 |
    |
Geodesic Object Proposals
Philipp Krähenbühl1 and Vladlen Koltun2
1Stanford University, USA
2Adobe Research, USA
Abstract. We present an approach for identifying a set of candidate objects in a given image. This set of candidates can be used for object recognition, segmentation, and other object-based image parsing tasks. To generate the proposals, we identify critical level sets in geodesic distance transforms computed for seeds placed in the image. The seeds are placed by specially trained classifiers that are optimized to discover objects. Experiments demonstrate that the presented approach achieves significantly higher accuracy than alternative approaches, at a fraction of the computational cost.
Keywords: perceptual organization, grouping
LNCS 8693, p. 725 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014