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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-19156-6_19 | WIRELESS AND SATELLITE SYSTEMS, PT II |
Keywords | DocType | Volume |
Least-square method, Laws filer, Multi-scale texture feature, MRF, Depth estimation | Conference | 281 |
ISSN | Citations | PageRank |
1867-8211 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lizhi Zhang | 1 | 0 | 1.01 |
Yongchao Chen | 2 | 0 | 0.34 |
Lianding Niu | 3 | 0 | 0.68 |
Zhijie Zhao | 4 | 40 | 10.05 |
Xiaowei Han | 5 | 0 | 1.69 |