TY - JOUR
T1 - Spatial and Structured SVM for Multilabel Image Classification
AU - Koda, Satoru
AU - Zeggada, Abdallah
AU - Melgani, Farid
AU - Nishii, Ryuei
N1 - Publisher Copyright:
© 1980-2012 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/10
Y1 - 2018/10
N2 - We describe a novel multilabel classification approach based on a support vector machine (SVM) for the extremely high-resolution remote sensing images. Its underlying ideas consist to: 1) exploit inter-label relationships by means of a structured SVM and 2) incorporate spatial contextual information by adding to the cost function a term that encourages spatial smoothness into the structural SVM optimization process. The resulting formulation appears as an extension of the traditional SVM learning, in which our proposed model integrates the output structure and spatial information simultaneously during the training. Numerical experiments conducted on two different UAV- and airborne-acquired sets of images show the interesting properties of the proposed model, in particular, in terms of classification accuracy.
AB - We describe a novel multilabel classification approach based on a support vector machine (SVM) for the extremely high-resolution remote sensing images. Its underlying ideas consist to: 1) exploit inter-label relationships by means of a structured SVM and 2) incorporate spatial contextual information by adding to the cost function a term that encourages spatial smoothness into the structural SVM optimization process. The resulting formulation appears as an extension of the traditional SVM learning, in which our proposed model integrates the output structure and spatial information simultaneously during the training. Numerical experiments conducted on two different UAV- and airborne-acquired sets of images show the interesting properties of the proposed model, in particular, in terms of classification accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85047600143&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047600143&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2018.2828862
DO - 10.1109/TGRS.2018.2828862
M3 - Article
AN - SCOPUS:85047600143
VL - 56
SP - 5948
EP - 5960
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
SN - 0196-2892
IS - 10
M1 - 8363005
ER -