Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/83157
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Efficient 3D scene labeling using fields of trees |
Author: | Kahler, O. Reid, I. |
Citation: | Proceedings 2013 IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 1-8 December 2013: pp.3064-3071 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2013 |
Series/Report no.: | IEEE International Conference on Computer Vision |
ISBN: | 9781479928392 |
ISSN: | 1550-5499 |
Conference Name: | International Conference on Computer Vision (2013 : Sydney, Australia)) |
Statement of Responsibility: | Olaf Kähler, Ian Reid |
Abstract: | We address the problem of 3D scene labeling in a structured learning framework. Unlike previous work which uses structured Support Vector Machines, we employ the recently described Decision Tree Field and Regression Tree Field frameworks, which learn the unary and binary terms of a Conditional Random Field from training data. We show this has significant advantages in terms of inference speed, while maintaining similar accuracy. We also demonstrate empirically the importance for overall labeling accuracy of features that make use of prior knowledge about the coarse scene layout such as the location of the ground plane. We show how this coarse layout can be estimated by our framework automatically, and that this information can be used to bootstrap improved accuracy in the detailed labeling. |
Rights: | © 2013 IEEE |
DOI: | 10.1109/ICCV.2013.380 |
Published version: | http://dx.doi.org/10.1109/iccv.2013.380 |
Appears in Collections: | Aurora harvest Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_83157.pdf Restricted Access | Restricted Access | 719.15 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.