Deep learning-based unsupervised change detection (CD) methods compare a prechange and a postchange image in deep feature space and require precise knowledge of the event date for selecting proper pre-/post-change images. However, in many applications changes may occur gradually over a span of time making pre-/post-dates difficult to establish or prior knowledge of event date is unknown. On the other hand, deep learning-based time-series analysis methods are generally supervised. Considering such scenarios, we propose a novel unsupervised deep learning-based method to detect changes in an image time-series. The method does not make any assumption on the date of the occurrence of the change event. It treats CD as an anomaly detection problem by exploiting multilayer long short term memory (LSTM) network to learn a representation of the time series. The proposed method ingests a shuffled time series and uses an encoder-decoder LSTM model to rearrange the input sequence in correct order. While the model fails to rearrange the changed pixels, unchanged data can be rearranged in the correct order. This enables the identification of the changed pixels. To show the effectiveness of the proposed method, we tested it on two multitemporal Sentinel-1 data sets over Brumadinho, Brazil, and Bhavanisagar, India.

Change Detection in Image Time-Series Using Unsupervised LSTM / Saha, S.; Bovolo, F.; Bruzzone, L.. - In: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS. - ISSN 1545-598X. - STAMPA. - 19:(2022), pp. 80052051-80052055. [10.1109/LGRS.2020.3043822]

Change Detection in Image Time-Series Using Unsupervised LSTM

Saha S.;Bovolo F.;Bruzzone L.
2022-01-01

Abstract

Deep learning-based unsupervised change detection (CD) methods compare a prechange and a postchange image in deep feature space and require precise knowledge of the event date for selecting proper pre-/post-change images. However, in many applications changes may occur gradually over a span of time making pre-/post-dates difficult to establish or prior knowledge of event date is unknown. On the other hand, deep learning-based time-series analysis methods are generally supervised. Considering such scenarios, we propose a novel unsupervised deep learning-based method to detect changes in an image time-series. The method does not make any assumption on the date of the occurrence of the change event. It treats CD as an anomaly detection problem by exploiting multilayer long short term memory (LSTM) network to learn a representation of the time series. The proposed method ingests a shuffled time series and uses an encoder-decoder LSTM model to rearrange the input sequence in correct order. While the model fails to rearrange the changed pixels, unchanged data can be rearranged in the correct order. This enables the identification of the changed pixels. To show the effectiveness of the proposed method, we tested it on two multitemporal Sentinel-1 data sets over Brumadinho, Brazil, and Bhavanisagar, India.
Saha, S.; Bovolo, F.; Bruzzone, L.
Change Detection in Image Time-Series Using Unsupervised LSTM / Saha, S.; Bovolo, F.; Bruzzone, L.. - In: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS. - ISSN 1545-598X. - STAMPA. - 19:(2022), pp. 80052051-80052055. [10.1109/LGRS.2020.3043822]
File in questo prodotto:
File Dimensione Formato  
Change_Detection_in_Image_Time-Series_Using_Unsupervised_LSTM.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.44 MB
Formato Adobe PDF
2.44 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/326894
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? 20
social impact