999 Part 1(1).mp4 <UPDATED • 2024>

Because real-world collision data is dangerous and expensive to collect, researchers used a approach:

: The video frames were used to train YOLOv7 (You Only Look Once) and Mask-RCNN models to detect objects and estimate distances accurately in real-time. 999 Part 1(1).mp4

: The system significantly decreased the number of "nuisance" alarms compared to static sensors, as it understands when a worker or another machine is approaching safely for collaboration. Because real-world collision data is dangerous and expensive

: Distinguishes between workers, excavators, and forklifts. 999 Part 1(1).mp4