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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

mmWave FMCW radar has attracted huge amount of research interest forhuman-centered applications in recent years, such as human gesture/activityrecognition. Most existing pipelines are built upon conventional DiscreteFourier Transform (DFT) pre-processing and deep neural network classifierhybrid methods, with a majority of previous works focusing on designing thedownstream classifier to improve overall accuracy. In this work, we take a stepback and look at the pre-processing module. To avoid the drawbacks ofconventional DFT pre-processing, we propose a learnable pre-processing module,named CubeLearn, to directly extract features from raw radar signal and buildan end-to-end deep neural network for mmWave FMCW radar motion recognitionapplications. Extensive experiments show that our CubeLearn module consistentlyimproves the classification accuracies of different pipelines, especiallybenefiting those previously weaker models. We provide ablation studies oninitialization methods and structure of the proposed module, as well as anevaluation of the running time on PC and edge devices. This work also serves asa comparison of different approaches towards data cube slicing. Through ourtask agnostic design, we propose a first step towards a generic end-to-endsolution for radar recognition problems.

CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals