Deep learning-based reconstruction methods for near-field MIMO radar imaging

Manisalı, İrfan
Near-field multiple-input multiple-output (MIMO) radar imaging systems are of interest in diverse fields such as medicine, through-wall imaging, airport security, and surveillance. These computational imaging systems reconstruct the three-dimensional scene reflectivity distribution from the radar data. Hence their imaging performance largely depends on the image reconstruction method. The analytical reconstruction methods suffer from either low image quality or high computational cost. In fact, sparsity-based methods offer better image quality than the traditional direct inversion methods, but their high computational cost is undesirable in real-time applications. In this thesis, we develop two novel deep learning-based reconstruction methods for near-field MIMO radar imaging. The main goal is to achieve high image quality with low computational cost. The first approach has a two-staged structure that consists of an adjoint operation followed by a deep neural network. The adjoint stage exploits the observation model and back project the measurements to the reconstruction space. The second stage employs a deep neural network which is trained to convert the backprojected measurements to a suitable reflectivity image. For comparison, a second approach is also developed which replaces the adjoint stage with a fully connected neural network. In this two-staged structure, the reconstruction is performed directly from the radar measurements using neural networks which are trained end-to-end to learn the direct mapping between the measurements and unknown reflectivity magnitude. For each case, a 3D U-Net is used at the second stage to jointly exploit range and cross-range correlations. We demonstrate the performance of the developed methods using a synthetically generated dataset and compare with the commonly used analytical methods. The developed two-staged method with adjoint provides the best reconstruction quality while enabling fast reconstruction.


Optimal design of sparse mimo arrays for wideband near-field imaging based on a statistical framework
Kocamış, Mehmet Burak; Öktem, Sevinç Figen; Department of Electrical and Electronics Engineering (2018)
Wideband near-field imaging is an emerging remote sensing technique in various applications such as airport security, surveillance, medical diagnosis, and through-wall imaging. Recently, there has been increasing interest in using sparse multiple-input-multiple-output (MIMO) arrays to achieve high resolution with reduced hardware complexity and cost. In this thesis, based on a statistical framework, an optimal design method is presented for two-dimensional MIMO arrays in wideband near-field imaging. Differe...
Sparsity-based three-dimensional image reconstruction for near-field MIMO radar imaging
Öktem, Sevinç Figen (The Scientific and Technological Research Council of Turkey, 2019-01-01)
Near-field multiple-input multiple-output (MIMO) radar imaging systems are of interest in diverse fields such as medicine, through-wall imaging, airport security, concealed weapon detection, and surveillance. The successful operation of these radar imaging systems highly depends on the quality of the images reconstructed from radar data. Since the underlying scenes can be typically represented sparsely in some transform domain, sparsity priors can effectively regularize the image formation problem and hence...
Deep convolutional neural networks for airport detection in remote sensing images
Budak, Umit; Sengur, Abdulkadir; Halıcı, Uğur (2018-05-05)
This study investigated the use of deep convolutional neural networks (CNNs) in providing a solution for the problem of airport detection in remote sensing images (RSIs). In recent years, Deep CNNs have gained much attention with numerous applications having been undertaken in the area of computer vision. Researchers generally approach airport detection as a pattern recognition problem, in which first various distinctive features are extracted, and then a classifier is adopted to detect airports. CNNs not o...
Computational Spectral Imaging with Photon Sieves
Öktem, Sevinç Figen; Davila, Joseph M. (2016-01-01)
Spectral imaging, the sensing of spatial information as a function of wavelength, is a widely used diagnostic technique in diverse fields such as physics, chemistry, biology, medicine, astronomy, and remote sensing. In this paper, we present a novel computational imaging modality that enables high-resolution spectral imaging by distributing the imaging task between a photon sieve system and a computer. The photon sieve system, coupled with a moving detector, provides measurements from multiple planes. Then ...
Çok Genişbantlı Mikrodalga Görüntüleme için Optimal MIMO Dizilimi
Kocamis, Burak; Öktem, Sevinç Figen (2017-05-18)
Wideband microwave imaging systems are recently used in various applications including airport security, surveillance, through-wall imaging and medicine. For the operation of such high-resolution systems, sparse multiple-input-multiple output (MIMO) arrays are of interest to reduce the hardware complexity and cost of conventional planar arrays. In this paper, we present a method for the optimal design of two-dimensional MIMO arrays in near-field imaging. Using a statistical framework, the optimality criteri...
Citation Formats
İ. Manisalı, “Deep learning-based reconstruction methods for near-field MIMO radar imaging,” M.S. - Master of Science, Middle East Technical University, 2022.