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

Fall detection is a vital task in health monitoring, as it allows the systemto trigger an alert and therefore enabling faster interventions when a personexperiences a fall. Although most previous approaches rely on standard RGBvideo data, such detailed appearance-aware monitoring poses significant privacyconcerns. Depth sensors, on the other hand, are better at preserving privacy asthey merely capture the distance of objects from the sensor or camera, omittingcolor and texture information. In this paper, we introduce a privacy-supportingsolution that makes the RGB-trained model applicable in depth domain andutilizes depth data at test time for fall detection. To achieve cross-modalfall detection, we present an unsupervised RGB to Depth (RGB2Depth) cross-modaldomain adaptation approach that leverages labelled RGB data and unlabelleddepth data during training. Our proposed pipeline incorporates an intermediatedomain module for feature bridging, modality adversarial loss for modalitydiscrimination, classification loss for pseudo-labeled depth data and labeledsource data, triplet loss that considers both source and target domains, and anovel adaptive loss weight adjustment method for improved coordination amongvarious losses. Our approach achieves state-of-the-art results in theunsupervised RGB2Depth domain adaptation task for fall detection. Code isavailable at https://github.com/1015206533/privacy_supporting_fall_detection.

Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation