CoSPE: Computer vision based Scene Parameter Estimation / Vision-baseret estimering af sceneparametre

    Projektdetaljer

    Beskrivelse

    CoSPE started in 2005 and is a 7 year research project funded by the Danish Technical Research Council. The project aims at estimating light source and material properties, i.e., illumination conditions and reflectances, given an image or a sequence of images of a scene. The approach is to exploit what we call a “hypothesize-synthesize-correlate-update” verification strategy. This is a special version of the classical “predict-match-update” loop in model-based control systems where the state of a system is predicted from a model, the predicted state is matched to the measured state and any discrepancies are used to update the model. The “hypothesize-synthesize-correlate-update” strategy will combine information from two of the three image forming components (illumination, reflectance, geometry) with actual image information and use this combination to generate information concerning the third component. Applications are, e.g., in synthesizing artificial images of real world environments that look photorealistic. This requires an accurate 3D description of the scene to be imaged including light source and material properties. Small inaccuracies, such as a too sharp shadow or a too glossy reflection on an object, can make the images look artificial to human observers. The project results will also be very valuable to Augmented Reality systems, where virtual objects are inserted into real scenes. This can only be done realistically if the real scene illumination conditions are known. Another important application is in robust computer vision systems, like autonomous outdoor vehicle navigation. Funded by the Danish Technical Research Council, 2005-2012. (Claus B. Madsen, Hans J. Andersen, Erik Granum)
    StatusAfsluttet
    Effektiv start/slut dato01/01/200501/06/2012

    Finansiering

    • <ingen navn>

    Fingerprint Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.

  • Aktiviteter

    • 1 Foredrag og præsentationer i privat eller offentlig virksomhed

    Computerspillenes Grafik: Behind The Scenes

    Claus B. Madsen (Foredragsholder)

    24 maj 2012

    Aktivitet: Foredrag og mundtlige bidragForedrag og præsentationer i privat eller offentlig virksomhed

    Projekter

    Koldinghus Augmented: The Castle Chapel

    Madsen, C. B., Stenholt, R., Skotte, P. & Madsen, J. B.

    Koldinghus Museum

    01/01/201231/12/2012

    Projekter: ProjektForskning

  • Koldinghus Augmented: The Walls Remember

    Madsen, C. B., Stenholt, R., Skotte, P. & Madsen, J. B.

    01/09/201101/03/2012

    Projekter: ProjektForskning

    Fil

    Publikation

    • 12 Konferenceartikel i proceeding
    • 2 Bidrag til bog/antologi
    • 1 Konferenceabstrakt i proceeding
    • 1 Konferenceartikel i tidsskrift

    Estimating Outdoor Illumination Conditions Based on Detection of Dynamic Shadows

    Madsen, C. B. & Lal, B. B., 1 mar. 2013, Computer Vision, Imaging and Computer Graphics: Theory and Applications. Csurka, G., Kraus, M., Mestetskiy, L., Richard, P. & Braz, J. (red.). Springer Publishing Company, s. 33-52 20 s. (Communications in Computer and Information Science, Bind 274).

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingBidrag til bog/antologiForskningpeer review

    Fil
  • 7 Citationer (Scopus)
    605 Downloads (Pure)

    Outdoor Illumination Estimation in Image Sequences for Augmented Reality

    Madsen, C. B. & Lal, B. B., 5 mar. 2011, Proceedings of GRAPP 2011: International Conference on Computer Graphics Theory and Applications. Richard, P. & Braz, J. (red.). Portugal: Institute for Systems and Technologies of Information, Control and Communication, s. 129 - 139 11 s.

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

    Fil
  • 8 Citationer (Scopus)
    279 Downloads (Pure)

    Probeless Illumination Estimation for Outdoor Augmented Reality

    Madsen, C. B. & Lal, B. B., 2010, Augmented Reality. Maad, S. (red.). Vienna, Austria: INTECH, 16 s.

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingBidrag til bog/antologiForskning

    Åben adgang
    Fil
    485 Downloads (Pure)