Deep learning for multi-label land cover classification

This item is provided by the institution :
Technical University of Crete   

Repository :
Institutional Repository Technical University of Crete   

see the original item page
in the repository's web site and access all digital files if the item*



Deep learning for multi-label land cover classification (EN)

Ζερβακης Μιχαλης (EL)
Zervakis Michalis (EN)
Panagiotis Tsakalides (EN)
Konstantinos Karalas (EN)
Grigorios Tsagkatakis (EN)

conferenceItem
poster

2015


Whereas single class classification has been a highly active topic in optical remote sensing, much less effort has been given to the multi-label classification framework, where pixels are associated with more than one labels, an approach closer to the reality than single-label classification. Given the complexity of this problem, identifying representative features extracted from raw images is of paramount importance. In this work, we investigate feature learning as a feature extraction process in order to identify the underlying explanatory patterns hidden in low-level satellite data for the purpose of multi-label classification. Sparse auto-encoders composed of a single hidden layer, as well as stacked in a greedy layer-wise fashion formulate the core concept of our approach. The results suggest that learning such sparse and abstract representations of the features can aid in both remote sensing and multi-label problems. The results presented in the paper correspond to a novel real dataset of annotated spectral imagery naturally leading to the multi-label formulation. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only. (EN)

Image and Signal Processing for Remote Sensing XXI (EL)

English

Πολυτεχνείο Κρήτης (EL)
Technical University of Crete (EN)




*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)