Rojtberg, Pavel ; Kuijper, Arjan (2019)
Real-Time Texturing for 6D Object Instance Detection from RGB Images.
2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). Beijing, China (10.-18. Oct.)
doi: 10.1109/ISMAR-Adjunct.2019.00-25
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
For objected detection, the availability of color cues strongly influences detection rates and is even a prerequisite for many methods. However, when training on synthetic CAD data, this information is not available. We therefore present a method for generating a texture-map from image sequences in real-time. The method relies on 6 degree-of-freedom poses and a 3D-model being available. In contrast to previous works this allows interleaving detection and texturing for upgrading the detector on-the-fly. Our evaluation shows that the acquired texture-map significantly improves detection rates using the LINEMOD [5] detector on RGB images only. Additionally, we use the texture-map to differentiate instances of the same object by surface color.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2019 |
| Autor(en): | Rojtberg, Pavel ; Kuijper, Arjan |
| Art des Eintrags: | Bibliographie |
| Titel: | Real-Time Texturing for 6D Object Instance Detection from RGB Images |
| Sprache: | Englisch |
| Publikationsjahr: | 2019 |
| Veranstaltungstitel: | 2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) |
| Veranstaltungsort: | Beijing, China |
| Veranstaltungsdatum: | 10.-18. Oct. |
| DOI: | 10.1109/ISMAR-Adjunct.2019.00-25 |
| URL / URN: | https://doi.org/10.1109/ISMAR-Adjunct.2019.00-25 |
| Kurzbeschreibung (Abstract): | For objected detection, the availability of color cues strongly influences detection rates and is even a prerequisite for many methods. However, when training on synthetic CAD data, this information is not available. We therefore present a method for generating a texture-map from image sequences in real-time. The method relies on 6 degree-of-freedom poses and a 3D-model being available. In contrast to previous works this allows interleaving detection and texturing for upgrading the detector on-the-fly. Our evaluation shows that the acquired texture-map significantly improves detection rates using the LINEMOD [5] detector on RGB images only. Additionally, we use the texture-map to differentiate instances of the same object by surface color. |
| Freie Schlagworte: | Artificial intelligence (AI) Modeling of physical attributes Recovery of physical attributes Pattern recognition Implementations Interactive systems |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 09 Apr 2020 10:48 |
| Letzte Änderung: | 09 Apr 2020 10:48 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum