Advertisement

Visual System Examination Using Synthetic Scenarios

  • Robert Manthey
  • Rico Thomanek
  • Christian Roschke
  • Tony Rolletschke
  • Benny Platte
  • Marc Ritter
  • Danny Kowerko
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 903)

Abstract

Many systems use visual devices to detect, inspect and analyze persons, scenes, and properties of objects. Often, they use samples to learn relevant indicators to reach a high level of quality of the appropriated operation. Nevertheless, collecting samples and annotate the relevant parts may be a hard, expensive and error prone task in same fields of use. To overcome this problem we create a system to generate synthetic scenarios based on predefined and exact definitions of the content as well as the sample production process. To demonstrate the usability we apply a scenario with a humanoid with known activity and with various environment objects to different systems for visual detection and analysis.

Keywords

System evaluation System inspection Dataset generation Human detection Human activity recognition Usability testing 

Notes

Acknowledgements

This work was partially accomplished within the project localizeIT (funding code 03IPT608X) funded by the Federal Ministry of Education and Research (BMBF, Germany) in the program of Entrepreneurial Regions InnoProfile-Transfer.

References

  1. 1.
    Hägele, M., Schaaf, W., Helms, E.: Robot assistants at manual workplaces: effective cooperation and safety aspects. In: Proceedings of the 33rd International Symposium on Robotics, pp. 1–6 (2002)Google Scholar
  2. 2.
    Germa, T., Lerasle, F., Danes, P., Brethes, L.: Human/robot visual interaction for a tour-guide robot. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3448–3453. IEEE Press (2007)Google Scholar
  3. 3.
    Bilenko, M., Kamath, B., Mooney, R.J.: Adaptive blocking: learning to scale up record linkage. In: Universal Access in Human-Computer Interaction, pp. 460–467. Springer, Heidelberg (2016)Google Scholar
  4. 4.
    Manthey, R., Conrad, C., Ritter, M.: A framework for generation of testsets for recent multimedia workflows. In: Proceedings of the 6th IEEE International Conference on Data Mining, pp. 87–96. IEEE Press (2006)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Robert Manthey
    • 1
  • Rico Thomanek
    • 2
  • Christian Roschke
    • 2
  • Tony Rolletschke
    • 2
  • Benny Platte
    • 2
  • Marc Ritter
    • 3
  • Danny Kowerko
    • 1
  1. 1.Junior Professorship Media Computing, Faculty of Computer ScienceTechnical University of ChemnitzChemnitzGermany
  2. 2.Faculty Media SciencesUniversity of Applied SciencesMittweidaGermany
  3. 3.Faculty Applied Computer Sciences and BiosciencesUniversity of Applied SciencesMittweidaGermany

Personalised recommendations