Depth Estimation from a Single Image Based on Gradient and Wavelet Analysis

DOI

10.2991/978-94-6463-040-4_129How to use a DOI?

Keywords

Depth estimation; Dense depth map; Sparse depth map; Wavelet analysis

Abstract

Recovering the depth information from a single image is a fundamental problem in computer vision field and has broad application prospects. To solve the problem that the accuracy of the depth recovered from a single image is not high enough, especially when there are several edges very close or intersecting, or when the edge is weak, a novel method to depth measurement is proposed in this article. Four steps are included in our method. Firstly, we obtain depth value of object edge point indirectly by measuring the defocusing degree of the object edge point. The gradient information of the 8 directions of edge point are employed during the process of measuring. Secondly, wavelet analysis is used to judge whether the measured depth value needs to be corrected or not. If necessary, it is corrected according to our formula. A sparse depth map is got when the depth values of all of edge points are measured and are corrected if necessary. Thirdly, the joint bilateral filter is employed to refine the sparse depth map. Lastly, the sparse depth map is extended to a dense depth map by the method of Matting Laplacian. The results of experiments show our method is effective.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lixin He
AU  - Zhi Cheng
AU  - Jing Yang
AU  - Bin Kong
PY  - 2022
DA  - 2022/12/27
TI  - Depth Estimation from a Single Image Based on Gradient and Wavelet Analysis
BT  - Proceedings of the 2022 3rd International Conference on Artificial Intelligence and Education (IC-ICAIE 2022)
PB  - Atlantis Press
SP  - 849
EP  - 857
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-040-4_129
DO  - 10.2991/978-94-6463-040-4_129
ID  - He2022
ER  -