Very-high-resolution (VHR) multi-temporal images are important in remote sensing to monitor the dynamics of the Earth surface. Image semantic segmentation classifies pixels and assigns them label from meaningful object groups. It has been extensively studied in context of single image analysis, however not explored for multi-temporal one. In this paper we propose to extend supervised semantic segmentation to the unsupervised joint segmentation of multi-temporal images. The proposed method processes multi-temporal images by separately feeding them to a deep network comprising of trainable convolutional layers. The training process does not involve any external label. Segmentation labels are obtained from argmax classification of the final layer. Multi-temporal segmentation labels and weights of the trainable layers are jointly optimized in iterations. We tested the method on a VHR dataset from Trento, Italy. Both quantitative and qualitative results demonstrated the effectiveness of the proposed approach.
A Novel Approach to Unsupervised Segmentation of Multitemporal VHR Images based on Deep Learning / Saha, Sudipan; Mou, Lichao; Qiu, Chunping; Zhu, Xiao Xiang; Bovolo, Francesca; Bruzzone, Lorenzo. - ELETTRONICO. - (2020), pp. 688-691. ((Intervento presentato al convegno IGARSS tenutosi a Waikoloa, HI, USA - Virtual Meeting nel 26 Sept.-2 Oct. 2020 [10.1109/IGARSS39084.2020.9324651].
A Novel Approach to Unsupervised Segmentation of Multitemporal VHR Images based on Deep Learning
Saha, Sudipan;Bovolo, Francesca;Bruzzone, Lorenzo
2020-01-01
Abstract
Very-high-resolution (VHR) multi-temporal images are important in remote sensing to monitor the dynamics of the Earth surface. Image semantic segmentation classifies pixels and assigns them label from meaningful object groups. It has been extensively studied in context of single image analysis, however not explored for multi-temporal one. In this paper we propose to extend supervised semantic segmentation to the unsupervised joint segmentation of multi-temporal images. The proposed method processes multi-temporal images by separately feeding them to a deep network comprising of trainable convolutional layers. The training process does not involve any external label. Segmentation labels are obtained from argmax classification of the final layer. Multi-temporal segmentation labels and weights of the trainable layers are jointly optimized in iterations. We tested the method on a VHR dataset from Trento, Italy. Both quantitative and qualitative results demonstrated the effectiveness of the proposed approach.File | Dimensione | Formato | |
---|---|---|---|
09324651.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.24 MB
Formato
Adobe PDF
|
1.24 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione