Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Effective semantic pixel labelling with convolutional networks and Conditional Random Fields|
Van Den Hengel, A.
|Citation:||Proceedings of the Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2015 / vol.2015-October, pp.36-43|
|Series/Report no.:||IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops|
|Conference Name:||IEEE Conference on Computer Vision and Pattern Recognition (CVPRW) (07 Jun 2015 - 12 Jun 2015 : Boston, MA)|
|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|
|Appears in Collections:||Computer Science publications|
Files in This Item:
|RA_hdl_107901.pdf||Restricted Access||587.38 kB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.