Dr. Amit Bhatia Profile

Dr. Amit Bhatia

at BAE Systems

SPIE Involvement:

Author

Publications (3)

Proceedings Article | 7 June 2024 Presentation + Paper

Image sequence analysis using dynamic topic model

Amit Bhatia, Neil Bomberger

Proceedings Volume 13057, 130570R (2024) https://doi.org/10.1117/12.3016281

KEYWORDS: Data modeling, Image analysis, Visual process modeling, Education and training, Cameras, Performance modeling, Mixtures, Ablation, Visualization, Systems modeling

Read Abstract +

Proceedings Article | 14 June 2023 Poster + Paper

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

William Snyder, Stephen DelMarco, Dylan Snover, Amit Bhatia, Scott Kuzdeba

Proceedings Volume 12529, 1252912 (2023) https://doi.org/10.1117/12.2666925

KEYWORDS: Synthetic aperture radar, 3D modeling, Education and training, 3D image processing, Data modeling, Image processing, 3D acquisition, Voxels, Machine learning, Solid modeling

Read Abstract +

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.

Proceedings Article | 20 August 2020 Presentation + Paper

Object detection in conditional GAN transferred sensor images

Amit Bhatia

Proceedings Volume 11511, 1151108 (2020) https://doi.org/10.1117/12.2566885

KEYWORDS: Infrared imaging, Data modeling, Sensors, Infrared cameras, Target detection, Optical filters, Image sensors, Signal generators, Artificial intelligence, Neural networks, Machine learning, Color imaging

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years