. https://doi.org/10.1007/978-3-030-19156-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-19156-6_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19155-9
Online ISBN: 978-3-030-19156-6
eBook Packages: Computer ScienceComputer Science (R0)