Wearable Sensors

Lead Researcher: Professor Christopher Chow

Forestry plantation and processing worksites often involve interaction between workers and machinery posing safety risks. Working with two sawmilling companies’, prototypes have been developed of an artificial intelligence learning system for detecting people and machinery. A prototype system has been developed and was trialled with videos taken of sawmill situations in place of being able to trial onsite due to COVID restrictions.

This project had a primary goal of understanding the needs, challenges, and opportunities of using sensor-based remote hazard monitoring, and developing a workwear embedded with such technology for harvesting and sawmilling operations to ensure the wellbeing of workers.

Four safety concerns / scenarios were identified as the priority of this project.

1. Human to vehicle (forklift and truck) - indoor
2. Human to vehicle (forklift and truck) – outdoor
3. Vehicle to vehicle – indoor (less common)
4. Vehicle to vehicle – outdoor

The project has successfully delivered an image-based detection algorithm which can accurately detect heavy equipment and staff to alert for potential collisions.

Our team: Chris Chow, Rameez Rameezdeen, Ivan Lee, Kutluyil Dogancay, Jill Dorrian, Jun Ahn, Jim O’Hehir and Braden Jenkin (Sylva Systems Pty Ltd)