Development and implementation of an AI backed human detection safety system for pilings rigs and cranes-PPT Presentation

PPT Presentation

Pdf Summary

The presentation describes the development of CSS Live, an AI-backed human-detection and safety system for piling rigs and cranes. It addresses the risk of workers being struck by moving plant, which accounts for around 10% of UK construction-site fatalities, alongside many injuries and near misses worldwide.<br /><br />Because physical separation and full automation are not currently feasible for all geotechnical operations, the system uses technology to warn operators and intervene when people enter hazardous areas. Developed through successive camera-based systems, CSS Live is now deployed on a range of machines.<br /><br />The system uses eight external cameras, combining 360-degree imaging with high-definition distance cameras. Customizable detection zones trigger different responses: visual and audible warnings in the amber zone, and intervention in the red zone. When someone enters the red zone, tracking and slewing stop immediately, while other machine operations continue. Operators can also access a live 360-degree view, and workers receive external visual and audible signals.<br /><br />Retrofitting the system to specialist machinery requires substantial integration work, with solutions tailored to different manufacturers. Other challenges include refining zone layouts, reducing false alerts, managing data protection, and preventing operator complacency. The system is intended as an aid, not a replacement for safe working practices.<br /><br />To date, no human–plant-related incidents have occurred while CSS Live was operational. The system has also encouraged safer site behavior and generated cloud-based data to support ongoing analysis and improvement.

Keywords

CSS Live

AI-backed safety system

human detection

piling rigs

cranes

construction site safety

moving plant hazards

camera-based monitoring

hazard zones

operator alerts