A two-layer Conditional Random Field for the classification of partially occluded objects

07/11/2013
by   Sergey Kosov, et al.
0

Conditional Random Fields (CRF) are among the most popular techniques for image labelling because of their flexibility in modelling dependencies between the labels and the image features. This paper proposes a novel CRF-framework for image labeling problems which is capable to classify partially occluded objects. Our approach is evaluated on aerial near-vertical images as well as on urban street-view images and compared with another methods.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset