Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm
In computer vision, estimating geometric relations between two different views of the same scene has great importance due to its applications in 3D reconstruction, object recognition and digitization, image registration, pose retrieval, visual tracking and more. The Random Sample Consensus (RANSAC)...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/9/4/101 |
| _version_ | 1797544357840027648 |
|---|---|
| author | Alan López-Martínez Francisco Javier Cuevas |
| author_facet | Alan López-Martínez Francisco Javier Cuevas |
| author_sort | Alan López-Martínez |
| collection | DOAJ |
| description | In computer vision, estimating geometric relations between two different views of the same scene has great importance due to its applications in 3D reconstruction, object recognition and digitization, image registration, pose retrieval, visual tracking and more. The Random Sample Consensus (RANSAC) is the most popular heuristic technique to tackle this problem. However, RANSAC-like algorithms present a drawback regarding either the tuning of the number of samples and the threshold error or the computational burden. To relief this problem, we propose an estimator based on a metaheuristic, the Teaching–Learning-Based Optimization algorithm (TLBO) that is motivated by the teaching–learning process. We use the TLBO algorithm in the problem of computing multiple view relations given by the homography and the fundamental matrix. To improve the method, candidate models are better evaluated with a more precise objective function. To validate the efficacy of the proposed approach, several tests, and comparisons with two RANSAC-based algorithms and other metaheuristic-based estimators were executed. |
| first_indexed | 2024-03-10T13:59:19Z |
| format | Article |
| id | doaj.art-a626737dc6f04ee5b978b8a687590c2d |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T13:59:19Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-a626737dc6f04ee5b978b8a687590c2d2023-11-21T01:20:30ZengMDPI AGComputers2073-431X2020-12-019410110.3390/computers9040101Multiple View Relations Using the Teaching and Learning-Based Optimization AlgorithmAlan López-Martínez0Francisco Javier Cuevas1Optical Metrology Division, Centro de Investigaciones en Óptica. A.C., Lomas del Bosque 115, León 37150, Guanajuato, MexicoOptical Metrology Division, Centro de Investigaciones en Óptica. A.C., Lomas del Bosque 115, León 37150, Guanajuato, MexicoIn computer vision, estimating geometric relations between two different views of the same scene has great importance due to its applications in 3D reconstruction, object recognition and digitization, image registration, pose retrieval, visual tracking and more. The Random Sample Consensus (RANSAC) is the most popular heuristic technique to tackle this problem. However, RANSAC-like algorithms present a drawback regarding either the tuning of the number of samples and the threshold error or the computational burden. To relief this problem, we propose an estimator based on a metaheuristic, the Teaching–Learning-Based Optimization algorithm (TLBO) that is motivated by the teaching–learning process. We use the TLBO algorithm in the problem of computing multiple view relations given by the homography and the fundamental matrix. To improve the method, candidate models are better evaluated with a more precise objective function. To validate the efficacy of the proposed approach, several tests, and comparisons with two RANSAC-based algorithms and other metaheuristic-based estimators were executed.https://www.mdpi.com/2073-431X/9/4/101epipolar geometryfundamental matrixhomographyRANSACmetaheuristicsTLBO |
| spellingShingle | Alan López-Martínez Francisco Javier Cuevas Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm Computers epipolar geometry fundamental matrix homography RANSAC metaheuristics TLBO |
| title | Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm |
| title_full | Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm |
| title_fullStr | Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm |
| title_full_unstemmed | Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm |
| title_short | Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm |
| title_sort | multiple view relations using the teaching and learning based optimization algorithm |
| topic | epipolar geometry fundamental matrix homography RANSAC metaheuristics TLBO |
| url | https://www.mdpi.com/2073-431X/9/4/101 |
| work_keys_str_mv | AT alanlopezmartinez multipleviewrelationsusingtheteachingandlearningbasedoptimizationalgorithm AT franciscojaviercuevas multipleviewrelationsusingtheteachingandlearningbasedoptimizationalgorithm |