Automatic Area-Based Registration of Optical and SAR Images Through Generative Adversarial Networks and a Correlation-Type Metric

Maggiolo, Luca; Solarna, David; Moser, Gabriele

doi:10.1109/igarss39084.2020.9323235

Cited by 7 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let us also suppose that the two images are well registered so that it is possible to process them coherently on the same reference frame. In the literature, many image registration methods exist [68][69][70], also capable of addressing multisensor registration problems [71][72][73].…”

Section: Energy Function Of the Proposed Markov Modelmentioning

confidence: 99%

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

et al. 2021

Self Cite

View full text Add to dashboard Cite

The aim of this paper is to address the monitoring of the recovery phase in the aftermath of Hurricane Matthew (28 September–10 October 2016) in the town of Jérémie, southwestern Haiti. This is accomplished via a novel change detection method that has been formulated, in a data fusion perspective, in terms of multitemporal supervised classification. The availability of very high resolution images provided by last-generation satellite synthetic aperture radar (SAR) and optical sensors makes this analysis promising from an application perspective and simultaneously challenging from a processing viewpoint. Indeed, pursuing such a goal requires the development of novel methodologies able to exploit the large amount of detailed information provided by this type of data. To take advantage of the temporal and spatial information associated with such images, the proposed method integrates multisensor, multisource, and contextual information. Markov random field modeling is adopted here to integrate the spatial context and the temporal correlation associated with images acquired at different dates. Moreover, the adoption of a region-based approach allows for the characterization of the geometrical structures in the images through multiple segmentation maps at different scales and times. The performances of the proposed approach are evaluated on multisensor pairs of COSMO-SkyMed SAR and Pléiades optical images acquired over Jérémie, in the aftermath of and during the three years after Hurricane Matthew. The effectiveness of the change detection results is analyzed both quantitatively, through the computation of accuracy measures on a test set, and qualitatively, by visual inspection of the classification maps. The robustness of the proposed method with respect to different algorithmic choices is also assessed, and the detected changes are discussed in relation to the recovery endeavors in the area and ground-truth data collected in the field in April 2019.

show abstract

Section: Energy Function Of the Proposed Markov Modelmentioning

confidence: 99%

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Here, the desired output is an image with SAR-like distribution ("fake SAR"), while the non-noise input is the optical image. The adopted DL method is the one in [14], which consists of two steps: first, a translation stage by means of the pix2pix cGAN [13], and then, an area-based registration stage using an 2 similarity (see Section 4.2). Details can be found in [14].…”

Section: Image-to-image Translation Through DLmentioning

confidence: 99%

“…The adopted DL method is the one in [14], which consists of two steps: first, a translation stage by means of the pix2pix cGAN [13], and then, an area-based registration stage using an 2 similarity (see Section 4.2). Details can be found in [14]. The application of the cGAN to the Amazon dataset is also described in [14].…”

Section: Image-to-image Translation Through DLmentioning

confidence: 99%

“…Details can be found in [14]. The application of the cGAN to the Amazon dataset is also described in [14]. Regarding the Bussac dataset, the Pléiades panchromatic image was manually warped to the COSMO-SkyMed image grid (which was around 5500 × 5500 pixels) to have paired patches to be used for training.…”

Section: Image-to-image Translation Through DLmentioning

confidence: 99%

“…The training set was made of 101 patches (512 × 512 pixels each) drawn from the whole scene except the South-West corner, which was used for testing. This training strategy was used here for experimental purposes, but in a general application of the method, the training would make use of pre-registered patches coming from the same data sources but not from the specific images to be registered [14]. pix2pix, which is aimed at RGB im-ages, was modified to map from the single-channel panchromatic to the single-channel SAR domains.…”

Section: Image-to-image Translation Through DLmentioning

confidence: 99%

See 2 more Smart Citations

Experimental Comparison of Registration Methods for Multisensor Sar-Optical Data

Pinel‐Puysségur

Maggiolo

Roux

et al. 2021

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

Self Cite

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) and optical satellite image registration is a field that developed in the last decades and gave rise to a great number of approaches. The registration process is composed of several steps: feature definition, feature comparison and optimization of a geometric transformation between the images. Feature definition can be done using simple traditional filtering or more complex deep learning (DL) methods. In this paper, two traditional approaches and a DL approach are compared. One can then wonder if the complexity of DL is worth to address the registration task. The aim of this paper is to quantitatively compare approaches rooted in distinct methodological areas on two common datasets with different resolutions. The comparison suggests that, although more complex, the DL approach is more precise than traditional methods.

show abstract

Synthetic SAR Data Generator Using Pix2pix cGAN Architecture for Automatic Target Recognition

Araujo,

Machado,

Pettersson

2023

IEEE Access

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) technology has unique advantages but faces challenges in obtaining enough data for noncooperative target classes. We propose a method to generate synthetic SAR data using a modified pix2pix Conditional Generative Adversarial Networks (cGAN) architecture. The cGAN is trained to create synthetic SAR images with specific azimuth and elevation angles, demonstrating its capability to closely mimic authentic SAR imagery through convergence and collapsing analyses. The study uses a model-based algorithm to assess the practicality of the generated synthetic data for Automatic Target Recognition (ATR). The results reveal that the classification accuracy achieved with synthetic data is comparable to that attained with original data, highlighting the effectiveness of the proposed method in mitigating the limitations imposed by noncooperative SAR data scarcity for ATR. This innovative approach offers a promising solution to craft customized synthetic SAR data, ultimately enhancing ATR performance in remote sensing.

show abstract

Automatic Area-Based Registration of Optical and SAR Images Through Generative Adversarial Networks and a Correlation-Type Metric

Cited by 7 publications

References 12 publications

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

Experimental Comparison of Registration Methods for Multisensor Sar-Optical Data

Synthetic SAR Data Generator Using Pix2pix cGAN Architecture for Automatic Target Recognition

Contact Info

Product

Resources

About