Multi-class Segmentation with Relative Location Prior

Date

2008

Authors

Gould, Stephen
Rodgers, Jim
Cohen, David
Elidan, Gal
Koller, Daphne

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

Multi-class image segmentation has made significant advances in recent years through the combination of local and global features. One important type of global feature is that of inter-class spatial relationships. For example, identifying "tree" pixels indicates that pixels above and to the sides are more likely to be "sky" whereas pixels below are more likely to be "grass." Incorporating such global information across the entire image and between all classes is a computational challenge as it is image-dependent, and hence, cannot be precomputed. In this work we propose a method for capturing global information from inter-class spatial relationships and encoding it as a local feature. We employ a two-stage classification process to label all image pixels. First, we generate predictions which are used to compute a local relative location feature from learned relative location maps. In the second stage, we combine this with appearance-based features to provide a final segmentation. We compare our results to recent published results on several multi-class image segmentation databases and show that the incorporation of relative location information allows us to significantly outperform the current state-of-the-art.

Description

Keywords

Keywords: Digital image storage; Image processing; Image segmentation; Maps; Appearance-based; Classification processes; Computational challenges; Current state; Global features; Global informations; Image pixels; Local features; Multi-class image segmentation; Rel Multi-class image segmentation; Relative location; Segmentation

Citation

Source

International Journal of Computer Vision

Type

Journal article

Book Title

Entity type

Access Statement

License Rights

Restricted until

2037-12-31