English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With its small size, low cost and all-weather operation, millimeter-waveradar can accurately measure the distance, azimuth and radial velocity of atarget compared to other traffic sensors. However, in practice, millimeter-waveradars are plagued by various interferences, leading to a drop in targetdetection accuracy or even failure to detect targets. This is undesirable inautonomous vehicles and traffic surveillance, as it is likely to threaten humanlife and cause property damage. Therefore, interference mitigation is of greatsignificance for millimeter-wave radar-based target detection. Currently, thedevelopment of deep learning is rapid, but existing deep learning-basedinterference mitigation models still have great limitations in terms of modelsize and inference speed. For these reasons, we propose Radar-STDA, aRadar-Spatial Temporal Denoising Autoencoder. Radar-STDA is an efficientnano-level denoising autoencoder that takes into account both spatial andtemporal information of range-Doppler maps. Among other methods, it achieves amaximum SINR of 17.08 dB with only 140,000 parameters. It obtains 207.6 FPS onan RTX A4000 GPU and 56.8 FPS on an NVIDIA Jetson AGXXavier respectively whendenoising range-Doppler maps for three consecutive frames. Moreover, we releasea synthetic data set called Ra-inf for the task, which involves 384,769range-Doppler maps with various clutters from objects of no interest andreceiver noise in realistic scenarios. To the best of our knowledge, Ra-inf isthe first synthetic dataset of radar interference. To support the community,our research is open-source via the link\url{https://github.com/GuanRunwei/rd_map_temporal_spatial_denoising_autoencoder}.

Radar-STDA: A High-Performance Spatial-Temporal Denoising Autoencoder for Interference Mitigation of FMCW Radars