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 November 2011 | public
Book Section - Chapter

Object Detection and Segmentation from Joint Embedding of Parts and Pixels

Abstract

We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This framework serves as a perceptual organization stage that integrates information from low-level image cues with that of high-level part detectors. Pixels and parts each appear as nodes in a graph whose edges encode both affinity and ordering relationships. We derive a generalized eigen-problem from this graph and read off an interpretation of the image from the solution eigenvectors. Combining an off-the-shelf top-down part-based person detector with our low-level cues and grouping formulation, we demonstrate improvements to object detection and segmentation.

Additional Information

© 2011 IEEE. ONR MURI N00014-06-1-0734, ONR MURI 1015 G NA127, and ARL Cooperative Agreement W911NF-10-2-0016 supported this work. Stella X. Yu was funded by NSF CAREER IIS-0644204 and a Clare Boothe Luce Professorship. Thanks to litendra Malik for suggesting poselets as a figure/ground cue and Lubomir Bourdev for providing poselet code.

Additional details

Created:
August 19, 2023
Modified:
October 18, 2023