Human pose estimation using learnt probabilistic region similarities and partial configurations

Timothy J. Roberts, Stephen J. McKenna, Ian W. Ricketts

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    12 Citations (Scopus)

    Abstract

    A model of human appearance is presented for efficient pose estimation from real-world images. In common with related approaches, a high-level model defines a space of configurations which can be associated with image measurements and thus scored. A search is performed to identify good configuration(s). Such an approach is challenging because the configuration space is high dimensional, the search is global, and the appearance of humans in images is complex due to background clutter, shape uncertainty and texture. The system presented here is novel in several respects. The formulation allows differing numbers of parts to be parameterised and allows poses of differing dimensionality to be compared in a principled manner based upon learnt likelihood ratios. In contrast with current approaches, this allows a part based search in the presence of self occlusion. Furthermore, it provides a principled automatic approach to other object occlusion. View based probabilistic models of body part shapes are learnt that represent intra and inter person variability (in contrast to rigid geometric primitives). The probabilistic region for each part is transformed into the image using the configuration hypothesis and used to collect two appearance distributions for the part's foreground and adjacent background. Likelihood ratios for single parts are learnt from the dissimilarity of the foreground and adjacent background appearance distributions. It is important to note the distinction between this technique and restrictive foreground/background specific modelling. It is demonstrated that this likelihood allows better discrimination of body parts in real world images than contour to edge matching techniques. Furthermore, the likelihood is less sparse and noisy, making coarse sampling and local search more effective. A likelihood ratio for body part pairs with similar appearances is also learnt. Together with a model of inter-part distances this better describes correct higher dimensional configurations. Results from applying an optimization scheme to the likelihood model for challenging real world images are presented.
    Original languageEnglish
    Title of host publicationComputer Vision - ECCV 2004
    Subtitle of host publication8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part IV
    EditorsTomás Pajdla, Jiří Matas
    Place of PublicationBerlin
    PublisherSpringer
    Pages291-303
    Number of pages13
    ISBN (Electronic)9783540246732
    ISBN (Print)9783540219811
    Publication statusPublished - 2004
    Event8th European Conference on Computer Vision - Zofin Palace, Slovansky ostrov, Prague 1, Prague, United Kingdom
    Duration: 11 May 200414 May 2004
    http://cmp.felk.cvut.cz/eccv2004/

    Publication series

    NameLecture notes in computer science
    PublisherSpringer
    Volume3024

    Conference

    Conference8th European Conference on Computer Vision
    Abbreviated titleECCV 2004
    CountryUnited Kingdom
    CityPrague
    Period11/05/0414/05/04
    Internet address

    Fingerprint Dive into the research topics of 'Human pose estimation using learnt probabilistic region similarities and partial configurations'. Together they form a unique fingerprint.

  • Cite this

    Roberts, T. J., McKenna, S. J., & Ricketts, I. W. (2004). Human pose estimation using learnt probabilistic region similarities and partial configurations. In T. Pajdla, & J. Matas (Eds.), Computer Vision - ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part IV (pp. 291-303). (Lecture notes in computer science; Vol. 3024). Springer . http://link.springer.com/chapter/10.1007%2F978-3-540-24673-2_24