In this article, we propose a new semi-supervised method to detect changes occurring in a geographical area after a major event such as war, an earthquake or flood. The detection is made by processing a pair of bi-temporal remotely sensed images of the area under consideration. The proposed method adopts a patch-based approach, where successive pairs of patches from the input images are compared using a deep machine learning method trained with augmented data. Our main contribution consists of proposing an approach for generating a training dataset from unlabeled pair of input images. The genuine training patch-pairs are directly generated from the transformed maps of the image taken before the event, while the impostor patch-pairs are generated by pairing the image taken before the event with any images, from the Internet, with textures that resemble the change shown in the image taken after the event. Several experiments were conducted on pairs of images related to five major events. The obtained subjective results demonstrate the effectiveness of the proposed method.
Change Detection from Unlabeled Remote Sensing Images Using SIAMESE ANN / Hedjam, R.; Abdesselam, A.; Melgani, F.. - (2019), pp. 1530-1533. (Intervento presentato al convegno 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 tenutosi a Convention Center "Pacifico Yokohama", jpn nel 2019) [10.1109/IGARSS.2019.8898672].
Change Detection from Unlabeled Remote Sensing Images Using SIAMESE ANN
Melgani F.
2019-01-01
Abstract
In this article, we propose a new semi-supervised method to detect changes occurring in a geographical area after a major event such as war, an earthquake or flood. The detection is made by processing a pair of bi-temporal remotely sensed images of the area under consideration. The proposed method adopts a patch-based approach, where successive pairs of patches from the input images are compared using a deep machine learning method trained with augmented data. Our main contribution consists of proposing an approach for generating a training dataset from unlabeled pair of input images. The genuine training patch-pairs are directly generated from the transformed maps of the image taken before the event, while the impostor patch-pairs are generated by pairing the image taken before the event with any images, from the Internet, with textures that resemble the change shown in the image taken after the event. Several experiments were conducted on pairs of images related to five major events. The obtained subjective results demonstrate the effectiveness of the proposed method.File | Dimensione | Formato | |
---|---|---|---|
08898672 (1).pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
4.32 MB
Formato
Adobe PDF
|
4.32 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione