Comparing two- and three-view computer vision
To reconstruct the points in three dimensional space, we need at least two images. In this paper we compared two different methods: the first uses only two images, the second one uses three. During the research we measured how camera resolution, camera angles and camera distances influence the numbe...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2019-08-01
|
| Series: | Acta Universitatis Sapientiae: Informatica |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/ausi-2019-0003 |
| id |
doaj-bfa33151deb0478c9887ec2082716d84 |
|---|---|
| record_format |
Article |
| spelling |
doaj-bfa33151deb0478c9887ec2082716d842021-09-06T19:41:25ZengSciendoActa Universitatis Sapientiae: Informatica2066-77602019-08-01111415110.2478/ausi-2019-0003ausi-2019-0003Comparing two- and three-view computer visionKucsván Zsolt Levente0Sapientia Hungarian University of Transylvania, Cluj-Napoca; Dept. of Mathematics and Informatics, Târgu Mureş, RomaniaTo reconstruct the points in three dimensional space, we need at least two images. In this paper we compared two different methods: the first uses only two images, the second one uses three. During the research we measured how camera resolution, camera angles and camera distances influence the number of reconstructed points and the dispersion of them. The paper presents that using the two-view method, we can reconstruct significantly more points than using the other one, but the dispersion of points is smaller if we use the three-view method. Taking into consideration the different camera settings, we can say that both the two- and three-view method behaves the same, and the best parameters are also the same for both methods.https://doi.org/10.2478/ausi-2019-0003i.4.m68r15computer visiontriangulationreconstruction |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Kucsván Zsolt Levente |
| spellingShingle |
Kucsván Zsolt Levente Comparing two- and three-view computer vision Acta Universitatis Sapientiae: Informatica i.4.m 68r15 computer vision triangulation reconstruction |
| author_facet |
Kucsván Zsolt Levente |
| author_sort |
Kucsván Zsolt Levente |
| title |
Comparing two- and three-view computer vision |
| title_short |
Comparing two- and three-view computer vision |
| title_full |
Comparing two- and three-view computer vision |
| title_fullStr |
Comparing two- and three-view computer vision |
| title_full_unstemmed |
Comparing two- and three-view computer vision |
| title_sort |
comparing two- and three-view computer vision |
| publisher |
Sciendo |
| series |
Acta Universitatis Sapientiae: Informatica |
| issn |
2066-7760 |
| publishDate |
2019-08-01 |
| description |
To reconstruct the points in three dimensional space, we need at least two images. In this paper we compared two different methods: the first uses only two images, the second one uses three. During the research we measured how camera resolution, camera angles and camera distances influence the number of reconstructed points and the dispersion of them. The paper presents that using the two-view method, we can reconstruct significantly more points than using the other one, but the dispersion of points is smaller if we use the three-view method. Taking into consideration the different camera settings, we can say that both the two- and three-view method behaves the same, and the best parameters are also the same for both methods. |
| topic |
i.4.m 68r15 computer vision triangulation reconstruction |
| url |
https://doi.org/10.2478/ausi-2019-0003 |
| work_keys_str_mv |
AT kucsvanzsoltlevente comparingtwoandthreeviewcomputervision |
| _version_ |
1717766259014107136 |