Change Detection Based on Convolutional Neural Networks Using Stacks of Wavelength-Resolution Synthetic Aperture Radar ImagesShow others and affiliations
2022 (English)In: IEEE Transactions on Geoscience and Remote Sensing, ISSN 0196-2892, E-ISSN 1558-0644, Vol. 60, article id 5236414Article in journal (Refereed) Published
Abstract [en]
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-the-art 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.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022. Vol. 60, article id 5236414
Keywords [en]
Change detection, Convolution, Deep learning, Image enhancement, Neural networks, Radar imaging, Remote sensing, Semantic Segmentation, Semantics, Signal detection, Tracking radar, CARABAS, CARABAS-II, Complexity theory, Convolutional neural network, Detection algorithm, Radar polarimetry, Remote-sensing, Ultra-wideband technology, Synthetic aperture radar, Classification, CNN, Convolutional neural networks, Detection algorithms, Monitoring, Ultra wideband technology
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-23775DOI: 10.1109/TGRS.2022.3211010ISI: 000874066100016Scopus ID: 2-s2.0-85139463271OAI: oai:DiVA.org:bth-23775DiVA, id: diva2:1705972
Note
Open access
2022-10-242022-10-242022-12-13Bibliographically approved