Vision-Based Warning System for Maintenance Personnel at Short-Term Roadworks Site

This paper proposes a vision-based warning system for the maintenance personnel working at short-term roadworks sites. Traditional solutions use passive protection, like setting up traffic cones and safety beacons. However, such methods cannot function as physical safety barriers to separate working areas from used lanes. In contrast, the proposed system provides active protection, leveraging acoustic and visual warning signals to help road workers be cautious of approaching vehicles before they pass the working area. For the reduction of too many warnings to relieve a disturbance of road workers, a traffic flow check algorithm is implemented, by which about 80% of the useless notices can be filtered. The evaluations are conducted in laboratory conditions and the real world, proving the applicability and reliability of the system.