Change detection in SAR images using deep belief network: a new training approach based on morphological images. Issue 12 (19th September 2019)

• Record Type: Journal Article
• Authors: Samadi, Farnaam; Akbarizadeh, Gholamreza; Kaabi, Hooman
• Is Part Of: IET image processing. Volume 13:Issue 12(2019)
• Page Start: 2255
• Page End: 2264
• Publication Date: 2019-09-19
• Subjects: belief networks -- image classification -- synthetic aperture radar -- unsupervised learning -- radar imaging -- learning (artificial intelligence); deep learning‐based algorithms -- change detection problems -- detection performance -- dataset -- trained DBN -- deep belief network -- training approach -- morphological images -- unsupervised methods -- supervised counterparts -- labelled data -- deep learning‐based supervised method -- synthetic aperture radar image changes -- deep architecture -- introduced method -- training process -- supervised network fine‐tuning -- change detection map -- input SAR images -- appropriate data volume -- diversity -- input images; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6248
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : 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.