Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Effective semantic pixel labelling with convolutional networks and Conditional Random Fields
Author: Paisitkriangkrai, S.
Sherrah, J.
Janney, P.
Van Den Hengel, A.
Citation: Conference on Computer Vision and Pattern Recognition Workshops IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops, 2015, vol.2015-October, pp.36-43
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISBN: 9781467367592
ISSN: 2160-7508
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (CVPRW) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)
Statement of
Sakrapee Paisitkriangkrai, Jamie Sherrah, Pranam Janney, and Anton Van Den Hengel
Abstract: Large amounts of available training data and increasing computing power have led to the recent success of deep convolutional neural networks (CNN) on a large number of applications. In this paper, we propose an effective semantic pixel labelling using CNN features, hand-crafted features and Conditional Random Fields (CRFs). Both CNN and hand-crafted features are applied to dense image patches to produce per-pixel class probabilities. The CRF infers a labelling that smooths regions while respecting the edges present in the imagery. The method is applied to the ISPRS 2D semantic labelling challenge dataset with competitive classification accuracy.
Rights: © 2015 IEEE
DOI: 10.1109/CVPRW.2015.7301381
Published version:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access587.38 kBAdobe PDFView/Open

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