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 .

This article presents two supervised change detection algorithms (CDA) based on convolutional neural networks (CNN) that use stacks of co-registered wavelength-resolution synthetic aperture radar (SAR) images to detect changes in an image under monitoring. The additional information of a scene of interest provided by SAR image stacks can be explored to enhance the performance of change detection algorithms. In particular, stacks of images with similar statistics can be obtained for ultra-wideband (UWB) very high frequency (VHF) SAR systems, as they produce images highly stable in time. The proposed CDAs can be summed up into four stages: difference image formation, semantic segmentation, clustering, and change classification. The CNN-GSP algorithm is based on a ground scene prediction (GSP) image, which is used as a reference to form a difference image (DI). A CNN-based model then analyzes the DI. The CNN-MDI algorithm feeds multiple DIs with identical monitored images to a CNN-based model, which will concurrently analyze their features. Tests with CARABAS-II data show that the proposed CDAs can outperform other state-of-theart algorithms that also use stacks of WR-SAR images. Beyond that, the proposed algorithms outperformed a CNN-based CDA that does not use image stacks, which shows that CNN-based algorithms can use the additional information provided by stacks of SAR images to reduce false alarm occurrences while increasing the probability of detection of changes.

<p>Anomaly detection in synthetic aperture radar (SAR) images is an important task with numerous applications, including damage assessment, oil spill detection, and land use classification. It is also a crucial pre-task for the detection and forecast of natural catastrophes (NatCat), as faulty data can lead to inaccurate predictions and potentially dangerous situations. Traditional methods for anomaly detection in SAR data often rely on manual inspection, which can be laborious and subjective. An AI-based approach to anomaly detection has the potential to quickly and automatically detect issues in SAR data, improving efficiency and accuracy. One advantage of using AI for anomaly detection is the ability to identify patterns and anomalies that may be difficult for humans to discern, including those that are subtle or not immediately apparent. In addition, an AI-based approach can be more objective and less prone to human bias compared to manual inspection. An AI-based anomaly detection system can also be highly scalable and adaptable, making it a flexible and valuable tool for anomaly detection in SAR images. We propose to present how an AI-based approach can be used to automatically detect different types of anomalies in SAR data to avoid faulty data being used in critical applications.  Overall, an AI-based anomaly detection system has the potential to significantly improve the efficiency and accuracy of anomaly detection in this domain and could have a wide range of applications in other fields also.</p>

Iterative demodulation and decoding (ID) seeks to extract useful information from decoders by performing multiple successive demodulation and decoding iterations. Multistage decoding with iterative demodulation and decoding (MSD-ID) unites MSD and ID, in order to improve error probability performance for multilevel codes. This article evaluates MSD-ID performance for multilevel LDPC codes and compares to a proposed MSD-ID modification called parity information aided iterative multistage decoding (PIA-MSD-ID), where parity-checking information obtained from the LDPC decoders is used to aid the whole decoding process. Rate distribution designs are made for MSD, MSD-ID and PIA-MSD-ID. The results show that PIA-MSD-ID achieves lower frame error rate, in comparison to multistage decoding (MSD) and similar to MSD average complexity, for higher SNR.