CNN-Based Change Detection Algorithm for Wavelength-Resolution SAR Images

Abstract

This letter presents an incoherent change detection algorithm (CDA) for wavelength-resolution synthetic aperture radar (SAR) based on convolutional neural networks (CNNs). The proposed CDA includes a segmentation CNN, which localizes potential changes, and a classification CNN, which further analyzes these candidates to classify them as real changes or false alarms. Compared to state-of-the-art solutions on the CARABAS-II data set, the proposed CDA shows a significant improvement in performance, achieving, in a particular setting, a detection probability of 99% at a false alarm rate of 0.0833/km 2 .

Change Detection Algorithm Based on U-NET Convolutional Neural Network for Multitemporal Wavelength-Resolution SAR Images

“…Using this algorithm, we achieved a probability of detection of 97% and a false alarm rate of 0.034/km 2 , while other algorithms such as [3] presented a P d of 97% and a FAR= 0.67/km 2 . More recent algorithms such as [4], achieved a P d of around 97% and a FAR= 0.28/km 2 , [16] achieved a P d of about 97% and a FAR= 0.0313/km 2 , and [15] achieved a P d of around 99% and a FAR= 0.0833/km 2 , respectively. It worth mentioning that methods presented in [16], [15] are based on more complex CNN with greater time complexity.…”

“…More recent algorithms such as [4], achieved a P d of around 97% and a FAR= 0.28/km 2 , [16] achieved a P d of about 97% and a FAR= 0.0313/km 2 , and [15] achieved a P d of around 99% and a FAR= 0.0833/km 2 , respectively. It worth mentioning that methods presented in [16], [15] are based on more complex CNN with greater time complexity.…”

“…In the last few years, aiming at overcoming this limitation of traditional CDA approaches, many studies have been developing considering the use of machine learning algorithms for target and change detection applications [15], [16]. Basically, there are two types of machine learning algorithms: supervised and unsupervised.…”

Change Detection Based on Convolutional Neural Networks Using Stacks of Wavelength-Resolution Synthetic Aperture Radar Images

“…We present the performance evaluation over the only publicly available data set for this class of SAR system. Multiple CNN architectures were not tested since the main objective of this article is to evaluate how much the use of stacks of WR-SAR images can improve the performance of a baseline CNN-based CDA for WR-SAR images, presented in [36].…”

“…The proposed CDAs search for positive changes in the monitored image and can be summarized into four stages: (i) difference image formation; (ii) semantic segmentation; (iii) clustering; and (iv) classification of changes. The CNN-GSP uses a ground scene prediction image, produced by fusing a WR-SAR stack into a single image, as a reference for change detection, which is then fed to the CDA presented in [36]. On the other hand, the CNN-MDI algorithm uses the images contained in a WR-SAR data stack as references to generate multiple difference images with identical monitored images.…”