Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Real-time texturing for 6D object instance detection from RGB Images

: Rojtberg, Pavel; Kuijper, Arjan


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
18th IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2019. Adjunct Proceedings : 14-18 October 2019, Beijing, China
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2019
ISBN: 978-1-7281-4765-9
ISBN: 978-1-7281-4766-6
International Symposium on Mixed and Augmented Reality (ISMAR) <18, 2019, Beijing>
Conference Paper
Fraunhofer IGD ()
artificial intelligence (AI); modeling of physical attributes; recovery of physical attributes; pattern recognition; implementation; interactive systems; Lead Topic: Digitized Work; Research Line: Computer graphics (CG); Research Line: Computer vision (CV); Research Line: Modeling (MOD)

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.