Differentiable Rendering for Synthetic Aperture Radar Imagery

Wilmanski, Michael; Tamir, Jonathan I.

doi:10.48550/arxiv.2204.01248

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, it would be worthwhile to examine whether penalty functions or bases that encourage left-right symmetry of the target could be used to mitigate BPDN's inability to fill in missing scatterers. It would also be of interest to explore novel view synthesis approaches other than BPDN, such as neural radiance fields (NeRF) methods that have recently been applied to SAR data [14].…”

Section: Discussionmentioning

confidence: 99%

Novel view synthesis with compressed sensing as data augmentation for SAR ATR

Banaś

Hill

Kreucher

et al. 2023

Algorithms for Synthetic Aperture Radar Imagery XXX

View full text Add to dashboard Cite

This work investigates the application of compressed sensing algorithms to the problem of novel view synthesis in synthetic aperture radar (SAR). We demonstrate the ability to generate new images of a SAR target from a sparse set of looks at said target, and we show that this can be used as a data augmentation technique for deep learning-based automatic target recognition (ATR). The newly synthesized views can be used both to enlarge the original, sparse training set, and in transfer learning as a source dataset for initial training of the network. The success of the approach is quantified by measuring ATR performance on the MSTAR dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

Novel view synthesis with compressed sensing as data augmentation for SAR ATR

Banaś

Hill

Kreucher

et al. 2023

Algorithms for Synthetic Aperture Radar Imagery XXX

View full text Add to dashboard Cite

show abstract

“…Several such formulations are published for EO [2], [21]. A recent study provides a differentiable forward model formulation for SAR and demonstrates its use in 3D reconstruction of simple shapes from multiple 2D SAR views [22]. Their experiment and example reconstruct 3D shapes, not 3D RCS models, but illustrate that a differentiable forward model for SAR is available.…”

Section: D Rcs Modelmentioning

confidence: 99%

Extending neural radiance fields (NeRF) for synthetic aperture radar (SAR) novel image generation

DelMarco

Bhatia

Kuzdeba

et al. 2023

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications

View full text Add to dashboard Cite

An important application of deep learning classifiers is to recognize vehicles or ships in satellite images. Neural Radiance Field (NeRF) methods apply a limited number of 2D electro-optical (EO) views of an object to learn its 3D shape and view-dependent radiance properties. The resulting latent model generates novel views for training a deep learning classifier. Space-based synthetic aperture radar (SAR) sensors present a new, useful source of wide-area imagery. Because SAR phenomenology and geometry are different from EO, we construct a suitable NeRF-like approach for SAR and demonstrate generation of realistic simulated SAR imagery..Several commercial and military applications classify vehicles or ships in satellite images. In many cases, it is infeasible to acquire looks at the objects over the wide range of views and conditions needed for machine learning classifier training. Neural Radiance Fields (NeRF) and other related methods apply a limited number of 2D views of an object to learn its 3D shape and view-dependent radiance properties. One application of these techniques is to generate additional, novel views of objects for training deep learning classifiers. Current NeRF and NeRF-like methods have been demonstrated with electro-optical (EO) imagery. The emergence of space-based synthetic aperture radar (SAR) imaging sensors presents a new, useful source of wide-area imagery with day/night, all-weather commercial and military applications. Because SAR imaging phenomenology and projection geometry are different from EO, the application of NeRF-like methods to generate novel SAR images of objects for training a classifier presents new challenges. For example, unlike EO, the mono-static SAR illumination source moves with the sensor view geometry. In addition, the 2D SAR image projection is angle-range, not angle-angle. In this paper, we evaluate the salient differences between EO and SAR, and construct a processing pipeline to generate realistic synthetic SAR imagery. The synthetic SAR imagery provides additional training data, augmenting collected image data, for machine learning-based Automatic Target Recognition (ATR) algorithms. We provide examples of synthetic SAR image creation using this approach.

show abstract

Differentiable Rendering for Synthetic Aperture Radar Imagery

Cited by 2 publications

References 0 publications

Novel view synthesis with compressed sensing as data augmentation for SAR ATR

Novel view synthesis with compressed sensing as data augmentation for SAR ATR

Extending neural radiance fields (NeRF) for synthetic aperture radar (SAR) novel image generation

Contact Info

Product

Resources

About