Multitask SVM learning for remote sensing data classification

Jose M. Leiva-Murillo; Luis Gómez-Chova; Gustavo Camps-Valls

doi:10.1117/12.865045

22 October 2010 Multitask SVM learning for remote sensing data classification

Jose M. Leiva-Murillo, Luis Gómez-Chova, Gustavo Camps-Valls

Proceedings Volume 7830, Image and Signal Processing for Remote Sensing XVI; 78300L (2010) https://doi.org/10.1117/12.865045
Event: SPIE Remote Sensing, 2010, Toulouse, France

Abstract

Many remote sensing data processing problems are inherently constituted by several tasks that can be solved either individually or jointly. For instance, each image in a multitemporal classification setting could be taken as an individual task but relation to previous acquisitions should be properly considered. In such problems, different modalities of the data (temporal, spatial, angular) gives rise to changes between the training and test distributions, which constitutes a difficult learning problem known as covariate shift. Multitask learning methods aim at jointly solving a set of prediction problems in an efficient way by sharing information across tasks. This paper presents a novel kernel method for multitask learning in remote sensing data classification. The proposed method alleviates the dataset shift problem by imposing cross-information in the classifiers through matrix regularization. We consider the support vector machine (SVM) as core learner and two regularization schemes are introduced: 1) the Euclidean distance of the predictors in the Hilbert space; and 2) the inclusion of relational operators between tasks. Experiments are conducted in the challenging remote sensing problems of cloud screening from multispectral MERIS images and for landmine detection.

Citation Download Citation

Jose M. Leiva-Murillo, Luis Gómez-Chova, and Gustavo Camps-Valls "Multitask SVM learning for remote sensing data classification", Proc. SPIE 7830, Image and Signal Processing for Remote Sensing XVI, 78300L (22 October 2010); https://doi.org/10.1117/12.865045

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available