Novel Hybrid-Learning Algorithms for Improved Millimeter-Wave Imaging Systems

Increasing attention is being paid to millimeter-wave (mmWave), 30 GHz to 300 GHz, and terahertz (THz), 300 GHz to 10 THz, sensing applications including security sensing, in- dustrial packaging, medical imaging, and non-destructive testing. Traditional methods for perception and imaging are challenged by novel data-driven algorithms that offer improved resolution, localization, and detection rates. Over the past decade, deep learning technology has garnered substantial popularity, particularly in perception and computer vision appli- cations. Whereas conventional signal processing techniques are more easily generalized to various applications, hybrid approaches where signal processing and learning-based algo- rithms are interleaved pose a promising compromise between performance and generalizabil- ity. Furthermore, such hybrid algorithms improve model training by leveraging the known characteristics of radio frequency (RF) waveforms, thus yielding more efficiently trained deep learning algorithms and offering higher performance than conventional methods. This dissertation introduces novel hybrid-learning algorithms for improved mmWave imaging systems applicable to a host of problems in perception and sensing. Various problem spaces are explored, including static and dynamic gesture classification; precise hand localization for human computer interaction; high-resolution near-field mmWave imaging using forward synthetic aperture radar (SAR); SAR under irregular scanning geometries; mmWave image super-resolution using deep neural network (DNN) and Vision Transformer (ViT) archi- tectures; and data-level multiband radar fusion using a novel hybrid-learning architecture. Furthermore, we introduce several novel approaches for deep learning model training and dataset synthesis. Depending on the application, a varying balance of classical signal pro- cessing techniques and deep learning is applied to optimally leverage the advantages of each technique. To verify the proposed algorithms, we employ virtual prototyping via simula- tion and develop custom-built imaging testbeds for empirical testing. Our custom tools for algorithm development, dataset generation, system-level design, and deployment are made public to promote further innovation in this arena. The simulation and experimental results demonstrate the wide application space of hybrid-learning algorithms and the efficacy of joint signal processing data-driven algorithms for radar sensing, perception, and imaging.