SmartEye: wearable data collection for workplace safety analysis - ON-1191

Project type: Research
Desired discipline(s): Engineering - computer / electrical, Engineering, Kinesiology, Life Sciences, Computer science, Mathematical Sciences
Company: Oakglade Safety Solutions
Project Length: 4 to 6 months
Preferred start date: 06/01/2026
Language requirement: English
Location(s): Toronto, ON, Canada
No. of positions: 1
Desired education level: Master'sPhD
Open to applicants registered at an institution outside of Canada: No

About the company: 

SmartEye is an early-stage safety technology initiative focused on improving worker safety in high-risk environments such as construction and mining. The project is developing a wearable device that captures real-time worker data, including motion patterns and environmental context, to better understand how safety incidents and near-miss events occur in real working conditions.
Current safety practices rely heavily on manual observation and reporting, which limits visibility into dynamic site conditions. SmartEye bridges this gap by AI Augmented insights that support proactive hazard identification and prevention.
The initial phase of the project is developing a prototype system and conducting pilot deployments to collect real-world data. This data will be used to identify patterns in hazard exposure and support the development of AI-based safety detection models.

Describe the project.: 

This project focuses on developing and evaluating a prototype wearable system designed to collect real-world safety data from workers in construction and industrial environments.
The SmartEye prototype will capture event-triggered data, including motion (IMU) and visual context (short video clips or images), to identify how hazards occur during daily work activities. The primary goal of this project is not to build a fully commercialized product, but to generate meaningful datasets and insights that can inform future safety technologies.
The selected candidate(s) will work on analyzing collected data to identify patterns related to hazard exposure, near-miss events, and unsafe conditions. This will include exploring computer vision techniques for detecting PPE compliance, posture risks, or environmental hazards, as well as analyzing motion data to detect events such as slips, trips, or sudden impacts.
The project will also focus on structuring and labeling datasets, developing initial classification models, and translating raw data into actionable safety insights for supervisors and safety professionals.
The outcome of this research will help define which types of data are most valuable for improving workplace safety and will support the development of future AI-driven hazard detection systems.

Required expertise/skills: 

We are seeking candidates with experience in one or more of the following areas:
• Computer vision (OpenCV, TensorFlow, PyTorch)
• Machine learning / AI model development
• Data science and data analysis (Python, Pandas)
• Video and image processing
• Sensor data analysis (IMU / time-series data)
• Backend development (optional)
• Familiarity with Streamlit or dashboard tools (optional)
Assets:
• Experience working with real-world datasets
• Interest in occupational health and safety
• Experience with wearable technologies or IoT systems