336 0

Multi-Instance Object Segmentation with Occlusion Handling

Title
Multi-Instance Object Segmentation with Occlusion Handling
Author
Yang, Ming-hsuan
Keywords
Shape; Proposals; Image segmentation; Feature extraction; Object segmentation; Semantics; Computer architecture
Issue Date
2015-06
Publisher
IEEE
Citation
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 3470-3478
Abstract
We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottomup schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.
URI
http://ieeexplore.ieee.org/document/7298969/?isnumber=7298593&arnumber=7298969http://hdl.handle.net/20.500.11754/25640
ISBN
978-1-4673-6964-0
ISSN
1063-6919
DOI
10.1109/CVPR.2015.7298969
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE