scispace - formally typeset
Search or ask a question
Author

Khalid El-Darymli

Bio: Khalid El-Darymli is an academic researcher from St. John's University. The author has contributed to research in topics: Synthetic aperture radar & Inverse synthetic aperture radar. The author has an hindex of 8, co-authored 26 publications receiving 524 citations. Previous affiliations of Khalid El-Darymli include Memorial University of Newfoundland.

Papers
More filters
Journal ArticleDOI
TL;DR: A two-fold benchmarking scheme for evaluating existing SAR-ATR systems and motivating new system designs is proposed, and a taxonomization methodology for surveying the numerous methods published in the open literature is proposed.
Abstract: The purpose of this paper is to survey and assess the state-of-the-art in automatic target recognition for synthetic aperture radar imagery (SAR-ATR). The aim is not to develop an exhaustive survey of the voluminous literature, but rather to capture in one place the various approaches for implementing the SAR-ATR system. This paper is meant to be as self-contained as possible, and it approaches the SAR-ATR problem from a holistic end-to-end perspective. A brief overview for the breadth of the SAR-ATR challenges is conducted. This is couched in terms of a single-channel SAR, and it is extendable to multi-channel SAR systems. Stages pertinent to the basic SAR-ATR system structure are defined, and the motivations of the requirements and constraints on the system constituents are addressed. For each stage in the SAR-ATR processing chain, a taxonomization methodology for surveying the numerous methods published in the open literature is proposed. Carefully selected works from the literature are presented under the taxa proposed. Novel comparisons, discussions, and comments are pinpointed throughout this paper. A two-fold benchmarking scheme for evaluating existing SAR-ATR systems and motivating new system designs is proposed. The scheme is applied to the works surveyed in this paper. Finally, a discussion is presented in which various interrelated issues, such as standard operating conditions, extended operating conditions, and target-model design, are addressed. This paper is a contribution toward fulfilling an objective of end-to-end SAR-ATR system design.

269 citations

Journal ArticleDOI
TL;DR: In this article, a taxonomy for the various target detection methods for SAR imagery is proposed. And a tabular comparison of representative examples is introduced. But, the underlying assumptions for different implementation strategies are overviewed.
Abstract: Target detection is the front-end stage in any automatic target recognition system for synthetic aperture radar (SAR) imagery (SAR-ATR). The efficacy of the detector directly impacts the succeeding stages in the SAR-ATR processing chain. There are numerous methods reported in the literature for implementing the detector. We offer an umbrella under which the various research activities in the field are broadly probed and taxonomized. First, a taxonomy for the various detection methods is proposed. Second, the underlying assumptions for different implementation strategies are overviewed. Third, a tabular comparison between careful selections of representative examples is introduced. Finally, a novel discussion is presented, wherein the issues covered include suitability of SAR data models, understanding the multiplicative SAR data models, and two unique perspectives on constant false alarm rate (CFAR) detection: signal processing and pattern recognition. From a signal processing perspective, CFAR is shown to be a finite impulse response band-pass filter. From a statistical pattern recognition perspective, CFAR is shown to be a suboptimal one-class classifier: a Euclidian distance classifier and a quadratic discriminant with a missing term for one-parameter and two-parameter CFAR, respectively. We make a contribution toward enabling an objective design and implementation for target detection in SAR imagery.

141 citations

Journal ArticleDOI
TL;DR: An umbrella under which the various research activities in the field are broadly probed and taxonomized is offered, and a taxonomy for the various detection methods is proposed, enabling an objective design and implementation for target detection in SAR imagery.
Abstract: Target detection is the front-end stage in any automatic target recognition system for synthetic aperture radar (SAR) imagery (SAR-ATR). The efficacy of the detector directly impacts the succeeding stages in the SAR-ATR processing chain. There are numerous methods reported in the literature for implementing the detector. We offer an umbrella under which the various research activities in the field are broadly probed and taxonomized. First, a taxonomy for the various detection methods is proposed. Second, the underlying assumptions for different implementation strategies are overviewed. Third, a tabular comparison between careful selections of representative examples is introduced. Finally, a novel discussion is presented, wherein the issues covered include suitability of SAR data models, understanding the multiplicative SAR data models, and two unique perspectives on constant false alarm rate (CFAR) detection: signal processing and pattern recognition. From a signal processing perspective, CFAR is shown to be a finite impulse response band-pass filter. From a statistical pattern recognition perspective, CFAR is shown to be a suboptimal one-class classifier: a Euclidian distance classifier and a quadratic discriminant with a missing term for one-parameter and two-parameter CFAR, respectively. We make a contribution toward enabling an objective design and implementation for target detection in SAR imagery.

54 citations

Proceedings ArticleDOI
04 May 2014
TL;DR: An investigation of the various forms for radiometric calibration in SAR imagery is presented, and it is concluded that the βo calibration gives the most accurate result, in contrast to σ and γ because it is not dependent on the sea-level geoid model typically used to approximate the local incidence angles.
Abstract: In applications such as target recognition, quantitative use of the information present in synthetic aperture radar (SAR) imagery is pivotal for detecting and classifying the scattering centers of the target(s). This paper presents an investigation of the various forms for radiometric calibration in SAR imagery. For the cases of point and extended targets, respectively, the radar cross section (σ) and the backscatter coefficient (σ o ) are studied. Other forms of the backscatter coefficient, including the radar brightness (β o ) and (γ o ) are also examined, and their relevance to σ o is presented. A real-world SAR chip from a single-channel Radarsat-2 image for groundtruthed vehicle targets is used to demonstrate the applicability of the radiometric calibrations. It is concluded that the β o calibration gives the most accurate result, in contrast to σ o and γ o because it is not dependent on the sea-level geoid model typically used to approximate the local incidence angles.

27 citations

Journal ArticleDOI
TL;DR: A new insight is offered into the relevance of phase in single-channel synthetic aperture radar (SAR) imagery and a new statistical model for the phase is considered, and a set of 15 solely phase-based features are discussed.
Abstract: Traditionally, the phase content in single-channel synthetic aperture radar (SAR) imagery is discarded. This practice is justified by conventional radar resolution theory, which is a theory strictly relevant to point targets. The advent of high-resolution radars permits small targets previously considered to be points to be now treated as extended targets, in which case this theory is not strictly applicable. With this in mind, this paper offers a new insight into the relevance of phase in single-channel SAR imagery. The proposed approach builds on techniques from the fields of complex-valued and directional statistics. In doing so, three main contributions are presented, the first being a novel method for characterizing the phase content. Second, a new statistical model for the phase is considered, and then a set of 15 solely phase-based features are discussed. Our results are demonstrated on real-world SAR datasets for ground-truthed targets. The statistical significance of the information carried in the phase is clearly demonstrated. Furthermore, if applied to a dataset with higher resolution, the proposed techniques are expected to achieve even higher performance.

27 citations


Cited by
More filters
Christopher M. Bishop1
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

10,141 citations

Journal ArticleDOI
TL;DR: To the best of our knowledge, there is only one application of mathematical modelling to face recognition as mentioned in this paper, and it is a face recognition problem that scarcely clamoured for attention before the computer age but, having surfaced, has attracted the attention of some fine minds.
Abstract: to be done in this area. Face recognition is a problem that scarcely clamoured for attention before the computer age but, having surfaced, has involved a wide range of techniques and has attracted the attention of some fine minds (David Mumford was a Fields Medallist in 1974). This singular application of mathematical modelling to a messy applied problem of obvious utility and importance but with no unique solution is a pretty one to share with students: perhaps, returning to the source of our opening quotation, we may invert Duncan's earlier observation, 'There is an art to find the mind's construction in the face!'.

3,015 citations

01 Jan 2016
TL;DR: Thank you very much for downloading spotlight synthetic aperture radar signal processing algorithms, maybe you have knowledge that, people have search numerous times for their favorite books, but end up in malicious downloads.
Abstract: Thank you very much for downloading spotlight synthetic aperture radar signal processing algorithms. Maybe you have knowledge that, people have search numerous times for their favorite books like this spotlight synthetic aperture radar signal processing algorithms, but end up in malicious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they juggled with some harmful virus inside their laptop.

455 citations

Journal ArticleDOI
TL;DR: This work proposes a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data, and designs an assembled CNN architecture consisting of a classification pathway and a reconstruction pathway, together with a feedback bypass additionally.
Abstract: Tremendous progress has been made in object recognition with deep convolutional neural networks (CNNs), thanks to the availability of large-scale annotated dataset. With the ability of learning highly hierarchical image feature extractors, deep CNNs are also expected to solve the Synthetic Aperture Radar (SAR) target classification problems. However, the limited labeled SAR target data becomes a handicap to train a deep CNN. To solve this problem, we propose a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data. We design an assembled CNN architecture consisting of a classification pathway and a reconstruction pathway, together with a feedback bypass additionally. Instead of training a deep network with limited dataset from scratch, a large number of unlabeled SAR scene images are used to train the reconstruction pathway with stacked convolutional auto-encoders (SCAE) at first. Then, these pre-trained convolutional layers are reused to transfer knowledge to SAR target classification tasks, with feedback bypass introducing the reconstruction loss simultaneously. The experimental results demonstrate that transfer learning leads to a better performance in the case of scarce labeled training data and the additional feedback bypass with reconstruction loss helps to boost the capability of classification pathway.

335 citations

Journal ArticleDOI
TL;DR: This paper proposes a unified and effective method for simultaneously detecting multi-class objects in remote sensing images with large scales variability, and shows that the method is more accurate than existing algorithms and is effective for multi-modalRemote sensing images.
Abstract: Automatic detection of multi-class objects in remote sensing images is a fundamental but challenging problem faced for remote sensing image analysis. Traditional methods are based on hand-crafted or shallow-learning-based features with limited representation power. Recently, deep learning algorithms, especially Faster region based convolutional neural networks (FRCN), has shown their much stronger detection power in computer vision field. However, several challenges limit the applications of FRCN in multi-class objects detection from remote sensing images: (1) Objects often appear at very different scales in remote sensing images, and FRCN with a fixed receptive field cannot match the scale variability of different objects; (2) Objects in large-scale remote sensing images are relatively small in size and densely peaked, and FRCN has poor localization performance with small objects; (3) Manual annotation is generally expensive and the available manual annotation of objects for training FRCN are not sufficient in number. To address these problems, this paper proposes a unified and effective method for simultaneously detecting multi-class objects in remote sensing images with large scales variability. Firstly, we redesign the feature extractor by adopting Concatenated ReLU and Inception module, which can increases the variety of receptive field size. Then, the detection is preformed by two sub-networks: a multi-scale object proposal network (MS-OPN) for object-like region generation from several intermediate layers, whose receptive fields match different object scales, and an accurate object detection network (AODN) for object detection based on fused feature maps, which combines several feature maps that enables small and densely packed objects to produce stronger response. For large-scale remote sensing images with limited manual annotations, we use cropped image blocks for training and augment them with re-scalings and rotations. The quantitative comparison results on the challenging NWPU VHR-10 data set, aircraft data set, Aerial-Vehicle data set and SAR-Ship data set show that our method is more accurate than existing algorithms and is effective for multi-modal remote sensing images.

327 citations