Video-Based Fall Detection for Construction Workers Safe

Fall accidents are one of the leading causes for serious work related fatalities and injuries in the construction industry. Every year, construction workers get injured due to falling off of overhead platforms, elevated work stations or into holes in floors and openings in walls. In order to alleviate this issue, several research studies have been proposed for fall detection; however, their practical values in construction projects are still limited. The objective of this research is to investigate the fall detection with vision techniques, as video cameras are becoming more common on construction sites. The research focuses on the detection feasibility under 1) a single monocular camera and 2) a distributed camera network. The results are expected to build a solid foundation to create a vision-based fall detection solution for construction safety engineers, which could help them timely detect and rescue injured workers when fall accidents happen.

Faculty Supervisor:

Zhenhua Zhu

Student:

Xiaoning Ren

Partner:

GreenOwl Mobile

Discipline:

Engineering - civil

Sector:

Construction and infrastructure

University:

Program: