Change detection in SAR images using deep belief network: a new training approach based on morphological images

In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled data. Nevertheless, in this paper, a supervised deep learning-based method is presented for change detection in synthetic aperture radar (SAR)...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IET image processing Jg. 13; H. 12; S. 2255 - 2264
Hauptverfasser:	Samadi, Farnaam, Akbarizadeh, Gholamreza, Kaabi, Hooman
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	The Institution of Engineering and Technology 17.10.2019
Schlagworte:	appropriate data volume belief networks change detection map change detection problems dataset deep architecture deep belief network deep learning‐based algorithms deep learning‐based supervised method detection performance diversity image classification input images input SAR images introduced method labelled data learning (artificial intelligence) morphological images radar imaging Research Article supervised counterparts supervised network fine‐tuning synthetic aperture radar synthetic aperture radar image changes trained DBN training approach training process unsupervised learning unsupervised methods supervised counterparts image classification morphological images unsupervised methods detection performance deep learning-based supervised method introduced method diversity supervised network fine-tuning deep belief network training approach radar imaging synthetic aperture radar image changes belief networks learning (artificial intelligence) change detection problems trained DBN input SAR images training process deep architecture unsupervised learning change detection map synthetic aperture radar labelled data appropriate data volume deep learning-based algorithms input images dataset
ISSN:	1751-9659, 1751-9667
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled data. Nevertheless, in this paper, a supervised deep learning-based method is presented for change detection in synthetic aperture radar (SAR) images. A Deep Belief Network (DBN) was employed as the deep architecture in the proposed method, and the training process of this network included unsupervised feature learning followed by supervised network fine-tuning. From a general perspective, the trained DBN produces a change detection map as the output. Studies on DBNs demonstrate that they do not produce ideal output without a proper dataset for training. Therefore, the proposed method in this study provided a dataset with an appropriate data volume and diversity for training the DBN using the input images and those obtained from applying the morphological operators on them. The great computational volume and the time-consuming nature of simulation are the drawbacks of deep learning-based algorithms. To overcome such disadvantages, a method was introduced to greatly reduce computations without compromising the performance of the trained DBN. Experimental results indicated that the proposed method had an acceptable implementation time in addition to its desirable performance and high accuracy.
ISSN:	1751-9659 1751-9667
DOI:	10.1049/iet-ipr.2018.6248