Articulated Object Recognition
This work is supported by the
NSF CAREER Award program and AFOSR MURI initiavite.
- The Problem:
- We give Human-Shape Contour Model and want to find it in
an image :
------>
We investigate the problems of recognizing and finding articulated and
deformable objects. In particular we study human arm and leg
articulations, restricting the class of objects to the one that can be
represented by the silhouette, i.e., with a contour
representation. Our aims are applications to aid video editing,
database content retrieval, animation and medical imaging. In real
world, articulated shapes are encountered almost everywhere. However,
most of the (invariant-based) object recognition systems do not have
the capability to recognize articulated or deformable targets. Methods
based on multiple views are interesting but, can not account for large
deformations or articulations. They lack a method that can realize
the similarity between an object and its articulated/deformed
counterparts.
- Our Approach:
-------->
We propose a deconstruction framework to recognize and find
articulated objects. The deconstruction view of recognition naturally
decomposes the problem of finding an object in an image, into the one
of (i) extracting key features in an image, (ii) detecting key points
in the models, (iii) segmenting an image, and (iv) comparing
shapes. All of these subproblems can not be resolved
independently. Together, they reconstruct the object in the image. For
details, see venice.ps.gz and deconstruct.ps.gz.