Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 2013 | Published
Book Section - Chapter Open

Hierarchical Scene Annotation

Abstract

We present a computer-assisted annotation system, together with a labeled dataset and benchmark suite, for evaluating an algorithm's ability to recover hierarchical scene structure. We evolve segmentation groundtruth from the two-dimensional image partition into a tree model that captures both occlusion and object-part relationships among possibly overlapping regions. Our tree model extends the segmentation problem to encompass object detection, object-part containment, and figure-ground ordering. We mitigate the cost of providing richer groundtruth labeling through a new web-based annotation tool with an intuitive graphical interface for rearranging the region hierarchy. Using precomputed superpixels, our tool also guides creation of user-specified regions with pixel-perfect boundaries. Widespread adoption of this human-machine combination should make the inaccuracies of bounding box labeling a relic of the past. Evaluating the state-of-the-art in fully automatic image segmentation reveals that it produces accurate two-dimension partitions, but does not respect groundtruth object-part structure. Our dataset and benchmark is the first to quantify these inadequacies. We illuminate recovery of rich scene structure as an important new goal for segmentation.

Additional Information

© 2013. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. ONR MURI N00014-10-1-0933 and ARO/JPL-NASA Stennis NAS7.03001 supported this work. Part of Stella Yu's work was supported by NSF CAREER IIS-1257700. Thanks to Alex Jose and Piotr Dollar for helpful discussion on user interfaces for segmentation

Attached Files

Published - paper0084.pdf

Files

paper0084.pdf
Files (9.8 MB)
Name Size Download all
md5:59d061eb05d5d24a8e90cac376ec4f87
9.8 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 20, 2023