Search for: All records

Abstract Current radio frequency (RF) classification techniques assume only one target in the field of view. Multi‐target recognition is challenging because conventional radar signal processing results in the superposition of target micro‐Doppler signatures, making it difficult to recognise multi‐target activity. This study proposes an angular subspace projection technique that generates multiple radar data cubes (RDC) conditioned on angle (RDC‐ω). This approach enables signal separation in the raw RDC, making possible the utilisation of deep neural networks taking the raw RF data as input or any other data representation in multi‐target scenarios. When targets are in closer proximity and cannot be separated by classical techniques, the proposed approach boosts the relative signal‐to‐noise ratio between targets, resulting in multi‐view spectrograms that boosts the classification accuracy when input to the proposed multi‐view DNN. Our results qualitatively and quantitatively characterise the similarity of multi‐view signatures to those acquired in a single‐target configuration. For a nine‐class activity recognition problem, 97.8% accuracy in a 3‐person scenario is achieved, while utilising DNN trained on single‐target data. We also present the results for two cases of close proximity (sign language recognition and side‐by‐side activities), where the proposed approach has boosted the performance. 

As next-generation communication services and satellite systems expand across diverse frequency bands, the escalating utilization poses heightened interference risks to passive sensors crucial for environmental and atmospheric sensing. Consequently, there is a pressing need for efficient methodologies to detect, characterize, and mitigate the harmful impact of unwanted anthropogenic signals known as radio frequency interference (RFI) at microwave radiometers. One effective strategy to reduce such interference is to facilitate the coexistence of active and passive sensing systems. Such approach would greatly benefit from a testbed along with a dataset encompassing a diverse array of scenarios under controlled environment. This study presents a physical environmentally controlled testbed including a passive fully calibrated L-band radiometer with a digital back-end capable of collecting raw in-phase/quadrature (IQ) samples and an active fifth-generation (5G) wireless communication system with the capability of transmitting waveforms with advanced modulations. Various RFI scenarios such as in-band, transition-band, and out-of-band transmission effects are quantified in terms of calibrated brightness temperature. Raw radiometer and 5G communication samples along with preprocessed time-frequency representations and true brightness temperature data are organized and made publicly available. A detailed procedure and publicly accessible dataset are provided to help test the impact of wireless communication on passive sensing, enabling the scientific community to facilitate coexistence research and quantify interference effects on radiometers.