University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > A joint part- and pixel-wise approach to human pose estimation

A joint part- and pixel-wise approach to human pose estimation

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending

For an object recognition task two standard, but disparate, approaches have developed in the field: the first is the part based approach for layout type problems, involving optimising an articulated pictorial structure; the second is the pixel based approach for image labelling involving optimising a random field graph defined on the image.

In this work, we combine these two models in a principled way in one optimisation problem inheriting the advantages of both of them. We apply this formulation to the problem of detecting humans and estimating their 2D pose in single images. In particular, handling cases of partial visibility where some limbs may be occluded, a person partially occluding another, self-occluding or where an image is truncated. Inference method on this joint model finds the set of instances of persons in an image, the location of their visible joints, and a pixel-wise instance and body part labelling.

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity