Mixing deep learning with classical vision for object recognition
Authors:
- Maciej Stefańczyk,
- Tomasz Bocheński
Abstract
Nowadays, when one needs a system for image recognition, it is mostly a matter of finding pre-trained CNN and, sometimes, adding additional training based on transferred knowledge. Accurate 6-DOF object localization in the image is a more laborious task and requires more complex training data to be available. On the other hand, if we know the model of the object, it is straightforward to acquire its pose from the image (RGB or RGB-D). In this paper, we try to show the advantages of mixing deep learning object recognition/detection with classical 6-DOF pose estimation algorithms, with a focus on applications in service robotics
- Record ID
- WUTa2932b983f2e4cfdb1de9b8ec3084330
- Author
- Journal series
- Journal of WSCG, ISSN 1213-6972, e-ISSN 1213-6964, [1213-6964, 1213-6980]
- Issue year
- 2020
- Vol
- 28
- No
- 1-2
- Pages
- 147-154
- Publication size in sheets
- 0.50
- Keywords in English
- CNN object detection, VGG16, ResNet50, 6-DOF pose estimation, RanSaC, ICP, RGB-D
- ASJC Classification
- ; ;
- DOI
- DOI:10.24132/JWSCG.2020.28.18 Opening in a new tab
- URL
- http://wscg.zcu.cz/wscg2020/journal/G89.pdf Opening in a new tab
- Project (archive)
- Using spherical cameras in service robotics. Project leader: Stefańczyk Maciej, , end date 31-12-2018, dziek MStef 2018, CompletedWEiTI
- Language
- (en) English
- File
-
- File: 1
- Stefanczyk Bochenski WSCG20.pdf
-
- Score (nominal)
- 40
- Score source
- journalList
- Score
- = 40.0, 17-05-2022, ArticleFromJournal
- Publication indicators
- = 1; : 2018 = 0.425
- Citation count
- 1
- Uniform Resource Identifier
- https://repo.pw.edu.pl/info/article/WUTa2932b983f2e4cfdb1de9b8ec3084330/
- URN
urn:pw-repo:WUTa2932b983f2e4cfdb1de9b8ec3084330
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or PerishOpening in a new tab system.