SAR ATR in the phase history domain using deep convolutional neural networks

Alver, Muhammed Burak; Ahmed, Sara Atito Ali; Çetin, Müjdat

doi:10.1117/12.2325365

Cited by 8 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the network is more informed about the auxiliary confounding factor, improving its generalization capability. There have been several other models proposed to tackle the ATR problem with the MSTAR data-set, including [42] and [43], but we primarily build upon Zhong et al's [15] work.…”

Section: A Related Workmentioning

confidence: 99%

Sparse Signal Models for Data Augmentation in Deep Learning ATR

Agarwal¹,

Sugavanam²,

Ertin³

2020

Preprint

View full text Add to dashboard Cite

Automatic Target Recognition (ATR) algorithms classify a given Synthetic Aperture Radar (SAR) image into one of the known target classes using a set of training images available for each class. Recently, learning methods have shown to achieve state-of-the-art classification accuracy if abundant training data is available, sampled uniformly over the classes, and their poses. In this paper, we consider the task of ATR with a limited set of training images. We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm, such as a Convolutional neural network (CNN). The proposed data augmentation method employs a limited persistence sparse modeling approach, capitalizing on commonly observed characteristics of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of overparametrized model fitting. Using this estimated model, we synthesize new images at poses and sub-pixel translations not available in the given data to augment CNN's training data. The experimental results show that for the training data starved region, the proposed method provides a significant gain in the resulting ATR algorithm's generalization performance.

show abstract

Section: A Related Workmentioning

confidence: 99%