Constant elasticity of substitution function based RANSAC for image stitching
| Autor: | Zhuang Shengbin, Cao Lin, Guo Yanan |
|---|---|
| Jazyk: | English<br />French |
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | MATEC Web of Conferences, Vol 336, p 06032 (2021) |
| Druh dokumentu: | article |
| ISSN: | 2261-236X 20213360 |
| DOI: | 10.1051/matecconf/202133606032 |
| Popis: | Feature matching is very important in image stitching. RANSAC algorithm is a representative algorithm for feature matching. However, RANSAC still has many shortcomings such as a large number of iterations, a large computational complexity and cannot completely eliminate mismatches. To address above problem, in this paper, we propose a novel method termed constant elasticity of substitution function based RANSAC (CES-RANSAC) for image stitching. Specifically, CES-RANSAC improves the RANSAC algorithm by constructing a utility function, optimizing the boundary of the utility function, calculating Cobb-Douglas coefficients. It also introduces Lindahl equilibrium to derive the return value t to help eliminate mismatches. Experiments show that compared with the traditional RANSAC algorithm, CES-RANSAC has improved matching accuracy and increased computational efficiency, which further improves the efficiency of the image matching algorithm. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|