Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Real-time Instance Detection with Fast Incremental Learning

: Bormann, Richard; Wang, Xinjie; Völk, Markus; Kleeberger, Kilian; Lindermayr, Jochen


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Robotics and Automation Society:
IEEE International Conference on Robotics and Automation, ICRA 2021 : May 30 - June 5, 2021, Xi'an, China, (Hybrid Event)
Piscataway, NJ: IEEE, 2021
ISBN: 978-1-7281-9078-5
ISBN: 978-1-7281-9077-8
International Conference on Robotics and Automation (ICRA) <2021, Xian; Online>
Conference Paper
Fraunhofer IPA ()
Künstliche Intelligenz; Greifen; Bilderkennung; Robotik; Entfernungsmessung

Object instance detection is a highly relevant task to several robotic applications such as automated order picking, or household and hospital assistance robots. In these applications, a holistic scene labeling is often not required whereas it is sufficient to find a certain object type of interest, e.g. for picking it up. At the same time, large and continuously changing object sets are characteristic in such applications, requiring efficient model update capabilities from the object detector. Today’s monolithic multi-class detectors do not fulfill this criterion for fast and flexible model updates.This paper introduces InstanceNet, an ensemble of efficient single-class instance detectors capable of fast and incremental adaptation to new object sets. Due to a dynamic sampling-based training strategy, accurate detection models for new objects can be obtained within less than 40 minutes on a consumer GPU while only a small percentage of the existing detection models needs to be updated in a very efficient manner. The new detector has been thoroughly evaluated on the basis of a novel dataset of 100 grocery store objects.