: The study noted that moving machine parts (like an excavator's arm) can sometimes obstruct the view or cause perspective distortion, leading to slight distance errors.
Because real-world collision data is dangerous and expensive to collect, researchers used a approach:
The full research and technical details can be found in the article Dynamic Collision Alert System for Collaboration of Construction Equipment and Workers published in Buildings (MDPI). 999 Part 1(1).mp4
: Scenarios were built in Unity 3D to mimic real-world construction tasks, such as collaborative excavation.
: Recognizes if a worker is facing away or kneeling, which increases risk. : The study noted that moving machine parts
: Adjusts risk based on where the camera is mounted on the machine (e.g., blind spots). How the Video Was Created
: 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. : Recognizes if a worker is facing away
: By using the known size of objects and camera focal lengths, the system can estimate the distance of a worker or machine within a small margin of error.