Target Discrimination in Synthetic Aperture Radar (SAR) using Artificial Neural Networks
نویسندگان
چکیده
This paper addresses target discrimination in synthetic aperture radar (SAR) imagery using linear and nonlinear adaptive networks. Neural networks are extensively used for pattern classification but here the goal is discrimination. We will show that the two applications require different cost functions. We start by analyzing with a pattern recognition perspective the two-parameter constant false alarm rate (CFAR) detector which is widely utilized as a target detector in SAR. Then we generalize its principle to construct the Quadratic Gamma discriminator (QGD), a non-parametrically trained classifier based on local image intensity. The linear processing element of the QGD is further extended with nonlinearities yielding a multi-layer perceptron (MLP) which we call the NL-QGD (non-linear QGD). MLPs are normally trained based on the L2 norm. We experimentally show that the L2 norm is not recommended to train MLPs for discriminating targets in SAR. Inspired by the Neyman-Pearson criterion we create a cost function based on a mixed norm to weight the false alarms and the missed detections differently. Mixed norms can easily be incorporated into the backpropagation algorithm, and lead to better performance. Several other norms (L8, cross-entropy) are applied to train the NL-QGD and all outperformed the L2 norm when validated by receiver operating characteristics (ROC) curves. The data sets are constructed from Tabils 24 ISAR targets embedded in 7 km2 of SAR imagery (MIT/LL mission 90).
منابع مشابه
Deep Learning for End-to-End Automatic Target Recognition from Synthetic Aperture Radar Imagery
The standard architecture of synthetic aperture radar (SAR) automatic target recognition (ATR) consists of three stages: detection, discrimination, and classification. In recent years, convolutional neural networks (CNNs) for SAR ATR have been proposed, but most of them classify target classes from a target chip extracted from SAR imagery, as a classification for the third stage of SAR ATR. In ...
متن کاملTarget discrimination in synthetic aperture radar using artificial neural networks
This paper addresses target discrimination in synthetic aperture radar (SAR) imagery using linear and nonlinear adaptive networks. Neural networks are extensively used for pattern classification but here the goal is discrimination. We show that the two applications require different cost functions. We start by analyzing with a pattern recognition perspective the two-parameter constant false ala...
متن کاملA new algorithm of SAR target recognition based on advance deep learning neural network
In order to improve the accuracy of synthetic aperture radar images target recognition, we have proposed a new algorithm of SAR target recognition based on advance Deep Learning neural network. The traditional radar recognition algorithm has many disadvantages, In order to improve the accuracy of synthetic aperture radar images target recognition, the author have proposed a new algorithm of SAR...
متن کاملSAR Target Recognition Using Improved Fuzzy Neural Network
Target recognition in high-resolution synthetic aperture radar (SAR) images is a challenging task, because SAR images have higher ambiguity for different target, which will reduce the correct recognition rate. This paper presents an improved SAR recognition algorithm based on fuzzy neural network (FNN), which deals with the ambiguity SAR target recognition very well. This improved FNN system im...
متن کاملSoil Moisture Estimation in South-Eastern New Mexico Using High Resolution Synthetic Aperture Radar (SAR) Data
Soil moisture monitoring and characterization of the spatial and temporal variability of this hydrologic parameter at scales from small catchments to large river basins continues to receive much attention, reflecting its critical role in subsurface-land surface-atmospheric interactions and its importance to drought analysis, irrigation planning, crop yield forecasting, flood protection, and for...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1998