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

Accident of struck-by machines is one of the leading causes of casualties onconstruction sites. Monitoring workers' proximities to avoid human-machinecollisions has aroused great concern in construction safety management.Existing methods are either too laborious and costly to apply extensively, orlacking spatial perception for accurate monitoring. Therefore, this studyproposes a novel framework for proximity monitoring using only an ordinary 2Dcamera to realize real-time human-machine collision warning, which is designedto integrate a monocular 3D object detection model to perceive spatialinformation from 2D images and a post-processing classification module toidentify the proximity as four predefined categories: Dangerous, PotentiallyDangerous, Concerned, and Safe. A virtual dataset containing 22000 images with3D annotations is constructed and publicly released to facilitate the systemdevelopment and evaluation. Experimental results show that the trained 3Dobject detection model achieves 75% loose AP within 20 meters. Besides, theimplemented system is real-time and camera carrier-independent, achieving an F1of roughly 0.8 within 50 meters under specified settings for machines ofdifferent sizes. This study preliminarily reveals the potential and feasibilityof proximity monitoring using only a 2D camera, providing a new promising andeconomical way for early warning of human-machine collisions.

Monocular 2D Camera-based Proximity Monitoring for Human-Machine Collision Warning on Construction Sites