Enhancing Metric Perception with RGB-D Camera

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8021)


Metric measurement of environment has fundamental role in tasks such as interior design and plant maintenance. Conventional methods for these tasks suffer from high development cost or unstability. We propose a mobile metric perception enhancement system which focuses on interactivity through user locomotion. The proposed system overlays geometric annotations in real-time on a tablet device. The annotation is generated from RGB-D camera in per-frame basis, alleviating the object recognition problem by effectively utilizing processing power of human. We show a few illustrative cases where the system is tested, and discuss correctness of annotations.


Augmented Reality Augmented Human Mobile Device RGB-D Camera Geometric Annotation Per-frame Processing 


  1. 1.
    Carmigniani, J., Furht, B., Anisetti, M., Ceravolo, P., Damiani, E., Ivkovic, M.: Augmented reality technologies, systems and applications. Multimedia Tools and Applications 51, 341–377 (2011)CrossRefGoogle Scholar
  2. 2.
    Aulinas, J., Petillot, Y.R., Salvi, J., Lladó, X.: The SLAM problem: a survey. In: Catalonian Conference on AI, pp. 363–371 (2008)Google Scholar
  3. 3.
    von Gioi, R.G., Jakubowicz, J., Morel, J.-M., Randall, G.: LSD: a Line Segment Detector. Image Processing On Line (2012)Google Scholar
  4. 4.
    Mistry, P., Maes, P.: Sixthsense: a wearable gestural interface. In: ACM SIGGRAPH ASIA 2009 Sketches. SIGGRAPH ASIA 2009, pp. 11:1–11:1. ACM, New York (2009)Google Scholar
  5. 5.
    Khoshelham, K., Elberink, S.O.: Accuracy and resolution of kinect depth data for indoor mapping applications. Sensors 12(2), 1437–1454 (2012)CrossRefGoogle Scholar
  6. 6.
    Adelson, E.H.: Lightness perception and lightness illusion (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Graduate School of Energy ScienceKyoto UniversityJapan

Personalised recommendations