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

The use of hand gestures provides a natural alternative to cumbersomeinterface devices for Human-Computer Interaction (HCI) systems. However,real-time recognition of dynamic micro hand gestures from video streams ischallenging for in-vehicle scenarios since (i) the gestures should be performednaturally without distracting the driver, (ii) micro hand gestures occur withinvery short time intervals at spatially constrained areas, (iii) the performedgesture should be recognized only once, and (iv) the entire architecture shouldbe designed lightweight as it will be deployed to an embedded system. In thiswork, we propose an HCI system for dynamic recognition of driver micro handgestures, which can have a crucial impact in automotive sector especially forsafety related issues. For this purpose, we initially collected a dataset namedDriver Micro Hand Gestures (DriverMHG), which consists of RGB, depth andinfrared modalities. The challenges for dynamic recognition of micro handgestures have been addressed by proposing a lightweight convolutional neuralnetwork (CNN) based architecture which operates online efficiently with asliding window approach. For the CNN model, several 3-dimensional resourceefficient networks are applied and their performances are analyzed. Onlinerecognition of gestures has been performed with 3D-MobileNetV2, which providedthe best offline accuracy among the applied networks with similar computationalcomplexities. The final architecture is deployed on a driver simulatoroperating in real-time. We make DriverMHG dataset and our source code publiclyavailable.

DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework