Sub-linear Indexing for Large Scale Object Recognition
Czech Technical University, Prague
Friday, June 16, 2006
JEC 3117 - 4:00 p.m. to 5:00 p.m.
Refreshments at 3:30 p.m.
Realistic approaches to large scale object recognition, i.e. for
detection and localisation of hundreds or more objects, must support
sub-linear time indexing. A method capable of recognising one of N
objects in log(N) time will be presented. The "visual memory" is
organised as a binary decision tree that is built to minimise average
time to decision. Leaves of the tree represent a few local patches, and
each non-terminal node is associated with a weak classifier. In the
recognition phase, a single invariant measurement on a query patch
decides in which subtree a corresponding patch is sought. The method
possesses all the strengths of local affine region methods robustness
to background clutter, occlusion, and large changes of viewpoints.
Experimentally we show that it supports near real-time recognition of
hundreds of objects with state-of-the-art recognition rates. After the
test image is processed (in a second on a current PCs), the recognition
via indexing into the visual memory requires milliseconds.
Hosted by: Chuck Stewart (x6731)