Key Performance Indicators (KPIs) are measurable values, used to monitor progress on specific business objectives. KPIs are often described against headcount, for example as a number of events per 100,000 people, or against working hours, for example per one million hours worked. This makes KPIs comparable between different organizations or parts of the same organization and over time. A survey of over 600 safety specialists found that the most measured safety KPI is reported accidents and injuries. This is a reactive or lagging measure - it only tells you when things have already gone wrong. It’s the most common KPI because with conventional approaches it’s the easiest to measure. Artificial intelligence, and in particular computer vision monitoring of CCTV, makes it practical to have more proactive, leading KPIs – measures that help you prevent accidents and injuries in the first place. Here are four safety KPIs that will help you move from reactive to proactive monitoring of occupational safety and health (OSH).
1. Computer vision to support audits and inspections
The second most common KPI in the survey was scores from audits and inspections. Because audits are labor intensive, organizations tend to use them infrequently - perhaps once or twice a year. Inspections might be required more often, but can result in a tick box exercise – a process to get out of the way on Friday afternoon before you go home. CV can monitor some items that audits and inspections would look at, but more accurately and in real-time, every day of the year. For example, CV can be configured to identify obstacles in walkways or doors left open. When you do an annual audit, you can compare the data from CV to assess the accuracy of the auditing process.
2. Near misses
Counting near misses was the next most popular form of KPI. Near miss schemes rely on people to identify and then report things which might have resulted in an accident or injury, but didn’t. This could include a pedestrian walking in front of a fork lift truck (FLT) causing the driver to brake sharply to avoid hitting them, causing a load to be dropped. If the load is damaged, the near miss might get reported – but how many times did pedestrians walk in front of vehicles without damage? Most people won’t repeatedly report the same near miss. Computer vision can be consistent and objective about reporting near misses. As well as providing a more accurate KPI, it provides better information for fixing the problem, for example with improved signage or altered routes.
3. Safe behaviors
Counting near misses – like the sharply braking FLT in the example above – gets you closer to a preventative approach than just counting accidents, but the near miss can still damage productivity. Well-written safe operating procedures and method statements describe the steps that are needed to achieve a task safely, without an accident. If you can identify critical points in these steps, you can measure these as an early indicator of safe operations. For example, a procedure describes what tools should be used, what PPE should be worn and where an activity should be carried out. Computer vision could report how often the correct PPE is being worn in the location required, and QR codes linked to a job management system could report on the tools being used. This would provide a leading KPI, indicating how often there was a measurable deviation from the procedure.
4. Training effectiveness
A smaller but still substantial number of organizations use the number of employees receiving safety training as a KPI. While training is essential for OHS, attending a training course doesn’t prove someone will apply their learning on the job. A training KPI could be supported by CV. For example, from observation a safety manager notices some workers over-reach rather than move. Movement ranges are defined, and CV is used to count how often workers over-reach. The problem is widespread. Training is provided. After the training, the over-reaching reduces on the day shift, but not on the night shift. Discussion with the workers identifies that the day-supervisor is supporting the new way of working, while the night-supervisor is still emphasizing speed over caution. The CV provides the information you need to make the training more effective.
It has been said that “what gets measured gets done”, but it is also true that poorly set KPIs have unintended consequences, such as pointless activities or under-reporting of incidents to achieve the right numbers, without making the workplace any safer or healthier. The good news is that computer vision now makes it more practical to collect meaningful and accurate KPIs that will support a proactive approach to OHS.