Header

UZH-Logo

Maintenance Infos

Solving structured segmentation of aerial images as puzzles


Marcos, Diego; Volpi, Michele; Tuia, Devis (2016). Solving structured segmentation of aerial images as puzzles. In: IEEE International Geoscience & Remote Sensing Symposium IGARSS, Beijing (China), 10 July 2016 - 15 July 2016, 3346-3349.

Abstract

Traditional approaches to structured semantic segmentation employ appearance-based classifiers to provide a class likelihood at each spatial location and then post-process it with Markov Random Fields (MRF) to enforce label smoothness and structure in the output space. The spatial support for such techniques is usually a patch of pixels, which makes the prediction over-smoothed because the borders of objects are not explicitly taken into account. This is further exacerbated by MRF post-processing employing the standard Potts model, which tends to further over-smooth predictions at boundaries. In this paper, we propose a different but related approach: we optimize an energy function finding the optimal combination of small ground truth (GT) tiles from training data over predictions at test time, effectively solving a puzzle. We optimize over a first configuration given by a Convolutional Neural Network (CNN) output.

Abstract

Traditional approaches to structured semantic segmentation employ appearance-based classifiers to provide a class likelihood at each spatial location and then post-process it with Markov Random Fields (MRF) to enforce label smoothness and structure in the output space. The spatial support for such techniques is usually a patch of pixels, which makes the prediction over-smoothed because the borders of objects are not explicitly taken into account. This is further exacerbated by MRF post-processing employing the standard Potts model, which tends to further over-smooth predictions at boundaries. In this paper, we propose a different but related approach: we optimize an energy function finding the optimal combination of small ground truth (GT) tiles from training data over predictions at test time, effectively solving a puzzle. We optimize over a first configuration given by a Convolutional Neural Network (CNN) output.

Statistics

Altmetrics

Downloads

1 download since deposited on 08 Feb 2017
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:15 July 2016
Deposited On:08 Feb 2017 15:52
Last Modified:26 Mar 2017 05:41
Publisher:Institute of Electrical and Electronics Engineers
Series Name:IEEE International Geoscience and Remote Sensing Symposium Proceedings
ISSN:2153-6996
ISBN:978-1-5090-3332-4
Additional Information:Proceedings
Publisher DOI:https://doi.org/10.1109/IGARSS.2016.7729865

Download

Preview Icon on Download
Content: Published Version
Language: English
Filetype: PDF - Registered users only
Size: 234kB
View at publisher

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations